fix: use ssh to clone private git repos in sandboxes

PLAN-responses-api: OpenAI Responses API as the default wire format

assets/agents/adversary/graph.yaml

@@ -37,7 +37,9 @@ variables:
     description: |
       JSON array of shell commands the CALLER declares for the deterministic
       run_checks stage — e.g. '["cargo test --all"]'. Never inferred from the
-      prompt; empty array = none declared.
+      prompt; empty array = none declared. Must not boot shared stacks or
+      services (compose projects, fixed ports) — those collide with the probe
+      lane running in parallel.
     default: '[]'
 
 settings:
@@ -52,6 +54,7 @@ settings:
 
 initial_state:
   project_dir_in: ''
+  parse_retries: 0
   criteria: []
   diff_spec: auto
   plan_notes: ''
@@ -88,6 +91,18 @@ nodes:
         Split compound criteria ("A and B") into separate entries when they are
         independently verifiable. When the caller supplied NO plan/criteria at
         all, emit an empty array — downstream fails closed.
+        An empty array is ONLY correct when the prompt genuinely contains no
+        plan/criteria section — when the prompt carries one (a "Plan /
+        acceptance criteria:" or "PLAN —" block), returning zero criteria is
+        an extraction FAILURE, never a valid result.
+        The caller's explicit enumeration is AUTHORITATIVE: when the caller
+        declares "these N are the (only) criteria" or supplies a numbered
+        criteria list, extract EXACTLY those N — never add entries they did
+        not enumerate. NEVER mine criteria from sections the caller labels as
+        context ("FACTS", "Quality bar", "context, not criteria", background
+        material) — route those into plan_notes / scope_notes / extra_context
+        instead. Splitting applies only WITHIN a declared criterion; when in
+        doubt, FEWER criteria, verbatim.
       - `diff_spec`: the git diff basis the caller named — a range, a ref/SHA,
         "staged", "worktree", or "auto" when unnamed (a caller phrase like
         "get_diff --base X" means diff_spec = "X").
@@ -159,7 +174,7 @@ nodes:
     branch: check_criterion
     output_key: crit_verdict
     collect_into: crit_verdicts
-    max_concurrency: 4
+    max_concurrency: 6
     next: holistic
 
   check_criterion:
@@ -340,7 +355,7 @@ nodes:
         observations:
           type: string
       required: [extra_complaints, observations]
-    max_iterations: 20
+    max_iterations: 45
     max_attempts: 2
     state_updates:
       holistic_failure: '{{output}}'

assets/agents/adversary/scripts/diff_facts.py

@@ -8,6 +8,7 @@ review proceeds fail-closed rather than crashing.
 """
 
 import json
+import re
 import os
 import subprocess
 
@@ -22,6 +23,22 @@ def load_state():
 
 
 state = load_state()
+
+# Zero criteria from a prompt that visibly carries a plan is an extraction
+# failure (observed non-deterministically live), not a fail-closed no-plan
+# run — re-run the parse ONCE before the verdict fails closed on it.
+_crit = state.get("criteria") or []
+_prompt = state.get("initial_prompt") or ""
+if not _crit and isinstance(_prompt, str) and re.search(
+    r"acceptance criteria|PLAN\s*—|Plan / acceptance", _prompt, re.I
+):
+    try:
+        _pr = int(state.get("parse_retries") or 0)
+    except (TypeError, ValueError):
+        _pr = 0
+    if _pr < 1:
+        print(json.dumps({"_next": "parse", "parse_retries": _pr + 1}))
+        raise SystemExit(0)
 proj = os.path.expanduser(
     (state.get("project_dir_in") or "").strip() or state.get("project_dir") or "."
 )
@@ -56,8 +73,13 @@ try:
         if line.startswith("+++ b/")
     })
     out["changed_files"] = files[:300]
+    if len(files) > 300:
+        out["diff_note"] += (
+            f" (file list capped at 300 of {len(files)} changed files — use the fs "
+            "tools for the rest)"
+        )
     if len(text) > MAX_DIFF_CHARS:
-        out["diff_note"] = (
+        out["diff_note"] += (
             f" (truncated to {MAX_DIFF_CHARS} chars of {len(text)} — use the fs tools "
             "to inspect files beyond the cut)"
         )

assets/agents/adversary/scripts/run_checks.py

@@ -51,11 +51,43 @@ GRAPH_STATE_FILE, so an inherited live state file would silently win.
 import json
 import os
 import signal
+import fcntl
 import subprocess
+import sys
 import time
 
 PER_COMMAND_TIMEOUT_SECS = 900
 TOTAL_DEADLINE_SECS = float(os.environ.get("ADVERSARY_RUN_CHECKS_DEADLINE_SECS") or 3300)
+STACK_LOCK_PATH = os.path.expanduser("~/.cache/coyote/review-stack.lock")
+STACK_LOCK_WAIT_SECS = float(os.environ.get("ADVERSARY_STACK_LOCK_WAIT_SECS") or 1200)
+
+
+def acquire_stack_lock():
+    """Serialize with the probe lane's shared-stack work (advisory flock on a
+    well-known path; the probe is instructed to flock the same file around
+    stack boot/teardown). Bounded wait so a hogged lock can never turn into a
+    false red verification: on timeout we proceed WITHOUT the lock and note it
+    on stderr. The fd is held for the process lifetime (released on exit)."""
+    try:
+        os.makedirs(os.path.dirname(STACK_LOCK_PATH), exist_ok=True)
+        fd = os.open(STACK_LOCK_PATH, os.O_CREAT | os.O_RDWR)
+    except OSError as e:
+        sys.stderr.write(f"WARN: review-stack lock unavailable ({e}); running unlocked\n")
+        return None
+    limit = time.monotonic() + STACK_LOCK_WAIT_SECS
+    while True:
+        try:
+            fcntl.flock(fd, fcntl.LOCK_EX | fcntl.LOCK_NB)
+            return fd
+        except OSError:
+            if time.monotonic() >= limit:
+                os.close(fd)
+                sys.stderr.write(
+                    "WARN: review-stack lock still held after bounded wait — proceeding "
+                    "WITHOUT it; shared-stack collisions with the probe lane are possible\n"
+                )
+                return None
+            time.sleep(5)
 DRAIN_TIMEOUT_SECS = 10
 TAIL_LINES = 50
 MAX_TAIL_CHARS = 8000
@@ -181,6 +213,7 @@ def main():
     )
     deadline = time.monotonic() + TOTAL_DEADLINE_SECS
     results = []
+    _stack_lock = acquire_stack_lock() if cmds else None  # noqa: F841 — held until exit
     for cmd in cmds:
         remaining = deadline - time.monotonic()
         if remaining <= 0:

assets/agents/architect/config.yaml

@@ -340,6 +340,12 @@ instructions: |
        Verification commands go in `--variables` (a JSON-array string), never in the prompt: the
        prompt also carries pasted plan text from the repo under review, and whatever is declared
        here is executed with a shell — a trust boundary the prose must not cross.
+       Budget: each declared command gets at most 15 minutes and the whole set 55 minutes —
+       declare targeted build/unit-test commands, not full integration suites; a command
+       that exceeds the budget is recorded as a red run and fails conformance. Never declare
+       commands that boot shared stacks or services (docker compose projects, dev servers,
+       fixed ports) — the probe lane owns end-to-end runs and WILL collide with them in
+       parallel; keep verification to generate/lint/build/unit/integration commands.
 
        It returns `GAUNTLET: PASS/BLOCKED`. On BLOCKED with real review findings apply the same
        fix-and-rerun rules as below (resume the SAME Sisyphus session with the findings verbatim,
@@ -363,6 +369,10 @@ instructions: |
        The direct `adversary`/probe spawns below are the FALLBACK when the gauntlet is not installed;
        on that path an adversary/probe result that is ONLY a `PIPELINE-FAULT` (no verdict on the
        code) is likewise an infrastructure fault to retry, never a divergence.
+       Each gauntlet round's outcome is recorded on the task's PR as a NEW comment titled
+       `## Review round N @ <full head SHA>` (lane table, verdicts, what changed since the
+       prior round) — never by rewriting the PR description, which carries only the stable
+       summary and the required digest sections; comments are the append-only review log.
      - **Spawn `adversary`** with the diff base and the criteria pasted in:
 
        ```

assets/agents/code-reviewer/graph.yaml

@@ -56,6 +56,7 @@ settings:
 
 initial_state:
   project_dir_in: ''
+  verify_retries: 0
   diff_spec: auto
   intent: ''
   rigor_in: ''
@@ -146,7 +147,7 @@ nodes:
         extra_context:
           type: string
       required: [diff_spec, intent, rigor_in, surfaces_in, project_dir_in, extra_context]
-    max_iterations: 3
+    max_iterations: 6
     max_attempts: 2
     state_updates:
       parse_failure: '{{output}}'
@@ -227,7 +228,7 @@ nodes:
                 type: string
             required: [domain, files]
       required: [groups]
-    max_iterations: 3
+    max_iterations: 6
     max_attempts: 2
     state_updates:
       refine_failure: '{{output}}'
@@ -435,6 +436,13 @@ nodes:
         (cross-domain concerns from the leaders' reports + teammate alerts, or "None"),
         `operational_history` (from prior_art_notes; "" when the lane didn't run),
         `org_context_section` (from org_context_notes; "" when the lane didn't run).
+      Prior review decisions supplied in the caller context are SETTLED: never
+      invert or re-litigate one on the same line without NEW evidence (the line
+      changed, a new failure appeared). If you believe a settled decision is
+      wrong, do not re-flag it as a finding — surface it in `cross_file` as an
+      explicit conflict citing the prior decision, so the human sees a
+      disagreement, not a flip-flop.
+
     prompt: |
       Domain reports ({{file_count}} changed files, grouped into the domain slices below):
       {{domain_reports}}
@@ -522,6 +530,14 @@ nodes:
     state_updates:
       verifier_output: '{{output}}'
     fallback: verdict
+    next: verify_gate
+
+  verify_gate:
+    id: verify_gate
+    type: script
+    description: Local verifier-fault retry — when the verifier completed but its output carries PIPELINE-FAULT markers (or the verifier died), re-run the cheap finding-verifier ONCE instead of letting the fault escalate into a full lane re-run at the gauntlet. Falls through to verdict when clean or out of retries; a gate crash falls forward on the declared edge.
+    script: scripts/verify_gate.py
+    timeout: 60
     next: verdict
 
   verdict:

assets/agents/code-reviewer/scripts/facts.py

@@ -80,6 +80,11 @@ except Exception as e:  # noqa: BLE001
 out["resolved_diff_spec"] = resolved
 out["changed_files"] = files[:300]
 out["file_count"] = len(files)
+if len(files) > 300:
+    notes.append(
+        f"file list truncated: {len(files)} changed files, only the first 300 are "
+        "grouped and reviewed"
+    )
 
 
 def diff_text():

assets/agents/code-reviewer/scripts/verdict.py

@@ -165,14 +165,45 @@ def main():
         if v.get("id") == "pipeline-fault"
         or (isinstance(v.get("note"), str) and v["note"].lstrip().startswith("PIPELINE-FAULT:"))
     ]
-    if fv_faults:
+    # parse_fault's sentinel = the verifier verified NOTHING (hard fault, lane-
-        first = fv_faults[0].get("note")
+    # degrading). Per-finding verify_fault / crash-guard notes = those findings
+    # simply stand UNVERIFIED (soft: proportionate NEEDS-HUMAN attention — a
+    # ~1 h lane re-run to re-check a few findings is the wrong trade, and the
+    # verify_gate node already retried the verifier locally once).
+    hard_fv = [v for v in fv_faults if v.get("id") == "pipeline-fault"]
+    soft_fv = [v for v in fv_faults if v.get("id") != "pipeline-fault"]
+
+    def _fv_detail(entries):
+        first = entries[0].get("note")
         detail = first.strip().replace("\n", " ") if isinstance(first, str) else ""
         if len(detail) > MAX_DETAIL_CHARS:
             detail = detail[: MAX_DETAIL_CHARS - 1] + "…"
+        return detail
+
+    soft_notes = []
+    if hard_fv:
         faults.append(
-            f"PIPELINE-FAULT: finding verification degraded — {len(fv_faults)} verifier "
+            "PIPELINE-FAULT: finding verification degraded — the verifier verified "
-            f"verdict(s) carry a pipeline fault ({detail})"
+            f"nothing ({_fv_detail(hard_fv)})"
+        )
+    if soft_fv:
+        soft_notes.append(
+            f"Verifier: {len(soft_fv)} finding(s) could not be verified (verifier "
+            f"branch fault: {_fv_detail(soft_fv)}) — they stand above UNVERIFIED; "
+            "verify them manually"
+        )
+    # Files beyond facts.py's 300-file cap were never grouped or reviewed —
+    # disclose the gap and force NEEDS-HUMAN with wording that does NOT match
+    # the gauntlet's degraded-run anchors (a lane re-run cannot fix a cap).
+    coverage_notes = []
+    try:
+        total_files = int(state.get("file_count") or 0)
+    except (TypeError, ValueError):
+        total_files = 0
+    if total_files > len(changed):
+        coverage_notes.append(
+            f"Coverage gap: {total_files - len(changed)} of {total_files} changed files "
+            "were NOT reviewed (file-list cap) — review them manually or split the PR"
         )
     # Keyed off synth_failure + a non-empty diff, NEVER off findings == [] —
     # a clean review legitimately has zero findings and stays MERGE-READY.
@@ -190,7 +221,7 @@ def main():
     # faults go FIRST and uncapped so the display cap can never hide one;
     # the trigger reason keys off the human-facing triggers alone
     has_triggers = bool(attention)
-    attention = faults + attention[:5]
+    attention = faults + soft_notes + coverage_notes + attention[:5]
 
     reasons = []
     if counts["🔴"]:
@@ -200,6 +231,13 @@ def main():
     if faults:
         # CONTRACT: review-gauntlet/verdict_gate.py anchors on this wording
         reasons.append("pipeline fault(s) recorded — degraded run")
+    if soft_notes:
+        # Deliberately does NOT match the gauntlet's degraded-run anchors:
+        # unverified findings are a human-attention item, not a re-runnable
+        # lane fault.
+        reasons.append(f"{len(soft_fv)} finding(s) unverified (verifier branch fault)")
+    if coverage_notes:
+        reasons.append(f"{total_files - len(changed)} changed file(s) not reviewed (file cap)")
     if has_triggers:
         reasons.append("always-human trigger(s) fired")
     verdict = "NEEDS-HUMAN" if reasons else "MERGE-READY"

assets/agents/code-reviewer/scripts/verify_gate.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+"""Local verifier-fault retry gate for the code-reviewer graph.
+
+finding-verifier converts its own branch faults into DATA (UNVERIFIABLE
+verdicts with a PIPELINE-FAULT: note, or parse_fault's pipeline-fault
+sentinel), so the verify agent node completes "successfully" and its
+max_attempts never fires. Without this gate the fault escalates all the
+way to the gauntlet, which re-runs the ENTIRE code-review lane (~1 h) to
+recover a ~4-minute verifier — the wrong trade. This gate re-runs just
+the verifier ONCE; if faults persist, verdict.py downgrades them to a
+proportionate NEEDS-HUMAN (findings stand, unverified).
+
+Anchored detection only: the JSON-encoded note prefix and the sentinel id
+— a finding merely QUOTING the marker mid-text does not trip it. Always
+exits 0 with valid JSON; a crash falls forward on the declared edge.
+"""
+import json
+import os
+import sys
+
+
+def load_state():
+    if path := os.environ.get("GRAPH_STATE_FILE"):
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+try:
+    state = load_state()
+    raw = state.get("verifier_output")
+    text = raw if isinstance(raw, str) else (json.dumps(raw) if raw is not None else "")
+    faulted = (
+        text.lstrip().startswith("Agent node failed:")
+        or '"note": "PIPELINE-FAULT:' in text
+        or "'note': 'PIPELINE-FAULT:" in text
+        or '"id": "pipeline-fault"' in text
+    )
+    try:
+        retries = int(state.get("verify_retries") or 0)
+    except (TypeError, ValueError):
+        retries = 0
+    if faulted and retries < 1:
+        sys.stderr.write(
+            "WARN: verifier output carries pipeline-fault markers — re-running "
+            "finding-verifier locally (attempt 2/2) before computing the verdict.\n"
+        )
+        print(json.dumps({"_next": "verify", "verify_retries": retries + 1}))
+    else:
+        print(json.dumps({"verify_retries": retries}))
+except Exception as e:  # never block the verdict
+    print(json.dumps({"verify_gate_error": f"verify_gate crashed: {e}"}))

assets/agents/finding-verifier/graph.yaml

@@ -25,7 +25,7 @@ variables:
 settings:
   max_loop_iterations: 8
   log_state_snapshots: true
-  timeout: 900
+  timeout: 3000
 
 initial_state:
   findings_list: []
@@ -174,7 +174,7 @@ nodes:
       - fs_read
       - fs_cat
       - fs_grep
-    max_iterations: 8
+    max_iterations: 14
     max_attempts: 2
     state_updates:
       verdict: '{{output}}'

assets/agents/probe/config.yaml

@@ -101,6 +101,14 @@ instructions: |
 
   ## Rules
 
+  0. **Shared-stack discipline (parallel review lanes).** Wrap every stack boot/teardown
+     (docker compose, dev servers, fixed-port services) in
+     `flock "$HOME/.cache/coyote/review-stack.lock" <command>` — the adversary's
+     verification stage holds the same lock. A held port NEVER justifies removing or
+     stopping a container you did not create THIS RUN: wait on the lock, pick another
+     port, or return INCONCLUSIVE naming the conflict. Killing another lane's container
+     is a defect, not a remedy.
+
   1. **Never modify implementation code.** Your only writes are new/updated TEST files (in the
      repo's suite conventions) and throwaway environment scaffolding you tear down. The
      implementer owns all fixes.

assets/agents/review-gauntlet/graph.yaml

@@ -51,6 +51,7 @@ settings:
   timeout: 69600
 
 initial_state:
+  retry_notes: []
   diff_spec: worktree
   plan_context: ''
   rigor: production
@@ -114,8 +115,10 @@ nodes:
         the change (absolute path preferred); empty string when the caller
         named none.
       - `plan_context`: the plan / spec / acceptance-criteria text the
-        implementation must satisfy, verbatim (or a file path the caller
+        implementation must satisfy, copied through VERBATIM — never
-        pointed at). Empty string when the caller supplied none.
+        summarize it and never replace pasted text with file paths or a
+        sentence saying it was included; the adversary lane fails closed on
+        whatever you drop. Empty string when the caller supplied none.
       - `rigor`: poc | prototype | production. Default "production" when
         not stated.
       - `security_posture`: prototype | standard | hardened. Default
@@ -404,6 +407,11 @@ nodes:
       The workspace may contain test files from an aborted earlier attempt of
       this lane; reconcile rather than duplicate.
 
+      Shared-stack rule: wrap any stack boot/teardown in
+      `flock "$HOME/.cache/coyote/review-stack.lock" <command>` (the adversary's
+      verification stage holds the same lock), and NEVER remove or stop containers
+      you did not create this run — a held port means wait, re-port, or INCONCLUSIVE.
+
       Derive expected behaviors from the plan/contract BEFORE reading
       implementation code, run existing suites first, then author spec-first
       tests for the uncovered delta. Return your USAGE_PROBE verdict.

assets/agents/review-gauntlet/scripts/retry_gate.py

@@ -30,6 +30,7 @@ hard rules:
 import json
 import os
 import re
+import sys
 import time
 
 # 69600 (graph timeout) − 2 × 11400 (largest lane envelope) − 1200 (script stages)
@@ -184,6 +185,26 @@ def main():
             "review_incomplete": incomplete,
         }
     )
+    prior_notes = state.get("retry_notes")
+    notes = [n for n in prior_notes if isinstance(n, str)] if isinstance(prior_notes, list) else []
+    for lane in declined:
+        notes.append(
+            f"lane {lane} faulted and was NOT re-run "
+            f"(attempts {attempts.get(lane, '?')}/{MAX_ATTEMPTS}"
+            + ("" if within_budget else "; wall-clock budget exhausted")
+            + ") — recorded in review_incomplete"
+        )
+    for lane in retry:
+        notes.append(
+            f"lane {lane} faulted (missing / sentinel-less / degraded report) — "
+            f"re-running: attempt {attempts.get(lane, 0) + 1}/{MAX_ATTEMPTS}"
+        )
+    if retry or declined:
+        # stderr is discarded on success by today's engine but is the
+        # forward-compatible live-visibility channel; retry_notes carries the
+        # same lines into the final report either way.
+        sys.stderr.write("WARN: " + " | ".join(notes[-(len(retry) + len(declined)):]) + "\n")
+    out["retry_notes"] = notes
     if retry:
         out["_next"] = "build_items"
     print(json.dumps(out))

assets/agents/review-gauntlet/scripts/signals.py

@@ -38,6 +38,25 @@ def git(*args):
 
 
 out = {"project_dir": proj}
+
+# Deterministic plan_context recovery: the parse LLM proved a lossy channel
+# for verbatim spec text (observed replacing ~4 KB of pasted criteria with
+# file paths + a summary sentence). When the raw prompt carries the callers'
+# labeled plan block, cut it out verbatim and override the extraction — but
+# only when the recovered block is LONGER, so a good extraction is never
+# degraded. The adversary lane fails closed on whatever goes missing here.
+_prompt = state.get("initial_prompt")
+if isinstance(_prompt, str) and _prompt:
+    _m = re.search(
+        r"Plan / acceptance criteria:\s*(.+?)"
+        r"(?=\n\s*(?:Local-run recipe|Forced lanes|Rigor:|Security posture:|Extra context)\b|\Z)",
+        _prompt,
+        re.S | re.I,
+    )
+    if _m:
+        _block = _m.group(1).strip()
+        if len(_block) > len((state.get("plan_context") or "").strip()):
+            out["plan_context"] = _block
 # retry_gate measures its wall-clock budget from this stamp; it is set
 # before the git work so a failed diff still starts the clock.
 if not state.get("gauntlet_started_at"):

assets/agents/review-gauntlet/scripts/verdict_gate.py

@@ -360,6 +360,11 @@ def main():
         + [f"| {lane} | {status} | {detail} |" for lane, (status, detail) in rows.items()]
     )
     md += "\n\n## Lane selection\n" + (state.get("lanes_summary") or "(none recorded)")
+    _notes = state.get("retry_notes")
+    if isinstance(_notes, list):
+        _shown = [n for n in _notes if isinstance(n, str)][:8]
+        if _shown:
+            md += "\n\n## Pipeline notes\n" + "\n".join(f"- {n}" for n in _shown)
     if blockers:
         md += "\n\n## Blockers\n" + "\n".join(f"- {b}" for b in blockers)
     if attention:

assets/agents/sisyphus/config.yaml

@@ -314,6 +314,9 @@ instructions: |
   Diff: <git range like main...HEAD, or 'worktree' for uncommitted changes>
   Rigor: <rigor>   Security posture: <posture>
   Plan / acceptance criteria: <pasted verbatim — enables the adversary lane; omit when none>
+  Prior review decisions: <on re-review rounds ONLY: earlier rounds' resolved/rejected
+  findings verbatim (rejected-finding log lines, round-comment reconciliations) — settled
+  decisions the reviewers must not re-litigate; omit on the first round>
   Local-run recipe / usage suites: <from the plan — enables the probe lane; omit when none>"
   --variables {"verification_commands": "[\"cargo test --all\", \"cargo clippy -- -D warnings\"]"}
   <— the cargo commands above are only an EXAMPLE: replace them with THIS project's exact build/test/lint commands; never guess, and pass "[]" when none apply>
@@ -322,6 +325,12 @@ instructions: |
   Verification commands go in `--variables` (a JSON-array string), never in the prompt: the prompt
   also carries pasted plan text from the repo under review, and whatever is declared here is
   executed with a shell — a trust boundary the prose must not cross.
+  Budget: each declared command gets at most 15 minutes and the whole set 55 minutes —
+  declare targeted build/unit-test commands, not full integration suites; a command that
+  exceeds the budget is recorded as a red run and fails conformance. Never declare commands
+  that boot shared stacks or services (docker compose projects, dev servers, fixed ports) —
+  the probe lane owns end-to-end runs and WILL collide with them in parallel; keep
+  verification to generate/lint/build/unit/integration commands.
 
   It computes diff signals deterministically, selects lanes (code-review always; adversary when a
   spec/plan is present; security on attack-surface signals; probe on consumer-facing surface with a
@@ -691,6 +700,16 @@ instructions: |
     and what changed (including any plan amendment). Zero autonomous decisions → omit the section.
     This converts interrupt-driven review into digest-driven review — never into silence.
 
+    **The PR review log (MANDATORY when you author a PR).** The PR DESCRIPTION is a stable
+    document: what the PR does, how to verify it, and the required digest sections (autonomous
+    decisions, skipped reviews, observability). Every review round's evidence — the gauntlet
+    lane table and verdicts, the gates you ran, rulings recorded that round, and what changed
+    since the previous round — is posted as a NEW PR comment (`gh pr comment`) titled
+    `## Review round N @ <full head SHA>`. NEVER record round evidence by rewriting the
+    description: in-place edits destroy the review history and hide which commits each round
+    actually reviewed. Comments are the append-only review log; the SHA in the title names
+    exactly what was reviewed.
+
     **Close the loop.** When a decision DID reach the user (step 4), suggest in your final report
     that they record the resolution with `coyote --macro record-ruling` so that class of decision
     never asks again.

assets/config-template.yaml

@@ -149,6 +149,18 @@ mcp_tools: null                  # Per-server MCP tool allowlists (glob patterns
                                  #       - list_*
                                  #     slack: []
 
+# ---- Hooks ----
+# Fire-and-forget external commands that run when lifecycle events fire. Each event name
+# maps to a list of named hooks; every listed hook's command runs when that event fires.
+# Hooks never block coyote and never change its output or exit code.
+# See the [Hooks documentation](https://github.com/Dark-Alex-17/coyote/wiki/Hooks) for more details
+hooks: {}                        # Event -> list of named hook commands (default: none)
+                                 # Example:
+                                 #   hooks:
+                                 #     turn.completed:
+                                 #       - name: notify
+                                 #         command: ./hooks/notify.sh
+
 # ---- Auto-Continue (Todo System) ----
 # The auto-continue system provides built-in task tracking for improved reliability.
 # When enabled, the model can create todo lists and the system will automatically
@@ -290,4 +302,28 @@ sync_models_ttl_hours: 24        # Hours before the synced model catalog is cons
 #
 # The claude, bedrock, and vertexai clients also support:
 #   prompt_cache: true                              # Enable Anthropic prompt caching (default: true)
+#
+# The openai and openai-compatible clients also support:
+#   wire_api: responses                             # Which OpenAI wire protocol to use; Possible values: responses and chat
+#                                                   # Defaults when unset: stock openai (no api_base) -> responses;
+#                                                   # openai with a custom api_base -> chat; openai-compatible -> chat.
+#                                                   # Codex OAuth always uses responses (`wire_api: chat` there is a config error)
+#
+# Patches are selected per wire: `chat_completions` patches only ever touch chat bodies. To patch
+# requests on the responses wire, use the `responses` key on the client `patch` block (same
+# <regex> -> url/body/headers shape as chat_completions):
+#   patch:
+#     responses:
+#       <regex>:
+#         body:
+#           <json>
+# Model patches likewise: the top-level `patch` keys apply to the chat wire only, and a
+# `responses:` sub-key applies to the responses wire only:
+#   models:
+#     - name: xxxx
+#       patch:
+#         responses:
+#           body:
+#             <json>
+# Env override per wire: COYOTE_PATCH_<client>_RESPONSES / COYOTE_PATCH_<client>_CHAT_COMPLETIONS
 __CLIENTS_BLOCK__

assets/functions/tools/web_search_coyote.sh

@@ -23,10 +23,16 @@ set -e
 #   - perplexity:*
 #   - ernie:*
 #   - claude:*                       (Anthropic native web_search server tool)
-#   - openai:gpt-4o-search-preview   (and -mini-; requires an api-key openai
+#   - openai:gpt-4o*/gpt-4.1*/gpt-5*/o3*/o4*
-#                                     client — the codex OAuth path uses the
+#     OpenAI serves web search through two different mechanisms depending on
-#                                     Responses API where this parameter
+#     the wire API the client resolves (the script cannot pick the wire):
-#                                     does not exist)
+#     Chat Completions serves it via `web_search_options` on the chat-only
+#     *-search-preview models, while the Responses API serves it via its
+#     native `web_search` tool on regular models. Both request patches are
+#     exported (request patching is wire-aware, so the resolved wire applies
+#     exactly one) and openai searches run as an attempt chain: the
+#     chat-completions mechanism first, then the Responses mechanism, and
+#     the search fails only when both attempts fail.
 # @env WEB_SEARCH_USE_CURRENT_MODEL=true Prefer the running session's model when it natively supports web search.
 # @env LLM_OUTPUT=/dev/stdout The output path
 
@@ -34,7 +40,7 @@ set -e
 supports_native_search() {
     case "$1" in
     gemini:* | vertexai:gemini-* | perplexity:* | ernie:* | claude:*) return 0 ;;
-    openai:gpt-4o*search-preview*) return 0 ;;
+    openai:gpt-4o* | openai:gpt-4.1* | openai:gpt-5* | openai:o3* | openai:o4*) return 0 ;;
     *) return 1 ;;
     esac
 }
@@ -46,7 +52,8 @@ export_search_patch() {
         COYOTE_PATCH_VERTEXAI_CHAT_COMPLETIONS \
         COYOTE_PATCH_ERNIE_CHAT_COMPLETIONS \
         COYOTE_PATCH_CLAUDE_CHAT_COMPLETIONS \
-        COYOTE_PATCH_OPENAI_CHAT_COMPLETIONS
+        COYOTE_PATCH_OPENAI_CHAT_COMPLETIONS \
+        COYOTE_PATCH_OPENAI_RESPONSES
 
     case "${1%%:*}" in
     gemini)
@@ -65,18 +72,67 @@ export_search_patch() {
         export COYOTE_PATCH_CLAUDE_CHAT_COMPLETIONS='{".*":{"body":{"tools":[{"type":"web_search_20250305","name":"web_search","max_uses":5}]}}}'
         ;;
     openai)
-        # Chat Completions native search exists only on the search-preview
+        # Both patches are exported; request patching is wire-aware, so the
-        # models; the regex scopes the patch so other OpenAI models run
+        # client's resolved wire applies exactly one of them. Each regex
-        # unpatched instead of erroring on an unsupported parameter.
+        # scopes its patch to the models that actually support that
+        # mechanism, so other OpenAI models run unpatched instead of
+        # erroring on an unsupported parameter:
+        #   - Chat Completions native search exists only on the chat-only
+        #     *-search-preview models (`web_search_options`).
+        #   - The Responses API serves search through its native
+        #     `web_search` tool, which only some model families support.
         export COYOTE_PATCH_OPENAI_CHAT_COMPLETIONS='{"gpt-4o.*search-preview.*":{"body":{"web_search_options":{}}}}'
+        export COYOTE_PATCH_OPENAI_RESPONSES='{"(gpt-4o|gpt-4\\.1|gpt-5|o3|o4).*":{"body":{"tools":[{"type":"web_search"}]}}}'
         ;;
     esac
 }
 
+# Maps an openai model to the one used for the chat-completions attempt:
+# Chat Completions web search is served only by the *-search-preview models.
+openai_chat_search_model() {
+    case "${1#openai:}" in
+    gpt-4o*search-preview*) echo "$1" ;;
+    gpt-4o-mini*) echo "openai:gpt-4o-mini-search-preview" ;;
+    *) echo "openai:gpt-4o-search-preview" ;;
+    esac
+}
+
+# Maps an openai model to the one used for the Responses attempt: the
+# *-search-preview models are chat-only and do not exist on /v1/responses,
+# so they map back to their base models.
+openai_responses_search_model() {
+    case "${1#openai:}" in
+    gpt-4o-mini-search-preview*) echo "openai:gpt-4o-mini" ;;
+    gpt-4o*search-preview*) echo "openai:gpt-4o" ;;
+    *) echo "$1" ;;
+    esac
+}
+
+# OpenAI attempt chain: try the chat-completions mechanism first (works when
+# the client's wire is chat); if that fails — e.g. the client resolved the
+# responses wire, where the search-preview models do not exist — retry with
+# the Responses mechanism on a responses-capable model. Fails when both
+# attempts fail.
+# shellcheck disable=SC2154
+run_openai_search() {
+    if coyote -m "$(openai_chat_search_model "$1")" "$argc_query" >>"$LLM_OUTPUT"; then
+        return 0
+    fi
+    echo "web_search: openai chat-completions attempt failed; retrying via the Responses API" >&2
+    coyote -m "$(openai_responses_search_model "$1")" "$argc_query" >>"$LLM_OUTPUT"
+}
+
 # shellcheck disable=SC2154
 run_search() {
     export_search_patch "$1"
-    coyote -m "$1" "$argc_query" >>"$LLM_OUTPUT"
+    case "$1" in
+    openai:*)
+        run_openai_search "$1"
+        ;;
+    *)
+        coyote -m "$1" "$argc_query" >>"$LLM_OUTPUT"
+        ;;
+    esac
 }
 
 main() {

assets/hooks/log-events.sh

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+# Event-logging hook: appends a timestamped snapshot of every COYOTE_* env var
+# to a log file, so you can see exactly which events fire and what context
+# each one carries.
+#
+# Env vars read:
+#   COYOTE_HOOK_LOG   log file to append to (default: /tmp/coyote-hooks.log)
+#   COYOTE_*          everything coyote sets for the event is dumped verbatim
+#
+# Secrets (COYOTE_SECRET_*) are excluded from the snapshot; widening the grep
+# filter below opts into logging them.
+#
+# Wire it up under `hooks:` in your config.yaml (any event works):
+#   hooks:
+#     tool.completed:
+#       - name: log-events
+#         command: ./hooks/log-events.sh
+#
+# A relative command path like ./hooks/log-events.sh resolves against the
+# coyote config directory for global hooks, so this works with the default
+# hooks dir.
+#
+# See https://github.com/Dark-Alex-17/coyote/wiki/Hooks for the full list of
+# events and env vars. Hooks are fire-and-forget: this script never fails
+# loudly, and coyote ignores its exit code either way.
+
+set -u
+
+log_file="${COYOTE_HOOK_LOG:-/tmp/coyote-hooks.log}"
+
+# The default lives in shared /tmp: refuse to append through a symlink someone
+# else planted there. Point COYOTE_HOOK_LOG at a private path to avoid the
+# shared directory entirely.
+[ -L "$log_file" ] && exit 0
+umask 077
+{
+  echo "=== $(date '+%Y-%m-%dT%H:%M:%S%z') ${COYOTE_EVENT:-unknown}"
+  env | grep '^COYOTE_' | grep -v '^COYOTE_SECRET_' | sort
+  echo
+} >> "$log_file" 2> /dev/null || true

assets/hooks/notify.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+# Desktop-notification hook: posts a notification describing the event that
+# fired, falling back to a message on the controlling terminal when no
+# notifier is present.
+#
+# Env vars read (set by coyote when the hook fires):
+#   COYOTE_EVENT        dotted event name, e.g. turn.completed
+#   COYOTE_AGENT_NAME   agent name, when the event carries one
+#   COYOTE_TOOL_NAME    tool name, when the event carries one
+#
+# Wire it up under `hooks:` in your config.yaml:
+#   hooks:
+#     turn.completed:
+#       - name: notify
+#         command: ./hooks/notify.sh
+#
+# A relative command path like ./hooks/notify.sh resolves against the coyote
+# config directory for global hooks, so this works with the default hooks dir.
+#
+# See https://github.com/Dark-Alex-17/coyote/wiki/Hooks for the full list of
+# events and env vars. Hooks are fire-and-forget: this script never fails
+# loudly, and coyote ignores its exit code either way.
+
+set -u
+
+title="coyote"
+body="${COYOTE_EVENT:-event}"
+[ -n "${COYOTE_AGENT_NAME:-}" ] && body="$body agent=$COYOTE_AGENT_NAME"
+[ -n "${COYOTE_TOOL_NAME:-}" ] && body="$body tool=$COYOTE_TOOL_NAME"
+
+if command -v notify-send > /dev/null 2>&1; then
+  notify-send "$title" "$body" 2> /dev/null || true
+elif command -v osascript > /dev/null 2>&1; then
+  # $body carries model-influenced values (e.g. tool names); strip quotes and
+  # backslashes so it cannot escape the AppleScript string literal.
+  safe_body=${body//[\"\\]/}
+  osascript -e "display notification \"$safe_body\" with title \"$title\"" 2> /dev/null || true
+else
+  # coyote discards hook stdout, so aim the fallback at the controlling
+  # terminal when one exists; plain stdout keeps direct/manual runs working.
+  { echo "[$title] $body" > /dev/tty; } 2> /dev/null || echo "[$title] $body"
+fi

config.example.yaml

@@ -206,6 +206,18 @@ enabled_macros: null              # Which macros are invocable by default (no ro
                                   # Example (comma-separated form):
                                   #   enabled_macros: generate-commit-message,review
 
+# ---- Hooks ----
+# Fire-and-forget external commands that run when lifecycle events fire. Each event name
+# maps to a list of named hooks; every listed hook's command runs when that event fires.
+# Hooks never block coyote and never change its output or exit code.
+# See the [Hooks documentation](https://github.com/Dark-Alex-17/coyote/wiki/Hooks) for more details
+hooks: {}                         # Event -> list of named hook commands (default: none)
+                                  # Example:
+                                  #   hooks:
+                                  #     turn.completed:
+                                  #       - name: notify
+                                  #         command: ./hooks/notify.sh
+
 # ---- Auto-Continue (Todo System) ----
 # The auto-continue system provides built-in task tracking for improved reliability.
 # When enabled, the model can create todo lists and the system will automatically
@@ -338,6 +350,9 @@ clients:
     api_base: https://api.openai.com/v1               # Optional
     api_key: '{{OPENAI_API_KEY}}'                     # You can either hard-code or inject secrets from the Coyote vault
     organization_id: org-xxx                          # Optional
+    auth: null                                        # When set to 'oauth', Coyote will use OAuth instead of an API key
+                                                      # Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
+    # Supports a custom `oauth:` block like the claude client below. `api_base` is REQUIRED with it
 
   # For any platform compatible with OpenAI's API
   - type: openai-compatible
@@ -385,6 +400,20 @@ clients:
     auth: null                                          # When set to 'oauth', Coyote will use OAuth instead of an API key
                                                         # Authenticate with `coyote --authenticate` or `.authenticate` in the REPL
     prompt_cache: true                                  # Optional - enable Anthropic prompt caching (default: true)
+    # Optional: custom OAuth endpoints (e.g. a private gateway). Requires `auth: oauth` above.
+    # With `auth: oauth` and no `oauth:` block you get the stock Claude Pro/Max provider; adding
+    # `oauth:` switches to generic OAuth against your endpoints (the Claude-Code system-prefix
+    # and anthropic-beta header are not sent). An `oauth:` block makes `api_base` REQUIRED —
+    # Coyote refuses to fall back to api.anthropic.com with a gateway token.
+    # auth: oauth
+    # api_base: https://gateway.example/anthropic/v1
+    # oauth:
+    #   client_id: '{{GATEWAY_CLIENT_ID}}'
+    #   device_authorization_url: https://auth.gateway.example/oauth/device_authorization
+    #   token_url: https://auth.gateway.example/oauth/token
+    #   flow: device_code
+    #   scopes: [claude.chat]
+    #   resource: https://gateway.example/v1
 
   # See https://docs.mistral.ai/
   - type: openai-compatible

models.yaml

@@ -351,6 +351,10 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -370,6 +374,10 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -429,6 +437,10 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
     max_output_tokens: 100000
     supports_function_calling: true
     reasoning_levels:
@@ -540,6 +552,12 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
+          reasoning:
+            effort: high
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -556,6 +574,12 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
+          reasoning:
+            effort: high
     supports_vision: true
     supports_function_calling: true
     system_prompt_prefix: Formatting re-enabled
@@ -571,6 +595,12 @@
         max_tokens: null
         temperature: null
         top_p: null
+      responses:
+        body:
+          temperature: null
+          top_p: null
+          reasoning:
+            effort: high
     max_output_tokens: 100000
     supports_vision: true
     supports_function_calling: true
@@ -2234,6 +2264,14 @@
     - high
     - xhigh
     - max
+  - name: zai-org/glm-5.2-maas
+    type: chat
+    max_input_tokens: 1000000
+    input_price: 1.4
+    output_price: 4.4
+    cache_read_price: 0.14
+    max_output_tokens: 64000
+    supports_function_calling: true
   - name: claude-fable-5@default
     type: chat
     max_input_tokens: 1000000
@@ -3092,10 +3130,10 @@
   - name: au.anthropic.claude-opus-5
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3140,10 +3178,10 @@
   - name: jp.anthropic.claude-opus-5
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3156,10 +3194,10 @@
   - name: us.anthropic.claude-opus-5
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     require_max_tokens: true
     supports_vision: true
@@ -3377,10 +3415,10 @@
   - name: au.anthropic.claude-sonnet-5
     type: chat
     max_input_tokens: 1000000
-    input_price: 2.0
+    input_price: 2.2
-    output_price: 10.0
+    output_price: 11.0
-    cache_read_price: 0.2
+    cache_read_price: 0.22
-    cache_write_price: 2.5
+    cache_write_price: 2.75
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3425,10 +3463,10 @@
   - name: jp.anthropic.claude-sonnet-5
     type: chat
     max_input_tokens: 1000000
-    input_price: 2.0
+    input_price: 2.2
-    output_price: 10.0
+    output_price: 11.0
-    cache_read_price: 0.2
+    cache_read_price: 0.22
-    cache_write_price: 2.5
+    cache_write_price: 2.75
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3441,10 +3479,10 @@
   - name: us.anthropic.claude-sonnet-5
     type: chat
     max_input_tokens: 1000000
-    input_price: 2.0
+    input_price: 2.2
-    output_price: 10.0
+    output_price: 11.0
-    cache_read_price: 0.2
+    cache_read_price: 0.22
-    cache_write_price: 2.5
+    cache_write_price: 2.75
     max_output_tokens: 128000
     require_max_tokens: true
     supports_vision: true
@@ -3507,10 +3545,10 @@
   - name: us.anthropic.claude-fable-5
     type: chat
     max_input_tokens: 1000000
-    input_price: 10.0
+    input_price: 11.0
-    output_price: 50.0
+    output_price: 55.0
-    cache_read_price: 1.0
+    cache_read_price: 1.1
-    cache_write_price: 12.5
+    cache_write_price: 13.75
     max_output_tokens: 128000
     require_max_tokens: true
     supports_vision: true
@@ -3541,10 +3579,10 @@
   - name: au.anthropic.claude-opus-4-8
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3589,10 +3627,10 @@
   - name: jp.anthropic.claude-opus-4-8
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3605,10 +3643,10 @@
   - name: us.anthropic.claude-opus-4-8
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     require_max_tokens: true
     supports_vision: true
@@ -3716,10 +3754,10 @@
   - name: jp.anthropic.claude-opus-4-7
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3732,10 +3770,10 @@
   - name: us.anthropic.claude-opus-4-7
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     require_max_tokens: true
     supports_vision: true
@@ -3805,11 +3843,11 @@
   - name: anthropic.claude-sonnet-4-6
     type: chat
     max_input_tokens: 1000000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
-    max_output_tokens: 64000
+    max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
     reasoning_levels:
@@ -3839,7 +3877,7 @@
     output_price: 16.5
     cache_read_price: 0.33
     cache_write_price: 4.125
-    max_output_tokens: 64000
+    max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
     reasoning_levels:
@@ -3854,7 +3892,7 @@
     output_price: 15.0
     cache_read_price: 0.3
     cache_write_price: 3.75
-    max_output_tokens: 64000
+    max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
     reasoning_levels:
@@ -3865,11 +3903,11 @@
   - name: jp.anthropic.claude-sonnet-4-6
     type: chat
     max_input_tokens: 1000000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
-    max_output_tokens: 64000
+    max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
     reasoning_levels:
@@ -3880,11 +3918,11 @@
   - name: us.anthropic.claude-sonnet-4-6
     type: chat
     max_input_tokens: 1000000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
-    max_output_tokens: 64000
+    max_output_tokens: 128000
     require_max_tokens: true
     supports_vision: true
     supports_function_calling: true
@@ -3898,10 +3936,10 @@
     type: chat
     real_name: us.anthropic.claude-sonnet-4-6
     max_input_tokens: 1000000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
     patch:
       body:
         inferenceConfig:
@@ -3932,10 +3970,10 @@
   - name: anthropic.claude-opus-4-6-v1
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3947,10 +3985,10 @@
   - name: au.anthropic.claude-opus-4-6-v1
     type: chat
     max_input_tokens: 1000000
-    input_price: 16.5
+    input_price: 5.5
-    output_price: 82.5
+    output_price: 27.5
-    cache_read_price: 1.65
+    cache_read_price: 0.55
-    cache_write_price: 20.625
+    cache_write_price: 6.875
     max_output_tokens: 128000
     supports_vision: true
     supports_function_calling: true
@@ -3992,10 +4030,10 @@
   - name: us.anthropic.claude-opus-4-6-v1
     type: chat
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 128000
     require_max_tokens: true
     supports_vision: true
@@ -4010,10 +4048,10 @@
     type: chat
     real_name: us.anthropic.claude-opus-4-6-v1
     max_input_tokens: 1000000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     patch:
       body:
         inferenceConfig:
@@ -4186,6 +4224,13 @@
     output_price: 1.85
     max_output_tokens: 81920
     supports_function_calling: true
+  - name: moonshot.kimi-k2-thinking
+    type: chat
+    max_input_tokens: 262143
+    input_price: 0.6
+    output_price: 2.5
+    max_output_tokens: 16000
+    supports_function_calling: true
   - name: anthropic.claude-opus-4-5-20251101-v1:0
     type: chat
     max_input_tokens: 200000
@@ -4231,10 +4276,10 @@
   - name: us.anthropic.claude-opus-4-5-20251101-v1:0
     type: chat
     max_input_tokens: 200000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     max_output_tokens: 64000
     require_max_tokens: true
     supports_vision: true
@@ -4247,10 +4292,10 @@
     type: chat
     real_name: us.anthropic.claude-opus-4-5-20251101-v1:0
     max_input_tokens: 200000
-    input_price: 5.0
+    input_price: 5.5
-    output_price: 25.0
+    output_price: 27.5
-    cache_read_price: 0.5
+    cache_read_price: 0.55
-    cache_write_price: 6.25
+    cache_write_price: 6.875
     patch:
       body:
         inferenceConfig:
@@ -4263,13 +4308,6 @@
     max_output_tokens: 24000
     require_max_tokens: true
     supports_vision: true
-  - name: moonshot.kimi-k2-thinking
-    type: chat
-    max_input_tokens: 262143
-    input_price: 0.6
-    output_price: 2.5
-    max_output_tokens: 16000
-    supports_function_calling: true
   - name: openai.gpt-oss-safeguard-120b
     type: chat
     max_input_tokens: 128000
@@ -4320,10 +4358,10 @@
   - name: au.anthropic.claude-haiku-4-5-20251001-v1:0
     type: chat
     max_input_tokens: 200000
-    input_price: 1.0
+    input_price: 1.1
-    output_price: 5.0
+    output_price: 5.5
-    cache_read_price: 0.1
+    cache_read_price: 0.11
-    cache_write_price: 1.25
+    cache_write_price: 1.375
     max_output_tokens: 64000
     supports_vision: true
     supports_function_calling: true
@@ -4350,20 +4388,20 @@
   - name: jp.anthropic.claude-haiku-4-5-20251001-v1:0
     type: chat
     max_input_tokens: 200000
-    input_price: 1.0
+    input_price: 1.1
-    output_price: 5.0
+    output_price: 5.5
-    cache_read_price: 0.1
+    cache_read_price: 0.11
-    cache_write_price: 1.25
+    cache_write_price: 1.375
     max_output_tokens: 64000
     supports_vision: true
     supports_function_calling: true
   - name: us.anthropic.claude-haiku-4-5-20251001-v1:0
     type: chat
     max_input_tokens: 200000
-    input_price: 1.0
+    input_price: 1.1
-    output_price: 5.0
+    output_price: 5.5
-    cache_read_price: 0.1
+    cache_read_price: 0.11
-    cache_write_price: 1.25
+    cache_write_price: 1.375
     max_output_tokens: 64000
     require_max_tokens: true
     supports_vision: true
@@ -4372,10 +4410,10 @@
     type: chat
     real_name: us.anthropic.claude-haiku-4-5-20251001-v1:0
     max_input_tokens: 200000
-    input_price: 1.0
+    input_price: 1.1
-    output_price: 5.0
+    output_price: 5.5
-    cache_read_price: 0.1
+    cache_read_price: 0.11
-    cache_write_price: 1.25
+    cache_write_price: 1.375
     patch:
       body:
         inferenceConfig:
@@ -4401,10 +4439,10 @@
   - name: au.anthropic.claude-sonnet-4-5-20250929-v1:0
     type: chat
     max_input_tokens: 200000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
     max_output_tokens: 64000
     supports_vision: true
     supports_function_calling: true
@@ -4431,20 +4469,20 @@
   - name: jp.anthropic.claude-sonnet-4-5-20250929-v1:0
     type: chat
     max_input_tokens: 200000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
     max_output_tokens: 64000
     supports_vision: true
     supports_function_calling: true
   - name: us.anthropic.claude-sonnet-4-5-20250929-v1:0
     type: chat
     max_input_tokens: 200000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
     max_output_tokens: 64000
     require_max_tokens: true
     supports_vision: true
@@ -4453,10 +4491,10 @@
     type: chat
     real_name: us.anthropic.claude-sonnet-4-5-20250929-v1:0
     max_input_tokens: 200000
-    input_price: 3.0
+    input_price: 3.3
-    output_price: 15.0
+    output_price: 16.5
-    cache_read_price: 0.3
+    cache_read_price: 0.33
-    cache_write_price: 3.75
+    cache_write_price: 4.125
     patch:
       body:
         inferenceConfig:
@@ -4628,6 +4666,47 @@
     output_price: 0.3
     max_output_tokens: 8192
     supports_function_calling: true
+  - name: apac.anthropic.claude-sonnet-4-20250514-v1:0
+    type: chat
+    max_input_tokens: 200000
+    input_price: 3.0
+    output_price: 15.0
+    cache_read_price: 0.3
+    cache_write_price: 3.75
+    max_output_tokens: 64000
+    supports_vision: true
+    supports_function_calling: true
+  - name: eu.anthropic.claude-sonnet-4-20250514-v1:0
+    type: chat
+    max_input_tokens: 200000
+    input_price: 3.0
+    output_price: 15.0
+    cache_read_price: 0.3
+    cache_write_price: 3.75
+    max_output_tokens: 64000
+    supports_vision: true
+    supports_function_calling: true
+  - name: global.anthropic.claude-sonnet-4-20250514-v1:0
+    type: chat
+    max_input_tokens: 200000
+    input_price: 3.0
+    output_price: 15.0
+    cache_read_price: 0.3
+    cache_write_price: 3.75
+    max_output_tokens: 64000
+    supports_vision: true
+    supports_function_calling: true
+  - name: us.anthropic.claude-sonnet-4-20250514-v1:0
+    type: chat
+    max_input_tokens: 200000
+    input_price: 3.0
+    output_price: 15.0
+    cache_read_price: 0.3
+    cache_write_price: 3.75
+    max_output_tokens: 64000
+    require_max_tokens: true
+    supports_vision: true
+    supports_function_calling: true
   - name: us.amazon.nova-premier-v1:0
     type: chat
     max_input_tokens: 300000
@@ -5306,6 +5385,19 @@
     reasoning_levels:
     - high
     - max
+  - name: kimi-k3
+    type: chat
+    max_input_tokens: 1048576
+    input_price: 3.0
+    output_price: 15.0
+    cache_read_price: 0.3
+    max_output_tokens: 1048576
+    supports_vision: true
+    supports_function_calling: true
+    reasoning_levels:
+    - low
+    - high
+    - max
   - name: glm-5.2
     type: chat
     max_input_tokens: 1000000
@@ -6956,9 +7048,9 @@
   - name: deepseek/deepseek-v4-pro-0813
     type: chat
     max_input_tokens: 1048576
-    input_price: 0.9834
+    input_price: 0.66
-    output_price: 2.9502
+    output_price: 1.98
-    cache_read_price: 0.0328
+    cache_read_price: 0.022
     max_output_tokens: 384000
     supports_function_calling: true
   - name: deepseek/deepseek-v4-pro-0813:batch
@@ -7364,14 +7456,6 @@
     max_output_tokens: 16384
     supports_vision: true
     supports_function_calling: true
-  - name: google/gemma-4-31b-it:batch
-    type: chat
-    max_input_tokens: 262144
-    input_price: 0.39
-    output_price: 0.97
-    max_output_tokens: 235929
-    supports_vision: true
-    supports_function_calling: true
   - name: google/gemma-4-31b-it:free
     type: chat
     max_input_tokens: 262144
@@ -7397,8 +7481,8 @@
   - name: gryphe/mythomax-l2-13b
     type: chat
     max_input_tokens: 8192
-    input_price: 0.06
+    input_price: 0.08
-    output_price: 0.06
+    output_price: 0.11
     max_output_tokens: 3686
   - name: ibm-granite/granite-4.0-h-micro
     type: chat
@@ -7588,8 +7672,8 @@
   - name: meta/muse-glimmer-30b
     type: chat
     max_input_tokens: 131072
-    input_price: 0.35
+    input_price: 0.3
-    output_price: 1.5
+    output_price: 1.1
     cache_read_price: 0.04
     max_output_tokens: 117964
     supports_vision: true
@@ -7670,7 +7754,7 @@
   - name: minimax/minimax-m1
     type: chat
     max_input_tokens: 1000000
-    input_price: 0.55
+    input_price: 0.4
     output_price: 2.2
     max_output_tokens: 40000
     supports_function_calling: true
@@ -7916,8 +8000,8 @@
   - name: mistralai/mistral-small-3.2-24b-instruct
     type: chat
     max_input_tokens: 256000
-    input_price: 0.075
+    input_price: 0.0938
-    output_price: 0.2
+    output_price: 0.25
     max_output_tokens: 16384
     supports_vision: true
     supports_function_calling: true
@@ -7980,18 +8064,18 @@
   - name: moonshotai/kimi-k2.7-code
     type: chat
     max_input_tokens: 262144
-    input_price: 0.71
+    input_price: 0.7062
-    output_price: 3.5
+    output_price: 3.21
-    cache_read_price: 0.15
+    cache_read_price: 0.18
     max_output_tokens: 235929
     supports_vision: true
     supports_function_calling: true
   - name: moonshotai/kimi-k3
     type: chat
     max_input_tokens: 1048576
-    input_price: 2.6481
+    input_price: 3.0
-    output_price: 13.2827
+    output_price: 15.0
-    cache_read_price: 0.3026
+    cache_read_price: 0.3
     max_output_tokens: 943718
     supports_vision: true
     supports_function_calling: true
@@ -8053,9 +8137,8 @@
   - name: nvidia/nemotron-3-nano-30b-a3b
     type: chat
     max_input_tokens: 262144
-    input_price: 0.05
+    input_price: 0.06
-    output_price: 0.2
+    output_price: 0.24
-    cache_read_price: 0.03
     max_output_tokens: 235929
     supports_function_calling: true
   - name: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
@@ -8083,10 +8166,10 @@
   - name: nvidia/nemotron-3-ultra-550b-a55b
     type: chat
     max_input_tokens: 262144
-    input_price: 0.6
+    input_price: 0.625
-    output_price: 2.4
+    output_price: 3.125
-    cache_read_price: 0.12
+    cache_read_price: 0.1875
-    max_output_tokens: 182520
+    max_output_tokens: 32768
     supports_function_calling: true
   - name: nvidia/nemotron-3-ultra-550b-a55b:free
     type: chat
@@ -8969,12 +9052,6 @@
     cache_read_price: 0.03
     max_output_tokens: 117964
     supports_function_calling: true
-  - name: openai/gpt-oss-20b:batch
-    type: chat
-    max_input_tokens: 131072
-    input_price: 0.05
-    output_price: 0.2
-    max_output_tokens: 117964
   - name: openai/gpt-oss-safeguard-20b
     type: chat
     max_input_tokens: 131072
@@ -9378,9 +9455,9 @@
   - name: qwen/qwen3-vl-30b-a3b-instruct
     type: chat
     max_input_tokens: 262144
-    input_price: 0.15
+    input_price: 0.13
-    output_price: 0.6
+    output_price: 0.52
-    max_output_tokens: 16384
+    max_output_tokens: 32768
     supports_vision: true
     supports_function_calling: true
   - name: qwen/qwen3-vl-30b-a3b-thinking
@@ -9689,6 +9766,14 @@
     input_price: 0.65
     output_price: 0.75
     max_output_tokens: 16384
+  - name: stealth/union-alpha
+    type: chat
+    max_input_tokens: 262144
+    input_price: 0.0
+    output_price: 0.0
+    max_output_tokens: 131072
+    supports_vision: true
+    supports_function_calling: true
   - name: stepfun/step-3.5-flash
     type: chat
     max_input_tokens: 262144
@@ -9773,7 +9858,6 @@
     input_price: 0.4
     output_price: 0.4
     max_output_tokens: 819200
-    supports_function_calling: true
   - name: thinkingmachines/inkling
     type: chat
     max_input_tokens: 1048576
@@ -9792,15 +9876,6 @@
     max_output_tokens: 262144
     supports_vision: true
     supports_function_calling: true
-  - name: thinkingmachines/inkling-small:batch
-    type: chat
-    max_input_tokens: 524288
-    input_price: 0.5
-    output_price: 1.2
-    cache_read_price: 0.1
-    max_output_tokens: 471859
-    supports_vision: true
-    supports_function_calling: true
   - name: thinkingmachines/inkling-small:free
     type: chat
     max_input_tokens: 1048576
@@ -10020,7 +10095,7 @@
     input_price: 1.4
     output_price: 4.4
     cache_read_price: 0.14
-    max_output_tokens: 128000
+    max_output_tokens: 131072
     supports_function_calling: true
   - name: z-ai/glm-5.2:batch
     type: chat
@@ -10030,6 +10105,12 @@
     cache_read_price: 0.07
     max_output_tokens: 943718
     supports_function_calling: true
+  - name: z-ai/glm-5.2:free
+    type: chat
+    max_input_tokens: 32768
+    input_price: 0.0
+    output_price: 0.0
+    max_output_tokens: 29491
   - name: z-ai/glm-5.3
     type: chat
     max_input_tokens: 1310720
@@ -10041,9 +10122,9 @@
   - name: z-ai/glm-5.3-flash
     type: chat
     max_input_tokens: 1310720
-    input_price: 0.15
+    input_price: 0.09
-    output_price: 0.5
+    output_price: 0.3
-    cache_read_price: 0.03
+    cache_read_price: 0.018
     max_output_tokens: 131072
     supports_vision: true
     supports_function_calling: true
@@ -10133,8 +10214,8 @@
   - name: ~deepseek/deepseek-v4-flash-latest
     type: chat
     max_input_tokens: 1310720
-    input_price: 0.04
+    input_price: 0.03
-    output_price: 0.1
+    output_price: 0.13
     cache_read_price: 0.01
     max_output_tokens: 393216
     supports_function_calling: true

quirks.yaml

@@ -51,6 +51,10 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
     - match: "o3"
       system_prompt_prefix: Formatting re-enabled
       patch:
@@ -58,6 +62,10 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
     - match: "o3-mini"
       system_prompt_prefix: Formatting re-enabled
       patch:
@@ -65,6 +73,10 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
   models:
     - name: text-embedding-3-large
       type: embedding
@@ -94,6 +106,12 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
+            reasoning:
+              effort: high
     - name: o3-high
       real_name: o3
       max_input_tokens: 200000
@@ -108,6 +126,12 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
+            reasoning:
+              effort: high
     - name: o3-mini-high
       max_output_tokens: 100000
       real_name: o3-mini
@@ -123,6 +147,12 @@
           max_tokens: null
           temperature: null
           top_p: null
+        responses:
+          body:
+            temperature: null
+            top_p: null
+            reasoning:
+              effort: high
     - name: chat-latest
       max_input_tokens: 400000
       max_output_tokens: 128000

scripts/usage-probe-hooks.sh

@@ -0,0 +1,232 @@
+#!/usr/bin/env bash
+# Black-box usage-pattern probe for the coyote hook system.
+#
+# Verifies, against a REAL built `coyote` binary in a clean/isolated
+# COYOTE_CONFIG_DIR (dry_run:true, no network/LLM credentials required):
+#   A) exactly one turn.started + one turn.completed + one llm.request.completed
+#      fire per headless run, with correctly scoped env vars (no cross-event
+#      extras leakage).
+#   B) a failing/missing-script hook never changes coyote's stdout, stderr, or
+#      exit code.
+#   C) `coyote --install-builtins hooks` installs both bundled example scripts
+#      0755 into <config_dir>/hooks via the real CLI, and a second invocation
+#      (force reinstall) overwrites local edits back to the packaged content.
+#   D) `coyote --agent <bundled-agent> --info` (an inspection flag) fires ZERO
+#      agent.* hook events.
+#
+# Not covered here (see src/function/mod.rs tests for tool.* + payload-file
+# coverage instead): a live tool.started firing requires a real LLM round
+# trip that actually decides to call a tool; dry_run's echo_messages() path
+# never invokes tools, so it cannot be exercised via this recipe.
+#
+# Usage: scripts/usage-probe-hooks.sh
+# Requires: a `coyote` binary on PATH or at ./target/debug/coyote or
+# ./target/release/coyote (build with `cargo build --bin coyote` first).
+
+set -euo pipefail
+
+REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+BIN="${COYOTE_BIN:-}"
+if [ -z "$BIN" ]; then
+  if [ -x "$REPO_ROOT/target/debug/coyote" ]; then
+    BIN="$REPO_ROOT/target/debug/coyote"
+  elif [ -x "$REPO_ROOT/target/release/coyote" ]; then
+    BIN="$REPO_ROOT/target/release/coyote"
+  else
+    echo "No coyote binary found; run 'cargo build --bin coyote' first." >&2
+    exit 2
+  fi
+fi
+
+WORKDIR="$(mktemp -d)"
+trap 'rm -rf "$WORKDIR"' EXIT
+
+fail() {
+  echo "FAIL: $1" >&2
+  exit 1
+}
+
+write_dryrun_config() {
+  # $1 = config dir, $2..$n = extra YAML fragment lines appended verbatim
+  local dir="$1"
+  shift
+  cat > "$dir/config.yaml" <<'BASE'
+model: dryrun:dry-model
+dry_run: true
+clients:
+  - type: openai
+    name: dryrun
+    auth: none
+    api_key: 'unused'
+    models:
+      - name: dry-model
+        max_input_tokens: 100000
+        supports_function_calling: true
+save: false
+memory: false
+stream: false
+BASE
+  if [ "$#" -gt 0 ]; then
+    printf '%s\n' "$@" >> "$dir/config.yaml"
+  fi
+}
+
+echo "== Scenario A: turn/llm hook cadence and env scoping =="
+CFG_A="$WORKDIR/a"
+mkdir -p "$CFG_A"
+TS_LOG="$WORKDIR/turn-started.log"
+TC_LOG="$WORKDIR/turn-completed.log"
+LC_LOG="$WORKDIR/llm-completed.log"
+write_dryrun_config "$CFG_A" "hooks:" \
+  "  turn.started:" \
+  "    - name: probe" \
+  "      command: \"{ echo \\\"EVENT=\$COYOTE_EVENT NAME=\$COYOTE_HOOK_NAME\\\"; } >> $TS_LOG\"" \
+  "  turn.completed:" \
+  "    - name: probe" \
+  "      command: \"{ echo \\\"EVENT=\$COYOTE_EVENT NAME=\$COYOTE_HOOK_NAME\\\"; } >> $TC_LOG\"" \
+  "  llm.request.completed:" \
+  "    - name: probe-llm" \
+  "      command: \"{ echo \\\"EVENT=\$COYOTE_EVENT PROVIDER=\$COYOTE_LLM_PROVIDER MODEL=\$COYOTE_LLM_MODEL\\\"; } >> $LC_LOG\""
+
+COYOTE_CONFIG_DIR="$CFG_A" "$BIN" --no-stream "say exactly: hi" > /dev/null
+sleep 1
+
+[ "$(grep -c '^EVENT=turn.started' "$TS_LOG" 2>/dev/null || echo 0)" = "1" ] \
+  || fail "expected exactly one turn.started, got: $(cat "$TS_LOG" 2>/dev/null)"
+[ "$(grep -c '^EVENT=turn.completed' "$TC_LOG" 2>/dev/null || echo 0)" = "1" ] \
+  || fail "expected exactly one turn.completed, got: $(cat "$TC_LOG" 2>/dev/null)"
+[ "$(grep -c '^EVENT=llm.request.completed' "$LC_LOG" 2>/dev/null || echo 0)" = "1" ] \
+  || fail "expected exactly one llm.request.completed, got: $(cat "$LC_LOG" 2>/dev/null)"
+grep -q 'PROVIDER=dryrun MODEL=dryrun:dry-model' "$LC_LOG" \
+  || fail "llm.request.completed missing expected COYOTE_LLM_PROVIDER/MODEL: $(cat "$LC_LOG")"
+echo "PASS: exactly 1 turn.started + 1 turn.completed + 1 llm.request.completed, correctly scoped"
+
+echo "== Scenario B: failing/missing-script hooks never affect output or exit code =="
+CFG_B="$WORKDIR/b"
+mkdir -p "$CFG_B"
+write_dryrun_config "$CFG_B" "hooks:" \
+  "  turn.completed:" \
+  "    - name: failing" \
+  "      command: /nonexistent/script/does/not/exist" \
+  "    - name: exit1" \
+  "      command: \"exit 1\""
+CFG_BASE="$WORKDIR/base"
+mkdir -p "$CFG_BASE"
+write_dryrun_config "$CFG_BASE"
+
+exit_b=0
+COYOTE_CONFIG_DIR="$CFG_B" "$BIN" --no-stream "say exactly: hi" > "$WORKDIR/out_b.txt" 2> "$WORKDIR/err_b.txt" || exit_b=$?
+exit_base=0
+COYOTE_CONFIG_DIR="$CFG_BASE" "$BIN" --no-stream "say exactly: hi" > "$WORKDIR/out_base.txt" 2> "$WORKDIR/err_base.txt" || exit_base=$?
+
+[ "$exit_b" = "$exit_base" ] || fail "exit code differs: with-hooks=$exit_b baseline=$exit_base"
+diff -q "$WORKDIR/out_b.txt" "$WORKDIR/out_base.txt" > /dev/null || fail "stdout differs when a hook fails/is missing"
+diff -q "$WORKDIR/err_b.txt" "$WORKDIR/err_base.txt" > /dev/null || fail "stderr differs when a hook fails/is missing"
+echo "PASS: failing/missing-script hooks are invisible to stdout/stderr/exit code"
+
+echo "== Scenario C: coyote --install-builtins hooks (real CLI, clean config dir) =="
+CFG_C="$WORKDIR/c"
+mkdir -p "$CFG_C"
+
+out_install1="$WORKDIR/install1.out"
+COYOTE_CONFIG_DIR="$CFG_C" "$BIN" --install-builtins hooks > "$out_install1" 2>&1
+
+[ -f "$CFG_C/hooks/notify.sh" ] || fail "notify.sh was not installed: $(cat "$out_install1")"
+[ -f "$CFG_C/hooks/log-events.sh" ] || fail "log-events.sh was not installed: $(cat "$out_install1")"
+grep -q "Reinstalled bundled hooks" "$out_install1" \
+  || fail "expected confirmation message, got: $(cat "$out_install1")"
+
+if command -v stat > /dev/null 2>&1; then
+  mode_notify="$(stat -c '%a' "$CFG_C/hooks/notify.sh" 2>/dev/null || stat -f '%Lp' "$CFG_C/hooks/notify.sh")"
+  mode_log="$(stat -c '%a' "$CFG_C/hooks/log-events.sh" 2>/dev/null || stat -f '%Lp' "$CFG_C/hooks/log-events.sh")"
+  [ "$mode_notify" = "755" ] || fail "notify.sh mode is $mode_notify, expected 755"
+  [ "$mode_log" = "755" ] || fail "log-events.sh mode is $mode_log, expected 755"
+fi
+
+# Modify a script locally, then re-run --install-builtins hooks: it always
+# forces (no confirmation prompt on non-tty stdout), so the local edit must
+# be overwritten back to the packaged content.
+echo "# LOCALLY MODIFIED" > "$CFG_C/hooks/notify.sh"
+COYOTE_CONFIG_DIR="$CFG_C" "$BIN" --install-builtins hooks > "$WORKDIR/install2.out" 2>&1
+grep -q "LOCALLY MODIFIED" "$CFG_C/hooks/notify.sh" \
+  && fail "force reinstall did not overwrite the locally modified notify.sh"
+grep -q '^#!/usr/bin/env bash' "$CFG_C/hooks/notify.sh" \
+  || fail "notify.sh was not restored to the packaged script"
+echo "PASS: --install-builtins hooks installs both scripts 0755 and force-overwrites local edits"
+
+echo "== Scenario C2: cold-start auto-bootstrap fills the hooks dir but never forces =="
+CFG_C2="$WORKDIR/c2"
+mkdir -p "$CFG_C2/hooks"
+write_dryrun_config "$CFG_C2"
+
+# Every coyote invocation calls install_builtins() (force=false) before
+# dispatching any flag, so a plain run on a config dir with no hooks/ yet
+# must auto-populate it...
+rmdir "$CFG_C2/hooks" 2>/dev/null || true
+COYOTE_CONFIG_DIR="$CFG_C2" "$BIN" --no-stream "say exactly: hi" > /dev/null
+[ -f "$CFG_C2/hooks/notify.sh" ] || fail "cold-start run did not auto-install notify.sh"
+
+# ...but once a file exists, the non-force path must NEVER touch it again.
+echo "# LOCALLY MODIFIED" > "$CFG_C2/hooks/notify.sh"
+COYOTE_CONFIG_DIR="$CFG_C2" "$BIN" --no-stream "say exactly: hi" > /dev/null
+grep -q "LOCALLY MODIFIED" "$CFG_C2/hooks/notify.sh" \
+  || fail "a plain (non --install-builtins) invocation overwrote a locally modified hook script"
+echo "PASS: plain invocations auto-bootstrap missing hooks but never force-overwrite existing ones"
+
+echo "== Scenario C3: installed log-events.sh fires end-to-end via the documented relative path =="
+# Exercises the exact wiring promised in the script headers:
+#   command: ./hooks/log-events.sh   (resolves against the config dir)
+# and the script's own contract: COYOTE_HOOK_LOG override honored, log file
+# created 0600, COYOTE_SECRET_* values excluded from the snapshot.
+CFG_C3="$WORKDIR/c3"
+mkdir -p "$CFG_C3"
+HOOK_LOG="$WORKDIR/c3-hook.log"
+write_dryrun_config "$CFG_C3" "hooks:" \
+  "  turn.completed:" \
+  "    - name: log-events" \
+  "      command: ./hooks/log-events.sh"
+COYOTE_CONFIG_DIR="$CFG_C3" "$BIN" --install-builtins hooks > /dev/null 2>&1
+COYOTE_CONFIG_DIR="$CFG_C3" COYOTE_HOOK_LOG="$HOOK_LOG" COYOTE_SECRET_PROBE=hunter2 \
+  "$BIN" --no-stream "say exactly: hi" > /dev/null
+sleep 1
+
+[ -f "$HOOK_LOG" ] || fail "installed log-events.sh did not write to COYOTE_HOOK_LOG via relative-path wiring"
+[ "$(grep -c '^=== ' "$HOOK_LOG")" = "1" ] \
+  || fail "expected exactly one event block in the hook log, got: $(cat "$HOOK_LOG")"
+grep -q 'COYOTE_EVENT=turn.completed' "$HOOK_LOG" \
+  || fail "hook log missing COYOTE_EVENT=turn.completed: $(cat "$HOOK_LOG")"
+grep -q 'hunter2' "$HOOK_LOG" \
+  && fail "COYOTE_SECRET_* value leaked into the hook log"
+grep -q 'COYOTE_SECRET_' "$HOOK_LOG" \
+  && fail "COYOTE_SECRET_ variable name leaked into the hook log"
+if command -v stat > /dev/null 2>&1; then
+  mode_hook_log="$(stat -c '%a' "$HOOK_LOG" 2>/dev/null || stat -f '%Lp' "$HOOK_LOG")"
+  [ "$mode_hook_log" = "600" ] || fail "hook log mode is $mode_hook_log, expected 600"
+fi
+echo "PASS: relative-path wiring fires the installed log-events.sh; log is 0600 with secrets excluded"
+
+echo "== Scenario D: --agent <bundled> --info fires zero agent.* events =="
+CFG_D="$WORKDIR/d"
+mkdir -p "$CFG_D/agents"
+AGENT_LOG="$WORKDIR/agent-events.log"
+write_dryrun_config "$CFG_D" "hooks:" \
+  "  agent.started:" \
+  "    - name: probe-agent" \
+  "      command: \"echo AGENT_STARTED >> $AGENT_LOG\"" \
+  "  agent.completed:" \
+  "    - name: probe-agent" \
+  "      command: \"echo AGENT_DONE >> $AGENT_LOG\"" \
+  "  agent.failed:" \
+  "    - name: probe-agent" \
+  "      command: \"echo AGENT_FAILED >> $AGENT_LOG\""
+
+AGENT_NAME="$(ls "$REPO_ROOT/assets/agents" | head -1)"
+cp -r "$REPO_ROOT/assets/agents/$AGENT_NAME" "$CFG_D/agents/$AGENT_NAME"
+
+COYOTE_CONFIG_DIR="$CFG_D" "$BIN" --agent "$AGENT_NAME" --info > /dev/null 2>&1
+sleep 1
+[ -s "$AGENT_LOG" ] && fail "expected zero agent.* events from --agent --info, got: $(cat "$AGENT_LOG")"
+echo "PASS: --agent $AGENT_NAME --info fired zero agent.* hook events"
+
+echo
+echo "ALL SCENARIOS PASSED"

src/cli/mod.rs

@@ -609,6 +609,10 @@ mod tests {
             parse(&["--install-builtins", "mcp_config"]).install_builtins,
             Some(AssetCategory::McpConfig)
         );
+        assert_eq!(
+            parse(&["--install-builtins", "hooks"]).install_builtins,
+            Some(AssetCategory::Hooks)
+        );
     }
 
     #[test]
@@ -620,12 +624,14 @@ mod tests {
         assert!(category.get_name_and_aliases().any(|n| n == "mcp_config"));
         assert!(AssetCategory::NAMES.contains(&"mcp-config"));
         assert!(!AssetCategory::NAMES.contains(&"mcp_config"));
+        assert!(AssetCategory::NAMES.contains(&"hooks"));
 
         let filter = InstallFilter::McpConfig.to_possible_value().unwrap();
         assert_eq!(filter.get_name(), "mcp-config");
         assert!(filter.get_name_and_aliases().any(|n| n == "mcp_config"));
         assert!(InstallFilter::NAMES.contains(&"mcp-config"));
         assert!(!InstallFilter::NAMES.contains(&"mcp_config"));
+        assert!(InstallFilter::NAMES.contains(&"hooks"));
     }
 
     #[test]
@@ -685,6 +691,10 @@ mod tests {
             .filter,
             Some(InstallFilter::McpConfig)
         );
+        assert_eq!(
+            parse(&["--install", "https://github.com/x/y", "--filter", "hooks"]).filter,
+            Some(InstallFilter::Hooks)
+        );
     }
 
     #[test]

src/client/bedrock.rs

@@ -73,6 +73,7 @@ impl BedrockClient {
             url: _,
             headers,
             body,
+            ..
         } = request_data;
 
         let builder = aws_fetch(
@@ -126,6 +127,7 @@ impl BedrockClient {
             url: _,
             headers,
             body,
+            ..
         } = request_data;
 
         let builder = aws_fetch(
@@ -427,7 +429,9 @@ fn build_chat_completions_body(
                         let mut user_parts = vec![];
                         for (index, tool_result) in tool_results.iter().enumerate() {
                             for block in &tool_result.thinking {
-                                assistant_parts.push(converse_reasoning_block(block));
+                                if let Some(part) = converse_reasoning_block(block) {
+                                    assistant_parts.push(part);
+                                }
                             }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
@@ -496,7 +500,9 @@ fn build_chat_completions_body(
                                 chunk_ids.insert(id);
                             }
                             for block in &tool_result.thinking {
-                                assistant_parts.push(converse_reasoning_block(block));
+                                if let Some(part) = converse_reasoning_block(block) {
+                                    assistant_parts.push(part);
+                                }
                             }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
@@ -661,23 +667,26 @@ fn bedrock_tool_result_content(output: &Value) -> Value {
 }
 
 /// Maps a ThinkingBlock (Anthropic tagged shape) to the Converse
-/// reasoningContent union so signed blocks replay verbatim.
+/// reasoningContent union so signed blocks replay verbatim. OpenAI Responses
-fn converse_reasoning_block(block: &ThinkingBlock) -> Value {
+/// reasoning items have no Converse encoding, so they are dropped when the
+/// session moves to Bedrock.
+fn converse_reasoning_block(block: &ThinkingBlock) -> Option<Value> {
     match block {
         ThinkingBlock::Thinking {
             thinking,
             signature,
-        } => json!({
+        } => Some(json!({
             "reasoningContent": {
                 "reasoningText": {
                     "text": thinking,
                     "signature": signature,
                 }
             }
-        }),
+        })),
-        ThinkingBlock::RedactedThinking { data } => json!({
+        ThinkingBlock::RedactedThinking { data } => Some(json!({
             "reasoningContent": { "redactedContent": data }
-        }),
+        })),
+        ThinkingBlock::Reasoning { .. } => None,
     }
 }
 
@@ -1185,6 +1194,32 @@ mod tests {
         }
     }
 
+    #[test]
+    fn skips_openai_reasoning_blocks_in_converse_shape() {
+        let reasoning = ToolResult {
+            call: ToolCall::new(
+                "fs_read".into(),
+                json!({"path": "x"}),
+                Some("tool_A".into()),
+            ),
+            output: json!("ok"),
+            text: None,
+            thinking: vec![ThinkingBlock::Reasoning {
+                id: "rs_1".into(),
+                summary: json!([{ "type": "summary_text", "text": "thinking" }]),
+                encrypted_content: Some("enc123".into()),
+            }],
+        };
+
+        for sequence in [false, true] {
+            let body = build_body_with(vec![reasoning.clone()], "", sequence);
+
+            let content = body["messages"][1]["content"].as_array().unwrap();
+            assert_eq!(content.len(), 1, "body: {body}");
+            assert!(content[0].get("toolUse").is_some(), "body: {body}");
+        }
+    }
+
     #[test]
     fn extract_chat_completions_captures_reasoning_content() {
         let data = json!({

src/client/claude.rs

@@ -2,13 +2,12 @@ use std::collections::HashSet;
 use std::mem;
 
 use super::access_token::get_access_token;
-use super::claude_oauth::ClaudeOAuthProvider;
+use super::oauth::{self, OAuthConfig};
-use super::oauth::{self, OAuthProvider};
 use super::*;
 
 use crate::utils::strip_think_tag;
 
-use anyhow::{Context, Result, bail};
+use anyhow::{Context, Result, anyhow, bail};
 use reqwest::{Client as ReqwestClient, RequestBuilder};
 use serde::Deserialize;
 use serde_json::{Value, json};
@@ -22,6 +21,7 @@ pub struct ClaudeConfig {
     pub api_key: Option<String>,
     pub api_base: Option<String>,
     pub auth: Option<String>,
+    pub oauth: Option<Box<OAuthConfig>>,
     #[serde(default)]
     pub models: Vec<ModelData>,
     pub prompt_cache: Option<bool>,
@@ -71,9 +71,17 @@ async fn prepare_chat_completions(
     client: &ReqwestClient,
     data: ChatCompletionsData,
 ) -> Result<RequestData> {
-    let api_base = self_
+    let uses_oauth = self_.config.auth.as_deref() == Some("oauth");
-        .get_api_base()
+
-        .unwrap_or_else(|_| API_BASE.to_string());
+    if !uses_oauth && self_.config.oauth.is_some() {
+        bail!(
+            "'{}' has an `oauth:` block configured but `auth: oauth` is not set; the oauth block would be ignored. Set `auth: oauth` (and run 'coyote --authenticate {}') or remove the oauth block.",
+            self_.name(),
+            self_.name()
+        );
+    }
+
+    let api_base = resolve_api_base(self_)?;
 
     let url = format!("{}/messages", api_base.trim_end_matches('/'));
     let body = claude_build_chat_completions_body(
@@ -86,24 +94,27 @@ async fn prepare_chat_completions(
 
     request_data.header("anthropic-version", "2023-06-01");
 
-    let uses_oauth = self_.config.auth.as_deref() == Some("oauth");
-
     if uses_oauth {
-        let provider = ClaudeOAuthProvider;
+        let client_name = self_.name();
-        let ready = oauth::prepare_oauth_access_token(client, &provider, self_.name()).await?;
+        let cc = locate_client_config(self_)?;
+        let (provider, uses_stock_provider) =
+            oauth::claude_oauth_provider_for_client(cc, &ALL_PROVIDER_MODELS);
+        let ready = oauth::prepare_oauth_access_token(client, &*provider, client_name).await?;
         if !ready {
             bail!(
                 "OAuth configured but no tokens found for '{}'. Run: 'coyote --authenticate {}' or '.authenticate' in the REPL",
-                self_.name(),
+                client_name,
-                self_.name()
+                client_name
             );
         }
-        let token = get_access_token(self_.name())?;
+        let token = get_access_token(client_name)?;
         request_data.bearer_auth(token);
         for (key, value) in provider.extra_request_headers() {
             request_data.header(key, value);
         }
-        inject_oauth_system_prompt(&mut request_data.body);
+        if uses_stock_provider {
+            inject_oauth_system_prompt(&mut request_data.body);
+        }
     } else if let Ok(api_key) = self_.get_api_key() {
         request_data.header("x-api-key", api_key);
     } else {
@@ -117,6 +128,50 @@ async fn prepare_chat_completions(
     Ok(request_data)
 }
 
+fn resolve_api_base(self_: &ClaudeClient) -> Result<String> {
+    resolve_api_base_against(self_, &ALL_PROVIDER_MODELS)
+}
+
+fn resolve_api_base_against(
+    self_: &ClaudeClient,
+    all_provider_models: &[ProviderModels],
+) -> Result<String> {
+    if let Ok(api_base) = self_.get_api_base() {
+        return Ok(api_base);
+    }
+    let uses_config_oauth = self_.config.auth.as_deref() == Some("oauth")
+        && match locate_client_config(self_) {
+            Ok(cc) => oauth::config_oauth_for_client(cc, all_provider_models).is_some(),
+            // Safe: oauth prepare paths bail on this locate failure before attaching any token.
+            Err(_) => self_.config.oauth.is_some(),
+        };
+    if uses_config_oauth {
+        bail!(
+            "'{}' has a config-driven OAuth configuration (an `oauth:` block in the client entry or models catalog) but no `api_base`; refusing to fall back to {} (the oauth token would be sent to the wrong host). Set `api_base` on the '{}' client entry.",
+            self_.name(),
+            API_BASE,
+            self_.name()
+        );
+    }
+    Ok(API_BASE.to_string())
+}
+
+fn locate_client_config(self_: &ClaudeClient) -> Result<&ClientConfig> {
+    let client_name = self_.name();
+    self_
+        .app_config()
+        .clients
+        .iter()
+        .find(|cc| {
+            matches!(
+                cc,
+                ClientConfig::ClaudeConfig(c)
+                if c.name.as_deref().unwrap_or(ClaudeClient::NAME) == client_name
+            )
+        })
+        .ok_or_else(|| anyhow!("Could not locate ClientConfig entry for '{}'", client_name))
+}
+
 /// Anthropic requires OAuth-authenticated requests to include a Claude Code
 /// system prompt prefix in order to consider a request body as "valid".
 ///
@@ -352,7 +407,16 @@ pub fn claude_build_chat_completions_body(
                         let mut user_parts = vec![];
                         for (index, tool_result) in tool_results.iter().enumerate() {
                             for block in &tool_result.thinking {
-                                assistant_parts.push(json!(block));
+                                // Only Anthropic thinking blocks replay here;
+                                // Responses reasoning items (and any future
+                                // variant) are dropped.
+                                if matches!(
+                                    block,
+                                    ThinkingBlock::Thinking { .. }
+                                        | ThinkingBlock::RedactedThinking { .. }
+                                ) {
+                                    assistant_parts.push(json!(block));
+                                }
                             }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
@@ -420,7 +484,16 @@ pub fn claude_build_chat_completions_body(
                                 chunk_ids.insert(id);
                             }
                             for block in &tool_result.thinking {
-                                assistant_parts.push(json!(block));
+                                // Only Anthropic thinking blocks replay here;
+                                // Responses reasoning items (and any future
+                                // variant) are dropped.
+                                if matches!(
+                                    block,
+                                    ThinkingBlock::Thinking { .. }
+                                        | ThinkingBlock::RedactedThinking { .. }
+                                ) {
+                                    assistant_parts.push(json!(block));
+                                }
                             }
                             let round_text = if index == 0 && !text.is_empty() {
                                 Some(text.as_str())
@@ -632,7 +705,11 @@ pub fn claude_extract_chat_completions(data: &Value) -> Result<ChatCompletionsOu
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::client::access_token::set_access_token;
+    use crate::config::AppConfig;
     use crate::function::{FunctionDeclaration, ToolCall, ToolResult};
+    use chrono::Utc;
+    use std::sync::Arc;
 
     fn tool_result(id: &str, text: Option<&str>) -> ToolResult {
         ToolResult {
@@ -816,6 +893,48 @@ mod tests {
         assert_eq!(messages.len(), 1, "body: {body}");
     }
 
+    #[test]
+    fn replays_only_anthropic_thinking_blocks() {
+        let mixed = ToolResult {
+            call: ToolCall::new(
+                "fs_read".into(),
+                json!({"path": "x"}),
+                Some("toolu_A".into()),
+            ),
+            output: json!("ok"),
+            text: None,
+            thinking: vec![
+                ThinkingBlock::Thinking {
+                    thinking: "hmm".into(),
+                    signature: "sig123".into(),
+                },
+                ThinkingBlock::RedactedThinking {
+                    data: "b64data".into(),
+                },
+                ThinkingBlock::Reasoning {
+                    id: "rs_1".into(),
+                    summary: json!([{ "type": "summary_text", "text": "thinking" }]),
+                    encrypted_content: Some("enc123".into()),
+                },
+            ],
+        };
+
+        for sequence in [false, true] {
+            let body = build_body_with(vec![mixed.clone()], "", sequence, false);
+
+            let content = body["messages"][1]["content"].as_array().unwrap();
+            let types: Vec<_> = content
+                .iter()
+                .map(|block| block["type"].as_str().unwrap())
+                .collect();
+            assert_eq!(
+                types,
+                ["thinking", "redacted_thinking", "tool_use"],
+                "body: {body}"
+            );
+        }
+    }
+
     #[test]
     fn prompt_cache_places_breakpoints() {
         let functions = vec![function_declaration("a"), function_declaration("b")];
@@ -905,4 +1024,349 @@ mod tests {
         assert_eq!(usage.cache_creation_input_tokens, Some(100));
         assert_eq!(usage.cache_read_input_tokens, Some(200));
     }
+
+    fn claude_config(name: &str, auth: Option<&str>, oauth: Option<OAuthConfig>) -> ClaudeConfig {
+        ClaudeConfig {
+            name: Some(name.into()),
+            api_key: None,
+            api_base: oauth
+                .as_ref()
+                .map(|_| "https://gateway.example/v1".to_string()),
+            auth: auth.map(str::to_string),
+            oauth: oauth.map(Box::new),
+            models: vec![],
+            prompt_cache: None,
+            patch: None,
+            extra: None,
+        }
+    }
+
+    fn minimal_oauth_config() -> OAuthConfig {
+        serde_yaml::from_str("client_id: gateway\ntoken_url: https://gateway.example/token")
+            .unwrap()
+    }
+
+    fn make_client(config: ClaudeConfig, clients: Vec<ClientConfig>) -> ClaudeClient {
+        ClaudeClient {
+            app_config: Arc::new(AppConfig {
+                clients,
+                ..AppConfig::default()
+            }),
+            config,
+            model: Model::new("claude", "claude-test"),
+        }
+    }
+
+    fn prepare(client: &ClaudeClient) -> Result<RequestData> {
+        let data = ChatCompletionsData {
+            messages: vec![Message::new(
+                MessageRole::User,
+                MessageContent::Text("hello".to_string()),
+            )],
+            temperature: None,
+            top_p: None,
+            reasoning_effort: None,
+            functions: None,
+            stream: false,
+        };
+        tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .unwrap()
+            .block_on(prepare_chat_completions(
+                client,
+                &ReqwestClient::new(),
+                data,
+            ))
+    }
+
+    #[test]
+    fn oauth_stock_provider_applies_claude_code_spoof() {
+        let name = "claude-gate-stock-test";
+        let config = claude_config(name, Some("oauth"), None);
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+        set_access_token(name, "stock-at".into(), Utc::now().timestamp() + 3600, None);
+
+        let request_data = prepare(&client).unwrap();
+
+        assert_eq!(
+            request_data
+                .headers
+                .get("authorization")
+                .map(String::as_str),
+            Some("Bearer stock-at")
+        );
+        assert_eq!(
+            request_data
+                .headers
+                .get("anthropic-beta")
+                .map(String::as_str),
+            Some("oauth-2025-04-20")
+        );
+        assert_eq!(request_data.body["system"][0]["text"], CLAUDE_CODE_PREFIX);
+    }
+
+    #[test]
+    fn oauth_config_provider_skips_claude_code_spoof() {
+        let name = "claude-gate-gateway-test";
+        let config = claude_config(name, Some("oauth"), Some(minimal_oauth_config()));
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+        set_access_token(
+            name,
+            "gateway-at".into(),
+            Utc::now().timestamp() + 3600,
+            None,
+        );
+
+        let request_data = prepare(&client).unwrap();
+
+        assert_eq!(
+            request_data
+                .headers
+                .get("authorization")
+                .map(String::as_str),
+            Some("Bearer gateway-at")
+        );
+        assert!(
+            !request_data.headers.contains_key("anthropic-beta"),
+            "headers: {:?}",
+            request_data.headers
+        );
+        assert!(
+            request_data.body.get("system").is_none(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn api_key_auth_sets_x_api_key_without_spoof() {
+        let name = "claude-gate-apikey-test";
+        let mut config = claude_config(name, None, None);
+        config.api_key = Some("sk-test".into());
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+
+        let request_data = prepare(&client).unwrap();
+
+        assert_eq!(
+            request_data.headers.get("x-api-key").map(String::as_str),
+            Some("sk-test")
+        );
+        assert!(!request_data.headers.contains_key("authorization"));
+        assert!(!request_data.headers.contains_key("anthropic-beta"));
+        assert!(
+            request_data.body.get("system").is_none(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn oauth_block_without_auth_oauth_is_rejected() {
+        let name = "claude-gate-contradiction-test";
+        let mut config = claude_config(name, None, Some(minimal_oauth_config()));
+        config.api_key = Some("sk-test".into());
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+
+        let err = match prepare(&client) {
+            Ok(_) => panic!("expected the contradictory config to be rejected"),
+            Err(err) => err.to_string(),
+        };
+
+        assert!(
+            err.contains("has an `oauth:` block configured but `auth: oauth` is not set"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn oauth_block_without_api_base_is_rejected() {
+        let name = "claude-gate-apibase-missing-test";
+        let mut config = claude_config(name, Some("oauth"), Some(minimal_oauth_config()));
+        config.api_base = None;
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+
+        let err = resolve_api_base(&client).unwrap_err().to_string();
+
+        assert!(
+            err.contains(name) && err.contains("refusing to fall back"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn catalog_only_oauth_block_without_api_base_is_rejected() {
+        let name = "claude-gate-catalog-oauth-test";
+        let config = claude_config(name, Some("oauth"), None);
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+        let catalog = vec![ProviderModels {
+            provider: name.into(),
+            oauth: Some(minimal_oauth_config()),
+            models: vec![],
+        }];
+
+        let err = resolve_api_base_against(&client, &catalog)
+            .unwrap_err()
+            .to_string();
+
+        assert!(
+            err.contains(name) && err.contains("refusing to fall back"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn catalog_oauth_block_with_api_key_auth_falls_back_to_stock_api_base() {
+        let name = "claude-gate-catalog-apikey-test";
+        let mut config = claude_config(name, None, None);
+        config.api_key = Some("sk-test".into());
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+        let catalog = vec![ProviderModels {
+            provider: name.into(),
+            oauth: Some(minimal_oauth_config()),
+            models: vec![],
+        }];
+
+        let api_base = resolve_api_base_against(&client, &catalog).unwrap();
+
+        assert_eq!(api_base, API_BASE);
+    }
+
+    #[test]
+    fn auth_mismatch_bails_before_missing_api_base_guard() {
+        let name = "claude-gate-bail-order-test";
+        let mut config = claude_config(name, None, Some(minimal_oauth_config()));
+        config.api_base = None;
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+
+        let err = match prepare(&client) {
+            Ok(_) => panic!("expected the contradictory config to be rejected"),
+            Err(err) => err.to_string(),
+        };
+
+        assert!(
+            err.contains("has an `oauth:` block configured but `auth: oauth` is not set")
+                && !err.contains("refusing to fall back"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn oauth_block_with_api_base_resolves_it() {
+        let name = "claude-gate-apibase-set-test";
+        let config = claude_config(name, Some("oauth"), Some(minimal_oauth_config()));
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+
+        let api_base = resolve_api_base(&client).unwrap();
+
+        assert_eq!(api_base, "https://gateway.example/v1");
+    }
+
+    #[test]
+    fn no_oauth_block_falls_back_to_stock_api_base() {
+        let name = "claude-gate-apibase-fallback-test";
+        let config = claude_config(name, None, None);
+        let client = make_client(config.clone(), vec![ClientConfig::ClaudeConfig(config)]);
+
+        let api_base = resolve_api_base(&client).unwrap();
+
+        assert_eq!(api_base, API_BASE);
+    }
+
+    #[test]
+    fn oauth_lookup_resolves_entry_matching_client_name() {
+        let name = "claude-gate-lookup-test";
+        // The sibling entry resolves to the stock provider; if the lookup
+        // ignored the name it would apply the Claude Code spoof here.
+        let sibling = claude_config("claude-gate-lookup-sibling-test", Some("oauth"), None);
+        let config = claude_config(name, Some("oauth"), Some(minimal_oauth_config()));
+        let client = make_client(
+            config.clone(),
+            vec![
+                ClientConfig::ClaudeConfig(sibling),
+                ClientConfig::ClaudeConfig(config),
+            ],
+        );
+        set_access_token(
+            name,
+            "lookup-at".into(),
+            Utc::now().timestamp() + 3600,
+            None,
+        );
+
+        let request_data = prepare(&client).unwrap();
+
+        assert_eq!(
+            request_data
+                .headers
+                .get("authorization")
+                .map(String::as_str),
+            Some("Bearer lookup-at")
+        );
+        assert!(!request_data.headers.contains_key("anthropic-beta"));
+        assert!(request_data.body.get("system").is_none());
+    }
+
+    #[test]
+    fn oauth_lookup_falls_back_to_default_name_for_unnamed_entry() {
+        // An entry with `name: None` must match a client named "claude" via
+        // the `unwrap_or(ClaudeClient::NAME)` fallback.
+        let sibling = claude_config("claude-gate-fallback-sibling-test", Some("oauth"), None);
+        let mut config = claude_config("ignored", Some("oauth"), Some(minimal_oauth_config()));
+        config.name = None;
+        let client = make_client(
+            config.clone(),
+            vec![
+                ClientConfig::ClaudeConfig(sibling),
+                ClientConfig::ClaudeConfig(config),
+            ],
+        );
+        set_access_token(
+            ClaudeClient::NAME,
+            "fallback-at".into(),
+            Utc::now().timestamp() + 3600,
+            None,
+        );
+
+        let request_data = prepare(&client).unwrap();
+
+        assert_eq!(
+            request_data
+                .headers
+                .get("authorization")
+                .map(String::as_str),
+            Some("Bearer fallback-at")
+        );
+        assert!(!request_data.headers.contains_key("anthropic-beta"));
+        assert!(request_data.body.get("system").is_none());
+    }
+
+    #[test]
+    fn oauth_lookup_errors_when_config_entry_missing() {
+        let config = claude_config("claude-gate-missing-test", Some("oauth"), None);
+        let client = make_client(config, vec![]);
+
+        let err = match prepare(&client) {
+            Ok(_) => panic!("expected the lookup to fail"),
+            Err(err) => err.to_string(),
+        };
+
+        assert!(
+            err.contains("Could not locate ClientConfig entry"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn shipped_catalog_resolves_stock_claude_provider() {
+        let cc = ClientConfig::ClaudeConfig(claude_config("claude", Some("oauth"), None));
+        let bundled: Vec<ProviderModels> = serde_yaml::from_str(MODELS_YAML).unwrap();
+
+        let (_, is_stock) = oauth::claude_oauth_provider_for_client(&cc, &bundled);
+
+        assert!(
+            is_stock,
+            "bundled models.yaml must not carry a claude oauth block: it would silently drop the Claude Code spoof for stock Pro/Max users"
+        );
+    }
 }

src/client/common.rs

@@ -2,6 +2,7 @@ use super::*;
 
 use super::access_token::{distrust_access_token, get_access_token};
 use crate::config::{RenderMode, paths};
+use crate::hooks::{self, HookEvent};
 use crate::{
     config::{AppConfig, Input, RequestContext},
     function::{FunctionDeclaration, ToolCall, ToolResult, eval_tool_calls},
@@ -20,7 +21,7 @@ use reqwest::{Client as ReqwestClient, RequestBuilder};
 use serde::{Deserialize, Serialize};
 use serde_json::{Value, json};
 use std::sync::LazyLock;
-use std::time::Duration;
+use std::time::{Duration, Instant};
 use tokio::sync::mpsc::unbounded_channel;
 
 pub const MODELS_YAML: &str = include_str!("../../models.yaml");
@@ -221,23 +222,39 @@ pub trait Client: Sync + Send {
         request_data.into_builder(client)
     }
 
+    /// Patches are chat-shaped unless keyed otherwise: on the Responses wire
+    /// only the `responses` sub-patch of a model patch and the `responses`
+    /// section of a client patch apply, so chat-only keys never leak into a
+    /// responses body.
     fn patch_request_data(&self, request_data: &mut RequestData) {
         let model_type = self.model().model_type();
+        let wire = request_data.wire;
         if let Some(patch) = self.model().patch() {
-            request_data.apply_patch(patch.clone());
+            match wire {
+                WireApi::Chat => request_data.apply_patch(patch.clone()),
+                WireApi::Responses => {
+                    if let Some(patch) = patch.get("responses") {
+                        request_data.apply_patch(patch.clone());
+                    }
+                }
+            }
         }
 
+        let api_name = match wire {
+            WireApi::Responses => "responses",
+            WireApi::Chat => model_type.api_name(),
+        };
         let patch_map = std::env::var(get_env_name(&format!(
-            "patch_{}_{}",
+            "patch_{}_{api_name}",
             self.model().client_name(),
-            model_type.api_name(),
         )))
         .ok()
         .and_then(|v| serde_json::from_str(&v).ok())
         .or_else(|| {
-            self.patch_config()
+            self.patch_config().and_then(|v| match wire {
-                .and_then(|v| model_type.extract_patch(v))
+                WireApi::Responses => v.responses.clone(),
-                .cloned()
+                WireApi::Chat => model_type.extract_patch(v).cloned(),
+            })
         });
         let patch_map = match patch_map {
             Some(v) => v,
@@ -271,16 +288,26 @@ pub struct ExtraConfig {
 #[derive(Debug, Clone, Deserialize, Default)]
 pub struct RequestPatch {
     pub chat_completions: Option<ApiPatch>,
+    pub responses: Option<ApiPatch>,
     pub embeddings: Option<ApiPatch>,
     pub rerank: Option<ApiPatch>,
 }
 
 pub type ApiPatch = IndexMap<String, Value>;
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Deserialize, Serialize)]
+#[serde(rename_all = "lowercase")]
+pub enum WireApi {
+    Responses,
+    Chat,
+}
+
+#[derive(Debug)]
 pub struct RequestData {
     pub url: String,
     pub headers: IndexMap<String, String>,
     pub body: Value,
+    pub wire: WireApi,
 }
 
 impl RequestData {
@@ -292,9 +319,15 @@ impl RequestData {
             url: url.to_string(),
             headers: Default::default(),
             body,
+            wire: WireApi::Chat,
         }
     }
 
+    pub fn wire(mut self, wire: WireApi) -> Self {
+        self.wire = wire;
+        self
+    }
+
     pub fn bearer_auth<T>(&mut self, auth: T)
     where
         T: std::fmt::Display,
@@ -312,7 +345,9 @@ impl RequestData {
     }
 
     pub fn into_builder(self, client: &ReqwestClient) -> RequestBuilder {
-        let RequestData { url, headers, body } = self;
+        let RequestData {
+            url, headers, body, ..
+        } = self;
         debug!("Request {url} {body}");
 
         let mut builder = client.post(url);
@@ -546,6 +581,47 @@ pub async fn create_openai_compatible_client_config(
     Ok(Some((model, clients)))
 }
 
+fn llm_request_extras(client: &dyn Client) -> Vec<(&'static str, String)> {
+    vec![
+        ("COYOTE_LLM_PROVIDER", client.name().to_string()),
+        ("COYOTE_LLM_MODEL", client.model().id()),
+    ]
+}
+
+fn llm_completed_extras(client: &dyn Client, started_at: Instant) -> Vec<(&'static str, String)> {
+    let mut extras = llm_request_extras(client);
+    extras.push((
+        "COYOTE_LLM_DURATION_MS",
+        started_at.elapsed().as_millis().to_string(),
+    ));
+    extras
+}
+
+fn llm_failed_extras(
+    client: &dyn Client,
+    err: Option<&anyhow::Error>,
+    aborted: bool,
+) -> Vec<(&'static str, String)> {
+    let mut extras = llm_request_extras(client);
+    if aborted {
+        extras.push(("COYOTE_LLM_ERROR_KIND", "aborted".to_string()));
+    } else if let Some(api_err) = err.and_then(|err| err.downcast_ref::<ApiStatusError>()) {
+        extras.push(("COYOTE_LLM_ERROR_KIND", "api_error".to_string()));
+        extras.push(("COYOTE_LLM_STATUS", api_err.status.to_string()));
+    } else {
+        extras.push(("COYOTE_LLM_ERROR_KIND", "other".to_string()));
+    }
+    extras.push((
+        "COYOTE_LLM_ERROR",
+        // `{:#}` renders the whole context chain, so the root cause survives
+        // the `context(...)` wrapping the client trait defaults apply.
+        err.map(|err| format!("{err:#}"))
+            .unwrap_or_else(|| "Aborted.".to_string()),
+    ));
+
+    extras
+}
+
 pub async fn call_chat_completions(
     input: &Input,
     print: bool,
@@ -557,15 +633,28 @@ pub async fn call_chat_completions(
     let is_child_agent = ctx.current_depth > 0;
     let suppress_spinner = is_child_agent || ctx.render_mode == RenderMode::Silent;
     let spinner_message = if suppress_spinner { "" } else { "Generating" };
+    hooks::fire(
+        HookEvent::LlmRequestStarted,
+        ctx,
+        &llm_request_extras(client),
+        None,
+    );
+    let request_started_at = Instant::now();
     let ret = abortable_run_with_spinner(
         client.chat_completions(input.clone()),
         spinner_message,
-        abort_signal,
+        abort_signal.clone(),
     )
     .await;
 
     match ret {
         Ok(ret) => {
+            hooks::fire(
+                HookEvent::LlmRequestCompleted,
+                ctx,
+                &llm_completed_extras(client, request_started_at),
+                None,
+            );
             let ChatCompletionsOutput {
                 mut text,
                 tool_calls,
@@ -583,7 +672,15 @@ pub async fn call_chat_completions(
             ctx.record_token_usage(usage, client.model());
             finish_completion(ctx, text, tool_calls, thinking).await
         }
-        Err(err) => Err(err),
+        Err(err) => {
+            hooks::fire(
+                HookEvent::LlmRequestFailed,
+                ctx,
+                &llm_failed_extras(client, Some(&err), abort_signal.aborted()),
+                None,
+            );
+            Err(err)
+        }
     }
 }
 
@@ -600,6 +697,13 @@ pub async fn call_chat_completions_streaming(
         handler.set_silent(true);
     }
 
+    hooks::fire(
+        HookEvent::LlmRequestStarted,
+        ctx,
+        &llm_request_extras(client),
+        None,
+    );
+    let request_started_at = Instant::now();
     let (send_ret, render_ret) = tokio::join!(
         client.chat_completions_streaming(input, &mut handler),
         render_stream(rx, client.app_config(), abort_signal.clone(), silent),
@@ -615,12 +719,32 @@ pub async fn call_chat_completions_streaming(
     ctx.record_token_usage(usage, client.model());
 
     if aborted_ctrld {
+        hooks::fire(
+            HookEvent::LlmRequestFailed,
+            ctx,
+            &llm_failed_extras(client, None, true),
+            None,
+        );
         bail!("Aborted.");
     }
 
-    render_ret?;
+    if let Err(err) = render_ret {
+        hooks::fire(
+            HookEvent::LlmRequestFailed,
+            ctx,
+            &llm_failed_extras(client, Some(&err), false),
+            None,
+        );
+        return Err(err);
+    }
 
     if aborted_ctrlc {
+        hooks::fire(
+            HookEvent::LlmRequestFailed,
+            ctx,
+            &llm_failed_extras(client, None, true),
+            None,
+        );
         if !ctx.working_mode.is_repl() || ctx.session.is_none() {
             bail!("Aborted.");
         }
@@ -644,6 +768,12 @@ pub async fn call_chat_completions_streaming(
 
     match send_ret {
         Ok(_) => {
+            hooks::fire(
+                HookEvent::LlmRequestCompleted,
+                ctx,
+                &llm_completed_extras(client, request_started_at),
+                None,
+            );
             if !silent && !text.is_empty() && !text.ends_with('\n') {
                 println!();
             }
@@ -653,6 +783,12 @@ pub async fn call_chat_completions_streaming(
             if !silent && !text.is_empty() {
                 println!();
             }
+            hooks::fire(
+                HookEvent::LlmRequestFailed,
+                ctx,
+                &llm_failed_extras(client, Some(&err), false),
+                None,
+            );
             Err(err)
         }
     }
@@ -675,10 +811,36 @@ pub async fn call_chat_completions_streaming_quiet(
     ctx: &mut RequestContext,
     abort_signal: AbortSignal,
 ) -> Result<(String, Vec<ToolResult>)> {
+    hooks::fire(
+        HookEvent::LlmRequestStarted,
+        ctx,
+        &llm_request_extras(client),
+        None,
+    );
+    let request_started_at = Instant::now();
     if client.model().no_stream() {
         let output = tokio::select! {
-            ret = client.chat_completions(input.clone()) => ret?,
+            ret = client.chat_completions(input.clone()) => match ret {
-            _ = wait_abort_signal(&abort_signal) => bail!("Aborted."),
+                Ok(output) => output,
+                Err(err) => {
+                    hooks::fire(
+                        HookEvent::LlmRequestFailed,
+                        ctx,
+                        &llm_failed_extras(client, Some(&err), false),
+                        None,
+                    );
+                    return Err(err);
+                }
+            },
+            _ = wait_abort_signal(&abort_signal) => {
+                hooks::fire(
+                    HookEvent::LlmRequestFailed,
+                    ctx,
+                    &llm_failed_extras(client, None, true),
+                    None,
+                );
+                bail!("Aborted.")
+            }
         };
         let ChatCompletionsOutput {
             text,
@@ -688,8 +850,20 @@ pub async fn call_chat_completions_streaming_quiet(
         } = output;
         ctx.record_token_usage(usage, client.model());
         if abort_signal.aborted() {
+            hooks::fire(
+                HookEvent::LlmRequestFailed,
+                ctx,
+                &llm_failed_extras(client, None, true),
+                None,
+            );
             bail!("Aborted.");
         }
+        hooks::fire(
+            HookEvent::LlmRequestCompleted,
+            ctx,
+            &llm_completed_extras(client, request_started_at),
+            None,
+        );
         return finish_completion(ctx, text, tool_calls, thinking).await;
     }
 
@@ -705,10 +879,30 @@ pub async fn call_chat_completions_streaming_quiet(
     ctx.record_token_usage(usage, client.model());
 
     if abort_signal.aborted() {
+        hooks::fire(
+            HookEvent::LlmRequestFailed,
+            ctx,
+            &llm_failed_extras(client, None, true),
+            None,
+        );
         bail!("Aborted.");
     }
-    send_ret?;
+    if let Err(err) = send_ret {
+        hooks::fire(
+            HookEvent::LlmRequestFailed,
+            ctx,
+            &llm_failed_extras(client, Some(&err), false),
+            None,
+        );
+        return Err(err);
+    }
 
+    hooks::fire(
+        HookEvent::LlmRequestCompleted,
+        ctx,
+        &llm_completed_extras(client, request_started_at),
+        None,
+    );
     finish_completion(ctx, text, tool_calls, thinking).await
 }
 
@@ -969,6 +1163,7 @@ mod tests {
 
     use super::super::access_token::{is_rejected, set_access_token};
     use crate::config::{AppState, WorkingMode};
+    use anyhow::Error;
     use std::sync::Arc;
     use std::sync::atomic::{AtomicUsize, Ordering};
     use tokio::time::Instant;
@@ -1185,8 +1380,8 @@ mod tests {
 
     /// Wrapped in `.context(...)` so every test below proves the downcast
     /// works through an anyhow context chain, as in the trait methods.
-    fn api_status_error(status: u16) -> anyhow::Error {
+    fn api_status_error(status: u16) -> Error {
-        anyhow::Error::new(ApiStatusError {
+        Error::new(ApiStatusError {
             status,
             message: format!("error (status: {status})"),
         })
@@ -1524,4 +1719,590 @@ mod tests {
         assert_eq!(client.streaming_calls.load(Ordering::SeqCst), 1);
         assert_paced_reply(&text, &results);
     }
+
+    /// Fake provider whose every request fails with an [`ApiStatusError`],
+    /// wrapped in the same context chain the real trait defaults produce.
+    struct FailingStatusClient {
+        config: AppConfig,
+        model: Model,
+        status: u16,
+    }
+
+    impl FailingStatusClient {
+        fn new(status: u16) -> Self {
+            Self {
+                config: AppConfig::default(),
+                model: Model::default(),
+                status,
+            }
+        }
+
+        fn error(&self) -> Error {
+            Error::new(ApiStatusError {
+                status: self.status,
+                message: format!("error (status: {})", self.status),
+            })
+        }
+    }
+
+    #[async_trait::async_trait]
+    impl Client for FailingStatusClient {
+        fn app_config(&self) -> &AppConfig {
+            &self.config
+        }
+
+        fn extra_config(&self) -> Option<&ExtraConfig> {
+            None
+        }
+
+        fn patch_config(&self) -> Option<&RequestPatch> {
+            None
+        }
+
+        fn name(&self) -> &str {
+            "failing-status"
+        }
+
+        fn model(&self) -> &Model {
+            &self.model
+        }
+
+        async fn chat_completions_inner(
+            &self,
+            _client: &ReqwestClient,
+            _data: ChatCompletionsData,
+        ) -> Result<ChatCompletionsOutput> {
+            Err(self.error())
+        }
+
+        async fn chat_completions_streaming_inner(
+            &self,
+            _client: &ReqwestClient,
+            _handler: &mut SseHandler,
+            _data: ChatCompletionsData,
+        ) -> Result<()> {
+            Err(self.error())
+        }
+    }
+
+    fn llm_hooks_map(marker: &str) -> hooks::HooksMap {
+        [
+            "llm.request.started",
+            "llm.request.completed",
+            "llm.request.failed",
+        ]
+        .into_iter()
+        .map(|event| {
+            (
+                event.to_string(),
+                vec![crate::hooks::HookDef {
+                    name: marker.to_string(),
+                    command: "true".to_string(),
+                }],
+            )
+        })
+        .collect()
+    }
+
+    fn llm_hooked_ctx(marker: &str) -> RequestContext {
+        let mut app = AppState::test_default();
+        app.config = Arc::new(AppConfig {
+            hooks: llm_hooks_map(marker),
+            ..Default::default()
+        });
+        let mut ctx = RequestContext::new(Arc::new(app), WorkingMode::Cmd);
+        ctx.render_mode = RenderMode::Silent;
+        ctx
+    }
+
+    fn llm_captures(marker: &str) -> Vec<hooks::test_sink::Capture> {
+        hooks::test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name == marker)
+            .collect()
+    }
+
+    #[tokio::test(start_paused = true)]
+    #[serial_test::serial]
+    async fn plain_transport_fires_llm_request_started_and_completed() {
+        let marker = "llm-hooks-plain-ok-x7x";
+        let mut ctx = llm_hooked_ctx(marker);
+        let input = Input::from_str(&ctx, "hi", None).unwrap();
+        let mut client = paced_client(false);
+        client.nonstream_replies = true;
+        let _guard = hooks::test_sink::install();
+
+        call_chat_completions(
+            &input,
+            false,
+            false,
+            &client,
+            &mut ctx,
+            create_abort_signal(),
+        )
+        .await
+        .unwrap();
+
+        let captures = llm_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::LlmRequestStarted);
+        assert_eq!(
+            captures[0]
+                .envs
+                .get("COYOTE_LLM_PROVIDER")
+                .map(String::as_str),
+            Some("paced-stream")
+        );
+        assert!(captures[0].envs.contains_key("COYOTE_LLM_MODEL"));
+        assert_eq!(captures[1].event, HookEvent::LlmRequestCompleted);
+        assert!(captures[1].envs.contains_key("COYOTE_LLM_DURATION_MS"));
+        assert!(!captures[1].envs.contains_key("COYOTE_LLM_ERROR_KIND"));
+    }
+
+    #[tokio::test]
+    #[serial_test::serial]
+    async fn plain_transport_fires_llm_request_failed_with_api_error_kind() {
+        let marker = "llm-hooks-plain-api-err-x7x";
+        let mut ctx = llm_hooked_ctx(marker);
+        let input = Input::from_str(&ctx, "hi", None).unwrap();
+        let client = FailingStatusClient::new(429);
+        let _guard = hooks::test_sink::install();
+
+        let err = call_chat_completions(
+            &input,
+            false,
+            false,
+            &client,
+            &mut ctx,
+            create_abort_signal(),
+        )
+        .await
+        .unwrap_err();
+
+        assert!(
+            err.downcast_ref::<ApiStatusError>().is_some(),
+            "hooks must not change the error: {err:?}"
+        );
+        let captures = llm_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::LlmRequestStarted);
+        let failed = &captures[1];
+        assert_eq!(failed.event, HookEvent::LlmRequestFailed);
+        assert_eq!(
+            failed.envs.get("COYOTE_LLM_ERROR_KIND").map(String::as_str),
+            Some("api_error")
+        );
+        assert_eq!(
+            failed.envs.get("COYOTE_LLM_STATUS").map(String::as_str),
+            Some("429")
+        );
+        assert!(
+            failed
+                .envs
+                .get("COYOTE_LLM_ERROR")
+                .unwrap()
+                .contains("error (status: 429)")
+        );
+        assert!(!failed.envs.contains_key("COYOTE_LLM_DURATION_MS"));
+    }
+
+    #[tokio::test(start_paused = true)]
+    #[serial_test::serial]
+    async fn streaming_transport_fires_llm_request_started_and_completed() {
+        let marker = "llm-hooks-stream-ok-x7x";
+        let mut ctx = llm_hooked_ctx(marker);
+        let input = Input::from_str(&ctx, "hi", None).unwrap();
+        let client = paced_client(false);
+        let _guard = hooks::test_sink::install();
+
+        call_chat_completions_streaming(&input, &client, &mut ctx, create_abort_signal())
+            .await
+            .unwrap();
+
+        let captures = llm_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::LlmRequestStarted);
+        assert_eq!(captures[1].event, HookEvent::LlmRequestCompleted);
+        assert!(captures[1].envs.contains_key("COYOTE_LLM_DURATION_MS"));
+    }
+
+    #[tokio::test(start_paused = true)]
+    #[serial_test::serial]
+    async fn streaming_transport_abort_fires_llm_request_failed_aborted() {
+        let marker = "llm-hooks-stream-abort-x7x";
+        let mut ctx = llm_hooked_ctx(marker);
+        let input = Input::from_str(&ctx, "hi", None).unwrap();
+        let client = paced_client(true);
+        let abort = create_abort_signal();
+        let trigger = abort.clone();
+        tokio::spawn(async move {
+            tokio::time::sleep(PACED_GAP * PACED_DELTAS as u32 + Duration::from_secs(30)).await;
+            trigger.set_ctrlc();
+        });
+        let _guard = hooks::test_sink::install();
+
+        let err = call_chat_completions_streaming(&input, &client, &mut ctx, abort)
+            .await
+            .expect_err("an aborted stream must not succeed");
+
+        assert_eq!(err.to_string(), "Aborted.");
+        let captures = llm_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        let failed = &captures[1];
+        assert_eq!(failed.event, HookEvent::LlmRequestFailed);
+        assert_eq!(
+            failed.envs.get("COYOTE_LLM_ERROR_KIND").map(String::as_str),
+            Some("aborted")
+        );
+        assert!(!failed.envs.contains_key("COYOTE_LLM_STATUS"));
+    }
+
+    #[tokio::test(start_paused = true)]
+    #[serial_test::serial]
+    async fn quiet_transport_fires_llm_request_started_and_completed() {
+        let marker = "llm-hooks-quiet-ok-x7x";
+        let mut ctx = llm_hooked_ctx(marker);
+        let input = Input::from_str(&ctx, "hi", None).unwrap();
+        let client = paced_client(false);
+        let _guard = hooks::test_sink::install();
+
+        call_chat_completions_streaming_quiet(&input, &client, &mut ctx, create_abort_signal())
+            .await
+            .unwrap();
+
+        let captures = llm_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::LlmRequestStarted);
+        assert_eq!(
+            captures[0]
+                .envs
+                .get("COYOTE_LLM_PROVIDER")
+                .map(String::as_str),
+            Some("paced-stream")
+        );
+        assert_eq!(captures[1].event, HookEvent::LlmRequestCompleted);
+        assert!(captures[1].envs.contains_key("COYOTE_LLM_DURATION_MS"));
+    }
+
+    #[tokio::test(start_paused = true)]
+    #[serial_test::serial]
+    async fn quiet_transport_abort_fires_llm_request_failed_aborted() {
+        let marker = "llm-hooks-quiet-abort-x7x";
+        let mut ctx = llm_hooked_ctx(marker);
+        let input = Input::from_str(&ctx, "hi", None).unwrap();
+        let client = paced_client(true);
+        let abort = create_abort_signal();
+        let trigger = abort.clone();
+        tokio::spawn(async move {
+            tokio::time::sleep(PACED_GAP * PACED_DELTAS as u32 + Duration::from_secs(30)).await;
+            trigger.set_ctrlc();
+        });
+        let _guard = hooks::test_sink::install();
+
+        let err = call_chat_completions_streaming_quiet(&input, &client, &mut ctx, abort)
+            .await
+            .expect_err("an aborted stream must not succeed");
+
+        assert_eq!(err.to_string(), "Aborted.");
+        let captures = llm_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        let failed = &captures[1];
+        assert_eq!(failed.event, HookEvent::LlmRequestFailed);
+        assert_eq!(
+            failed.envs.get("COYOTE_LLM_ERROR_KIND").map(String::as_str),
+            Some("aborted")
+        );
+        assert_eq!(
+            failed.envs.get("COYOTE_LLM_ERROR").map(String::as_str),
+            Some("Aborted.")
+        );
+    }
+
+    #[tokio::test]
+    #[serial_test::serial]
+    async fn quiet_transport_fires_llm_request_failed_with_api_error_kind() {
+        let marker = "llm-hooks-quiet-api-err-x7x";
+        let mut ctx = llm_hooked_ctx(marker);
+        let input = Input::from_str(&ctx, "hi", None).unwrap();
+        let client = FailingStatusClient::new(500);
+        let _guard = hooks::test_sink::install();
+
+        let err =
+            call_chat_completions_streaming_quiet(&input, &client, &mut ctx, create_abort_signal())
+                .await
+                .unwrap_err();
+
+        assert!(err.downcast_ref::<ApiStatusError>().is_some());
+        let captures = llm_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        let failed = &captures[1];
+        assert_eq!(failed.event, HookEvent::LlmRequestFailed);
+        assert_eq!(
+            failed.envs.get("COYOTE_LLM_ERROR_KIND").map(String::as_str),
+            Some("api_error")
+        );
+        assert_eq!(
+            failed.envs.get("COYOTE_LLM_STATUS").map(String::as_str),
+            Some("500")
+        );
+    }
+
+    /// Minimal client for exercising `patch_request_data`: only the model
+    /// and the client-level patch config matter.
+    struct PatchProbeClient {
+        config: AppConfig,
+        model: Model,
+        patch: Option<RequestPatch>,
+    }
+
+    #[async_trait::async_trait]
+    impl Client for PatchProbeClient {
+        fn app_config(&self) -> &AppConfig {
+            &self.config
+        }
+
+        fn extra_config(&self) -> Option<&ExtraConfig> {
+            None
+        }
+
+        fn patch_config(&self) -> Option<&RequestPatch> {
+            self.patch.as_ref()
+        }
+
+        fn name(&self) -> &str {
+            self.model.client_name()
+        }
+
+        fn model(&self) -> &Model {
+            &self.model
+        }
+
+        async fn chat_completions_inner(
+            &self,
+            _client: &ReqwestClient,
+            _data: ChatCompletionsData,
+        ) -> Result<ChatCompletionsOutput> {
+            bail!("the patch probe makes no requests")
+        }
+
+        async fn chat_completions_streaming_inner(
+            &self,
+            _client: &ReqwestClient,
+            _handler: &mut SseHandler,
+            _data: ChatCompletionsData,
+        ) -> Result<()> {
+            bail!("the patch probe makes no requests")
+        }
+    }
+
+    fn patch_probe(
+        client_name: &str,
+        model_patch: Option<Value>,
+        patch: Option<RequestPatch>,
+    ) -> PatchProbeClient {
+        let mut data = ModelData::new("gpt-test");
+        data.patch = model_patch;
+        PatchProbeClient {
+            config: AppConfig::default(),
+            model: Model::from_config(client_name, &[data]).remove(0),
+            patch,
+        }
+    }
+
+    fn client_patch(json: Value) -> RequestPatch {
+        serde_json::from_value(json).unwrap()
+    }
+
+    fn wire_request(wire: WireApi) -> RequestData {
+        RequestData::new("https://example.test/v1", json!({"model": "gpt-test"})).wire(wire)
+    }
+
+    #[test]
+    fn request_patch_accepts_a_responses_section() {
+        let patch = client_patch(json!({
+            "responses": {".*": {"body": {"store": true}}},
+            "chat_completions": {".*": {"body": {"temperature": 0.5}}},
+        }));
+
+        assert!(patch.responses.is_some());
+        assert!(patch.chat_completions.is_some());
+    }
+
+    #[test]
+    fn non_map_request_patch_responses_section_is_rejected() {
+        let err = serde_json::from_value::<RequestPatch>(json!({"responses": "bogus"}))
+            .unwrap_err()
+            .to_string();
+
+        assert!(err.contains("expected a map"), "unexpected error: {err}");
+    }
+
+    #[test]
+    fn chat_client_patch_never_touches_the_responses_wire() {
+        let client = patch_probe(
+            "patchprobechatiso",
+            None,
+            Some(client_patch(json!({
+                "chat_completions": {".*": {"body": {"temperature": 0.5}}}
+            }))),
+        );
+        let mut request_data = wire_request(WireApi::Responses);
+        let before = request_data.body.clone();
+
+        client.patch_request_data(&mut request_data);
+
+        assert_eq!(request_data.body, before);
+    }
+
+    #[test]
+    fn responses_client_patch_never_touches_the_chat_wire() {
+        let patch = Some(client_patch(json!({
+            "responses": {".*": {"body": {"store": true}}}
+        })));
+        let client = patch_probe("patchproberespiso", None, patch);
+
+        let mut chat_request = wire_request(WireApi::Chat);
+        let before = chat_request.body.clone();
+        client.patch_request_data(&mut chat_request);
+        assert_eq!(chat_request.body, before);
+
+        let mut responses_request = wire_request(WireApi::Responses);
+        client.patch_request_data(&mut responses_request);
+        assert_eq!(responses_request.body["store"], json!(true));
+    }
+
+    #[test]
+    fn chat_shaped_model_patch_never_touches_the_responses_wire() {
+        let client = patch_probe(
+            "patchprobemodeliso",
+            Some(json!({"body": {"reasoning_effort": "high"}})),
+            None,
+        );
+        let mut request_data = wire_request(WireApi::Responses);
+        let before = request_data.body.clone();
+
+        client.patch_request_data(&mut request_data);
+
+        assert_eq!(request_data.body, before);
+    }
+
+    #[test]
+    fn model_patch_responses_subkey_is_selected_per_wire() {
+        let model_patch = json!({
+            "body": {"temperature": 0.2},
+            "responses": {"body": {"store": true}},
+        });
+        let client = patch_probe("patchprobesubkey", Some(model_patch), None);
+
+        let mut responses_request = wire_request(WireApi::Responses);
+        client.patch_request_data(&mut responses_request);
+        assert_eq!(responses_request.body["store"], json!(true));
+        assert!(responses_request.body.get("temperature").is_none());
+
+        let mut chat_request = wire_request(WireApi::Chat);
+        client.patch_request_data(&mut chat_request);
+        assert_eq!(chat_request.body["temperature"], json!(0.2));
+        assert!(chat_request.body.get("store").is_none());
+    }
+
+    /// Pins the silent-ignore contract for a malformed `responses` sub-key:
+    /// model patches are untyped JSON maps and the whole patch layer is
+    /// deliberately lenient — `apply_patch` only reads object-shaped
+    /// `url`/`body`/`headers` keys — so a non-object `responses` sub-key
+    /// degrades to a no-op on the Responses wire (never a request-time
+    /// error, never a partial merge) and stays inert on the Chat wire,
+    /// where the patch's top-level keys still apply normally.
+    #[test]
+    fn malformed_model_patch_responses_subkey_is_silently_ignored() {
+        for malformed in [json!("oops"), json!([{"body": {"store": true}}])] {
+            let model_patch = json!({
+                "body": {"temperature": 0.2},
+                "responses": malformed,
+            });
+            let client = patch_probe("patchprobemalformed", Some(model_patch), None);
+
+            let mut responses_request = wire_request(WireApi::Responses);
+            let before_url = responses_request.url.clone();
+            let before_body = responses_request.body.clone();
+            let before_headers = responses_request.headers.clone();
+            client.patch_request_data(&mut responses_request);
+            assert_eq!(responses_request.url, before_url);
+            assert_eq!(responses_request.body, before_body);
+            assert_eq!(responses_request.headers, before_headers);
+
+            let mut chat_request = wire_request(WireApi::Chat);
+            client.patch_request_data(&mut chat_request);
+            assert_eq!(chat_request.body["temperature"], json!(0.2));
+            assert!(chat_request.body.get("store").is_none());
+        }
+    }
+
+    #[test]
+    fn env_patch_override_is_selected_per_wire() {
+        // Unique client name so the env vars cannot race parallel tests.
+        let client_name = "patchprobeenvwire";
+        let responses_env = get_env_name(&format!("patch_{client_name}_responses"));
+        let chat_env = get_env_name(&format!("patch_{client_name}_chat_completions"));
+        unsafe {
+            std::env::set_var(&responses_env, r#"{".*": {"body": {"store": true}}}"#);
+            std::env::set_var(&chat_env, r#"{".*": {"body": {"temperature": 0.7}}}"#);
+        }
+
+        let client = patch_probe(client_name, None, None);
+        let mut responses_request = wire_request(WireApi::Responses);
+        client.patch_request_data(&mut responses_request);
+        let mut chat_request = wire_request(WireApi::Chat);
+        client.patch_request_data(&mut chat_request);
+
+        unsafe {
+            std::env::remove_var(&responses_env);
+            std::env::remove_var(&chat_env);
+        }
+
+        assert_eq!(responses_request.body["store"], json!(true));
+        assert!(responses_request.body.get("temperature").is_none());
+        assert_eq!(chat_request.body["temperature"], json!(0.7));
+        assert!(chat_request.body.get("store").is_none());
+    }
+
+    #[test]
+    fn chat_wire_patching_is_unchanged_by_wire_awareness() {
+        let client = patch_probe(
+            "patchproberegress",
+            Some(json!({"body": {"max_tokens": null}, "headers": {"x-model": "m"}})),
+            Some(client_patch(json!({
+                "chat_completions": {".*": {
+                    "url": "https://patched.example/v1/chat/completions",
+                    "body": {"temperature": 0.9},
+                }}
+            }))),
+        );
+        let mut request_data = RequestData::new(
+            "https://example.test/v1/chat/completions",
+            json!({"model": "gpt-test", "max_tokens": 100}),
+        );
+        request_data.bearer_auth("sk-test");
+
+        client.patch_request_data(&mut request_data);
+
+        assert_eq!(
+            request_data.url,
+            "https://patched.example/v1/chat/completions"
+        );
+        assert_eq!(
+            request_data.body,
+            json!({"model": "gpt-test", "temperature": 0.9})
+        );
+        assert_eq!(
+            request_data.headers.get("x-model").map(String::as_str),
+            Some("m")
+        );
+        assert_eq!(
+            request_data
+                .headers
+                .get("authorization")
+                .map(String::as_str),
+            Some("Bearer sk-test")
+        );
+    }
 }

src/client/gemini.rs

@@ -1,10 +1,10 @@
 use super::access_token::get_access_token;
 use super::gemini_oauth::GeminiOAuthProvider;
-use super::oauth;
+use super::oauth::{self, OAuthConfig, OAuthProvider};
 use super::vertexai::*;
 use super::*;
 
-use anyhow::{Context, Result, bail};
+use anyhow::{Context, Result, anyhow, bail};
 use reqwest::{Client as ReqwestClient, RequestBuilder};
 use serde::Deserialize;
 use serde_json::{Value, json};
@@ -17,6 +17,7 @@ pub struct GeminiConfig {
     pub api_key: Option<String>,
     pub api_base: Option<String>,
     pub auth: Option<String>,
+    pub oauth: Option<Box<OAuthConfig>>,
     #[serde(default)]
     pub models: Vec<ModelData>,
     pub patch: Option<RequestPatch>,
@@ -85,9 +86,17 @@ async fn prepare_chat_completions(
     client: &ReqwestClient,
     data: ChatCompletionsData,
 ) -> Result<RequestData> {
-    let api_base = self_
+    let uses_oauth = self_.config.auth.as_deref() == Some("oauth");
-        .get_api_base()
+
-        .unwrap_or_else(|_| API_BASE.to_string());
+    if !uses_oauth && self_.config.oauth.is_some() {
+        bail!(
+            "'{}' has an `oauth:` block configured but `auth: oauth` is not set; the oauth block would be ignored. Set `auth: oauth` (and run 'coyote --authenticate {}') or remove the oauth block.",
+            self_.name(),
+            self_.name()
+        );
+    }
+
+    let api_base = resolve_api_base(self_)?;
 
     let func = match data.stream {
         true => "streamGenerateContent",
@@ -104,11 +113,9 @@ async fn prepare_chat_completions(
     let body = gemini_build_chat_completions_body(data, &self_.model)?;
     let mut request_data = RequestData::new(url, body);
 
-    let uses_oauth = self_.config.auth.as_deref() == Some("oauth");
-
     if uses_oauth {
-        let provider = GeminiOAuthProvider;
+        let (provider, _) = resolve_oauth_provider(self_)?;
-        let ready = oauth::prepare_oauth_access_token(client, &provider, self_.name()).await?;
+        let ready = oauth::prepare_oauth_access_token(client, &*provider, self_.name()).await?;
         if !ready {
             bail!(
                 "OAuth configured but no tokens found for '{}'. Run: 'coyote --authenticate {}' or '.authenticate' in the REPL",
@@ -118,6 +125,9 @@ async fn prepare_chat_completions(
         }
         let token = get_access_token(self_.name())?;
         request_data.bearer_auth(token);
+        for (key, value) in provider.extra_request_headers() {
+            request_data.header(key, value);
+        }
     } else if let Ok(api_key) = self_.get_api_key() {
         request_data.header("x-goog-api-key", api_key);
     } else {
@@ -136,12 +146,18 @@ async fn prepare_embeddings(
     client: &ReqwestClient,
     data: &EmbeddingsData,
 ) -> Result<RequestData> {
-    let api_base = self_
-        .get_api_base()
-        .unwrap_or_else(|_| API_BASE.to_string());
-
     let uses_oauth = self_.config.auth.as_deref() == Some("oauth");
 
+    if !uses_oauth && self_.config.oauth.is_some() {
+        bail!(
+            "'{}' has an `oauth:` block configured but `auth: oauth` is not set; the oauth block would be ignored. Set `auth: oauth` (and run 'coyote --authenticate {}') or remove the oauth block.",
+            self_.name(),
+            self_.name()
+        );
+    }
+
+    let api_base = resolve_api_base(self_)?;
+
     let url = if uses_oauth {
         format!(
             "{}/models/{}:batchEmbedContents",
@@ -177,8 +193,8 @@ async fn prepare_embeddings(
     let mut request_data = RequestData::new(url, body);
 
     if uses_oauth {
-        let provider = GeminiOAuthProvider;
+        let (provider, _) = resolve_oauth_provider(self_)?;
-        let ready = oauth::prepare_oauth_access_token(client, &provider, self_.name()).await?;
+        let ready = oauth::prepare_oauth_access_token(client, &*provider, self_.name()).await?;
         if !ready {
             bail!(
                 "OAuth configured but no tokens found for '{}'. Run: 'coyote --authenticate {}' or '.authenticate' in the REPL",
@@ -188,11 +204,72 @@ async fn prepare_embeddings(
         }
         let token = get_access_token(self_.name())?;
         request_data.bearer_auth(token);
+        for (key, value) in provider.extra_request_headers() {
+            request_data.header(key, value);
+        }
     }
 
     Ok(request_data)
 }
 
+fn resolve_api_base(self_: &GeminiClient) -> Result<String> {
+    resolve_api_base_against(self_, &ALL_PROVIDER_MODELS)
+}
+
+fn resolve_api_base_against(
+    self_: &GeminiClient,
+    all_provider_models: &[ProviderModels],
+) -> Result<String> {
+    if let Ok(api_base) = self_.get_api_base() {
+        return Ok(api_base);
+    }
+
+    let uses_config_oauth = self_.config.auth.as_deref() == Some("oauth")
+        && match locate_client_config(self_) {
+            Ok(cc) => oauth::config_oauth_for_client(cc, all_provider_models).is_some(),
+            // Safe: on locate failure, provider resolution bails when an inline oauth block exists; otherwise the stock provider is used and issuer-stamped gateway tokens are rejected before attach.
+            Err(_) => self_.config.oauth.is_some(),
+        };
+
+    if uses_config_oauth {
+        bail!(
+            "'{}' has a config-driven OAuth configuration (an `oauth:` block in the client entry or models catalog) but no `api_base`; refusing to fall back to {} (the oauth token would be sent to the wrong host). Set `api_base` on the '{}' client entry.",
+            self_.name(),
+            API_BASE,
+            self_.name()
+        );
+    }
+
+    Ok(API_BASE.to_string())
+}
+
+fn locate_client_config(self_: &GeminiClient) -> Result<&ClientConfig> {
+    let client_name = self_.name();
+    self_
+        .app_config()
+        .clients
+        .iter()
+        .find(|cc| {
+            matches!(
+                cc,
+                ClientConfig::GeminiConfig(c)
+                if c.name.as_deref().unwrap_or(GeminiClient::NAME) == client_name
+            )
+        })
+        .ok_or_else(|| anyhow!("Could not locate ClientConfig entry for '{}'", client_name))
+}
+
+fn resolve_oauth_provider(self_: &GeminiClient) -> Result<(Box<dyn OAuthProvider>, bool)> {
+    match locate_client_config(self_) {
+        Ok(cc) => Ok(oauth::gemini_oauth_provider_for_client(
+            cc,
+            &ALL_PROVIDER_MODELS,
+        )),
+        Err(_) if self_.config.oauth.is_none() => Ok((Box::new(GeminiOAuthProvider), true)),
+        Err(err) => Err(err),
+    }
+}
+
 async fn embeddings(builder: RequestBuilder, _model: &Model) -> Result<EmbeddingsOutput> {
     let res = builder.send().await?;
     let status = res.status();
@@ -219,3 +296,296 @@ struct EmbeddingsResBody {
 struct EmbeddingsResBodyEmbedding {
     values: Vec<f32>,
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::client::access_token::set_access_token;
+    use crate::config::AppConfig;
+    use chrono::Utc;
+    use std::sync::Arc;
+
+    fn gemini_config(name: &str, auth: Option<&str>, oauth: Option<OAuthConfig>) -> GeminiConfig {
+        GeminiConfig {
+            name: Some(name.into()),
+            api_base: oauth
+                .as_ref()
+                .map(|_| "https://gateway.example/v1".to_string()),
+            auth: auth.map(str::to_string),
+            oauth: oauth.map(Box::new),
+            ..Default::default()
+        }
+    }
+
+    fn make_client(config: GeminiConfig, clients: Vec<ClientConfig>) -> GeminiClient {
+        GeminiClient {
+            app_config: Arc::new(AppConfig {
+                clients,
+                ..AppConfig::default()
+            }),
+            config,
+            model: Model::new("gemini", "gemini-test"),
+        }
+    }
+
+    fn minimal_oauth_config() -> OAuthConfig {
+        serde_yaml::from_str("client_id: gateway\ntoken_url: https://gateway.example/token")
+            .unwrap()
+    }
+
+    fn prepare_chat(client: &GeminiClient) -> Result<RequestData> {
+        let data = ChatCompletionsData {
+            messages: vec![Message::new(
+                MessageRole::User,
+                MessageContent::Text("hello".to_string()),
+            )],
+            temperature: None,
+            top_p: None,
+            reasoning_effort: None,
+            functions: None,
+            stream: false,
+        };
+        tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .unwrap()
+            .block_on(prepare_chat_completions(
+                client,
+                &ReqwestClient::new(),
+                data,
+            ))
+    }
+
+    fn prepare_embed(client: &GeminiClient) -> Result<RequestData> {
+        let data = EmbeddingsData::new(vec!["hello".to_string()], false);
+        tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .unwrap()
+            .block_on(prepare_embeddings(client, &ReqwestClient::new(), &data))
+    }
+
+    #[test]
+    fn oauth_block_without_api_base_is_rejected() {
+        let name = "gemini-gate-apibase-missing-test";
+        let mut config = gemini_config(name, Some("oauth"), Some(minimal_oauth_config()));
+        config.api_base = None;
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+
+        let err = resolve_api_base(&client).unwrap_err().to_string();
+
+        assert!(
+            err.contains(name) && err.contains("refusing to fall back"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn catalog_only_oauth_block_without_api_base_is_rejected() {
+        let name = "gemini-gate-catalog-oauth-test";
+        let config = gemini_config(name, Some("oauth"), None);
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+        let catalog = vec![ProviderModels {
+            provider: name.into(),
+            oauth: Some(minimal_oauth_config()),
+            models: vec![],
+        }];
+
+        let err = resolve_api_base_against(&client, &catalog)
+            .unwrap_err()
+            .to_string();
+
+        assert!(
+            err.contains(name) && err.contains("refusing to fall back"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn oauth_block_with_api_base_resolves_it() {
+        let name = "gemini-gate-apibase-set-test";
+        let config = gemini_config(name, Some("oauth"), Some(minimal_oauth_config()));
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+
+        let api_base = resolve_api_base(&client).unwrap();
+
+        assert_eq!(api_base, "https://gateway.example/v1");
+    }
+
+    #[test]
+    fn no_oauth_block_falls_back_to_stock_api_base() {
+        let name = "gemini-gate-apibase-fallback-test";
+        let config = gemini_config(name, None, None);
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+
+        let api_base = resolve_api_base(&client).unwrap();
+
+        assert_eq!(api_base, API_BASE);
+    }
+
+    #[test]
+    fn oauth_block_without_auth_oauth_is_rejected() {
+        let name = "gemini-gate-contradiction-test";
+        let mut config = gemini_config(name, None, Some(minimal_oauth_config()));
+        config.api_key = Some("sk-test".into());
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+
+        let err = match prepare_chat(&client) {
+            Ok(_) => panic!("expected the contradictory config to be rejected"),
+            Err(err) => err.to_string(),
+        };
+
+        assert!(
+            err.contains("has an `oauth:` block configured but `auth: oauth` is not set"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn config_oauth_embeddings_url_omits_key_param() {
+        let name = "gemini-gate-embed-oauth-test";
+        let config = gemini_config(name, Some("oauth"), Some(minimal_oauth_config()));
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+        set_access_token(
+            name,
+            "gateway-at".into(),
+            Utc::now().timestamp() + 3600,
+            None,
+        );
+
+        let request_data = prepare_embed(&client).unwrap();
+
+        assert_eq!(
+            request_data.url,
+            "https://gateway.example/v1/models/gemini-test:batchEmbedContents"
+        );
+        assert_eq!(
+            request_data
+                .headers
+                .get("authorization")
+                .map(String::as_str),
+            Some("Bearer gateway-at")
+        );
+    }
+
+    #[test]
+    fn api_key_embeddings_url_appends_key_param() {
+        let name = "gemini-gate-embed-apikey-test";
+        let mut config = gemini_config(name, None, None);
+        config.api_key = Some("sk-test".into());
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+
+        let request_data = prepare_embed(&client).unwrap();
+
+        assert_eq!(
+            request_data.url,
+            format!("{API_BASE}/models/gemini-test:batchEmbedContents?key=sk-test")
+        );
+    }
+
+    #[test]
+    fn config_oauth_extra_request_headers_reach_request() {
+        let name = "gemini-gate-extra-headers-test";
+        let oauth: OAuthConfig = serde_yaml::from_str(
+            "client_id: gateway\ntoken_url: https://gateway.example/token\nextra_request_headers:\n  x-gateway-tenant: acme",
+        )
+        .unwrap();
+        let config = gemini_config(name, Some("oauth"), Some(oauth));
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+        set_access_token(
+            name,
+            "gateway-at".into(),
+            Utc::now().timestamp() + 3600,
+            None,
+        );
+
+        let request_data = prepare_chat(&client).unwrap();
+
+        assert_eq!(
+            request_data
+                .headers
+                .get("x-gateway-tenant")
+                .map(String::as_str),
+            Some("acme")
+        );
+    }
+
+    #[test]
+    fn catalog_oauth_block_with_api_key_auth_falls_back_to_stock_api_base() {
+        let name = "gemini-gate-catalog-apikey-test";
+        let mut config = gemini_config(name, None, None);
+        config.api_key = Some("sk-test".into());
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+        let catalog = vec![ProviderModels {
+            provider: name.into(),
+            oauth: Some(minimal_oauth_config()),
+            models: vec![],
+        }];
+
+        let api_base = resolve_api_base_against(&client, &catalog).unwrap();
+
+        assert_eq!(api_base, API_BASE);
+    }
+
+    #[test]
+    fn missing_config_entry_without_inline_oauth_resolves_stock_provider() {
+        let config = gemini_config("gemini-gate-missing-entry-test", Some("oauth"), None);
+        let client = make_client(config, vec![]);
+
+        let (_, is_stock) = resolve_oauth_provider(&client).unwrap();
+
+        assert!(is_stock);
+    }
+
+    #[test]
+    fn missing_config_entry_with_inline_oauth_is_a_hard_error() {
+        let config = gemini_config(
+            "gemini-gate-missing-entry-inline-test",
+            Some("oauth"),
+            Some(minimal_oauth_config()),
+        );
+        let client = make_client(config, vec![]);
+
+        let err = match resolve_oauth_provider(&client) {
+            Ok(_) => panic!("expected the missing ClientConfig entry to be a hard error"),
+            Err(err) => err.to_string(),
+        };
+
+        assert!(
+            err.contains("Could not locate ClientConfig entry"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn auth_mismatch_bails_before_missing_api_base_guard() {
+        let name = "gemini-gate-bail-order-test";
+        let mut config = gemini_config(name, None, Some(minimal_oauth_config()));
+        config.api_base = None;
+        let client = make_client(config.clone(), vec![ClientConfig::GeminiConfig(config)]);
+
+        let err = match prepare_chat(&client) {
+            Ok(_) => panic!("expected the contradictory config to be rejected"),
+            Err(err) => err.to_string(),
+        };
+
+        assert!(
+            err.contains("has an `oauth:` block configured but `auth: oauth` is not set")
+                && !err.contains("refusing to fall back"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn shipped_catalog_resolves_stock_gemini_provider() {
+        let cc = ClientConfig::GeminiConfig(gemini_config("gemini", Some("oauth"), None));
+        let bundled: Vec<ProviderModels> = serde_yaml::from_str(MODELS_YAML).unwrap();
+
+        let (_, is_stock) = oauth::gemini_oauth_provider_for_client(&cc, &bundled);
+
+        assert!(
+            is_stock,
+            "bundled models.yaml must not carry a gemini oauth block: it would silently replace the stock Google oauth provider"
+        );
+    }
+}

src/client/message.rs

@@ -188,15 +188,27 @@ pub struct ImageUrl {
     pub url: String,
 }
 
-/// An extended-thinking block returned by Anthropic-protocol models.
+/// An extended-thinking block returned by Anthropic-protocol models or an
-/// Serialized to match the API wire format (`type: thinking` / `type: redacted_thinking`)
+/// OpenAI Responses reasoning item. Serialized to match each API's wire
+/// format (`type: thinking` / `type: redacted_thinking` / `type: reasoning`)
 /// so blocks can be replayed verbatim, signature intact, in subsequent
-/// tool-loop rounds as the API requires.
+/// tool-loop rounds as the APIs require.
 #[derive(Debug, Clone, Deserialize, Serialize)]
 #[serde(tag = "type", rename_all = "snake_case")]
 pub enum ThinkingBlock {
-    Thinking { thinking: String, signature: String },
+    Thinking {
-    RedactedThinking { data: String },
+        thinking: String,
+        signature: String,
+    },
+    RedactedThinking {
+        data: String,
+    },
+    Reasoning {
+        id: String,
+        summary: serde_json::Value,
+        #[serde(default, skip_serializing_if = "Option::is_none")]
+        encrypted_content: Option<String>,
+    },
 }
 
 #[derive(Debug, Clone, Deserialize, Serialize)]
@@ -263,3 +275,87 @@ pub fn extract_system_message(messages: &mut Vec<Message>) -> Option<String> {
 
     None
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use serde_json::json;
+
+    #[test]
+    fn old_session_thinking_blocks_still_deserialize() {
+        let json = json!([
+            { "type": "thinking", "thinking": "hmm", "signature": "sig123" },
+            { "type": "redacted_thinking", "data": "b64data" },
+        ]);
+
+        let blocks: Vec<ThinkingBlock> = serde_json::from_value(json.clone()).unwrap();
+
+        assert!(
+            matches!(&blocks[0], ThinkingBlock::Thinking { thinking, signature } if thinking == "hmm" && signature == "sig123")
+        );
+        assert!(
+            matches!(&blocks[1], ThinkingBlock::RedactedThinking { data } if data == "b64data")
+        );
+        assert_eq!(serde_json::to_value(&blocks).unwrap(), json);
+    }
+
+    #[test]
+    fn reasoning_block_round_trips() {
+        let json = json!({
+            "type": "reasoning",
+            "id": "rs_1",
+            "summary": [{ "type": "summary_text", "text": "thinking about it" }],
+            "encrypted_content": "enc123",
+        });
+
+        let block: ThinkingBlock = serde_json::from_value(json.clone()).unwrap();
+
+        assert!(
+            matches!(&block, ThinkingBlock::Reasoning { id, encrypted_content, .. } if id == "rs_1" && encrypted_content.as_deref() == Some("enc123"))
+        );
+        assert_eq!(serde_json::to_value(&block).unwrap(), json);
+    }
+
+    #[test]
+    fn reasoning_block_without_encrypted_content_round_trips() {
+        let json = json!({
+            "type": "reasoning",
+            "id": "rs_1",
+            "summary": [],
+        });
+
+        let block: ThinkingBlock = serde_json::from_value(json.clone()).unwrap();
+
+        assert!(
+            matches!(&block, ThinkingBlock::Reasoning { encrypted_content, .. } if encrypted_content.is_none())
+        );
+        assert_eq!(serde_json::to_value(&block).unwrap(), json);
+    }
+
+    #[test]
+    fn thinking_blocks_round_trip_through_yaml() {
+        let json = json!([
+            { "type": "thinking", "thinking": "hmm", "signature": "sig123" },
+            { "type": "redacted_thinking", "data": "b64data" },
+            {
+                "type": "reasoning",
+                "id": "rs_1",
+                "summary": [{ "type": "summary_text", "text": "thinking about it" }],
+                "encrypted_content": "enc123",
+            },
+            {
+                "type": "reasoning",
+                "id": "rs_2",
+                "summary": [],
+            },
+        ]);
+
+        let blocks: Vec<ThinkingBlock> = serde_json::from_value(json.clone()).unwrap();
+
+        let yaml = serde_yaml::to_string(&blocks).unwrap();
+        assert!(!yaml.contains("encrypted_content: null"));
+
+        let restored: Vec<ThinkingBlock> = serde_yaml::from_str(&yaml).unwrap();
+        assert_eq!(serde_json::to_value(&restored).unwrap(), json);
+    }
+}

src/client/model.rs

@@ -536,4 +536,25 @@ reasoning_levels: [none, low, medium, high]
 
         assert_eq!(data.default_reasoning_effort.as_deref(), Some("none"));
     }
+
+    #[test]
+    fn shipped_catalog_carries_no_credentials_and_only_intended_oauth_defaults() {
+        assert!(
+            !super::super::common::MODELS_YAML.contains("api_key"),
+            "the shipped models.yaml must never carry an api key: the model catalog is credential-free by policy"
+        );
+
+        let bundled: Vec<ProviderModels> =
+            serde_yaml::from_str(super::super::common::MODELS_YAML).unwrap();
+        let with_oauth: Vec<&str> = bundled
+            .iter()
+            .filter(|p| p.oauth.is_some())
+            .map(|p| p.provider.as_str())
+            .collect();
+        assert_eq!(
+            with_oauth,
+            ["xai"],
+            "oauth blocks in the shipped models.yaml are limited to providers with no built-in stock oauth path (currently only xai's bundled defaults); adding one for claude/openai/gemini would silently swap stock oauth users onto a non-stock provider"
+        );
+    }
 }

src/client/oauth.rs

@@ -1,5 +1,8 @@
 use super::access_token::{clear_rejected, is_rejected, is_valid_access_token, set_access_token};
+use super::claude_oauth::ClaudeOAuthProvider;
+use super::gemini_oauth::GeminiOAuthProvider;
 use super::openai_compatible_oauth::OpenAICompatibleOAuthProvider;
+use super::openai_oauth::OpenAIOAuthProvider;
 use super::{ClientConfig, ProviderModels};
 use crate::config::paths;
 use anyhow::{Context, Error, Result, anyhow, bail};
@@ -211,6 +214,9 @@ pub trait OAuthProvider: Send + Sync {
     fn use_pkce_in_device_flow(&self) -> bool {
         false
     }
+    fn requires_issuer_stamp(&self) -> bool {
+        false
+    }
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -221,6 +227,10 @@ pub struct OAuthTokens {
     pub expires_at: i64,
     #[serde(default)]
     pub account_id: Option<String>,
+    /// `"{token_url}|{client_id}"` of the issuing provider, stamped on save.
+    /// `None` on files predating the stamp; those are grandfathered.
+    #[serde(default)]
+    pub issuer: Option<String>,
 }
 
 const TOKEN_ENDPOINT_TIMEOUT: Duration = Duration::from_secs(30);
@@ -376,9 +386,10 @@ async fn run_pkce_flow(provider: &dyn OAuthProvider, client_name: &str) -> Resul
         refresh_token,
         expires_at,
         account_id,
+        issuer: None,
     };
 
-    save_oauth_tokens(client_name, &tokens)?;
+    store_tokens(client_name, provider, tokens)?;
 
     println!(
         "Successfully authenticated client '{}' with {} via OAuth. Tokens saved.",
@@ -430,8 +441,9 @@ async fn run_client_credentials_flow(
         refresh_token: None,
         expires_at,
         account_id: provider.extract_account_id(&response),
+        issuer: None,
     };
-    save_oauth_tokens(client_name, &tokens)?;
+    store_tokens(client_name, provider, tokens)?;
 
     Ok(())
 }
@@ -597,8 +609,9 @@ async fn run_device_code_flow(provider: &dyn OAuthProvider, client_name: &str) -
                 refresh_token,
                 expires_at,
                 account_id,
+                issuer: None,
             };
-            save_oauth_tokens(client_name, &tokens)?;
+            store_tokens(client_name, provider, tokens)?;
             println!(
                 "Successfully authenticated client '{}' with {} via OAuth (device_code). Tokens saved.",
                 client_name,
@@ -637,12 +650,22 @@ pub fn load_oauth_tokens(client_name: &str) -> Option<OAuthTokens> {
     serde_json::from_str(&content).ok()
 }
 
-fn save_oauth_tokens(client_name: &str, tokens: &OAuthTokens) -> Result<()> {
+/// Stamps the issuer fingerprint of `provider` before writing so stored
+/// tokens stay bound to the provider that issued them.
+fn save_oauth_tokens(
+    client_name: &str,
+    provider: &(impl OAuthProvider + ?Sized),
+    tokens: &OAuthTokens,
+) -> Result<()> {
+    let tokens = OAuthTokens {
+        issuer: Some(issuer_fingerprint(provider)),
+        ..tokens.clone()
+    };
     let path = paths::token_file(client_name);
     if let Some(parent) = path.parent() {
         fs::create_dir_all(parent)?;
     }
-    let json = serde_json::to_string_pretty(tokens)?;
+    let json = serde_json::to_string_pretty(&tokens)?;
     // Write-then-rename so a crash mid-write never truncates the live token file.
     let mut tmp = path.clone().into_os_string();
     tmp.push(".tmp");
@@ -660,6 +683,35 @@ fn save_oauth_tokens(client_name: &str, tokens: &OAuthTokens) -> Result<()> {
     Ok(())
 }
 
+/// Persists freshly-minted tokens and primes the in-memory cache so a running
+/// session picks them up immediately instead of the stale token.
+fn store_tokens(
+    client_name: &str,
+    provider: &(impl OAuthProvider + ?Sized),
+    tokens: OAuthTokens,
+) -> Result<()> {
+    save_oauth_tokens(client_name, provider, &tokens)?;
+    set_access_token(
+        client_name,
+        tokens.access_token,
+        tokens.expires_at,
+        tokens.account_id,
+    );
+    clear_rejected(client_name);
+    Ok(())
+}
+
+fn issuer_fingerprint(provider: &(impl OAuthProvider + ?Sized)) -> String {
+    format!("{}|{}", provider.token_url(), provider.client_id())
+}
+
+fn issuer_matches(tokens: &OAuthTokens, provider: &(impl OAuthProvider + ?Sized)) -> bool {
+    match &tokens.issuer {
+        Some(issuer) => *issuer == issuer_fingerprint(provider),
+        None => !provider.requires_issuer_stamp(),
+    }
+}
+
 pub(crate) fn token_response_keys(response: &Value) -> String {
     match response.as_object() {
         Some(map) => {
@@ -764,9 +816,10 @@ pub async fn refresh_oauth_token(
         refresh_token,
         expires_at,
         account_id,
+        issuer: None,
     };
 
-    save_oauth_tokens(client_name, &new_tokens)?;
+    save_oauth_tokens(client_name, provider, &new_tokens)?;
 
     Ok(new_tokens)
 }
@@ -799,6 +852,10 @@ pub async fn prepare_oauth_access_token(
         None => return Ok(false),
     };
 
+    if !issuer_matches(&tokens, provider) {
+        return Ok(false);
+    }
+
     let tokens = if Utc::now().timestamp() >= tokens.expires_at
         || is_rejected(client_name, &tokens.access_token)
     {
@@ -817,6 +874,10 @@ pub async fn prepare_oauth_access_token(
             None => return Ok(false),
         };
 
+        if !issuer_matches(&tokens, provider) {
+            return Ok(false);
+        }
+
         if Utc::now().timestamp() >= tokens.expires_at
             || is_rejected(client_name, &tokens.access_token)
         {
@@ -998,13 +1059,85 @@ fn listen_for_oauth_callback(redirect_uri: &str) -> Result<(String, String)> {
 
 pub fn get_oauth_provider(provider_type: &str) -> Option<Box<dyn OAuthProvider>> {
     match provider_type {
-        "claude" => Some(Box::new(super::claude_oauth::ClaudeOAuthProvider)),
+        "claude" => Some(Box::new(ClaudeOAuthProvider)),
-        "gemini" => Some(Box::new(super::gemini_oauth::GeminiOAuthProvider)),
+        "gemini" => Some(Box::new(GeminiOAuthProvider)),
-        "openai" => Some(Box::new(super::openai_oauth::OpenAIOAuthProvider)),
+        "openai" => Some(Box::new(OpenAIOAuthProvider)),
         _ => None,
     }
 }
 
+pub(crate) fn config_oauth_for_client(
+    client_config: &ClientConfig,
+    all_provider_models: &[ProviderModels],
+) -> Option<OAuthConfig> {
+    let (client_name, _, _) = client_config_info(client_config);
+    let user_oauth = match client_config {
+        ClientConfig::OpenAICompatibleConfig(c) => c.oauth.clone().map(|b| *b),
+        ClientConfig::ClaudeConfig(c) => c.oauth.clone().map(|b| *b),
+        ClientConfig::OpenAIConfig(c) => c.oauth.clone().map(|b| *b),
+        ClientConfig::GeminiConfig(c) => c.oauth.clone().map(|b| *b),
+        _ => return None,
+    };
+    let base = all_provider_models
+        .iter()
+        .find(|p| p.provider == client_name)
+        .and_then(|p| p.oauth.clone());
+    match (base, user_oauth) {
+        (None, None) => None,
+        (Some(b), None) => Some(b),
+        (None, Some(u)) => Some(u),
+        (Some(b), Some(u)) => Some(b.merge(u)),
+    }
+}
+
+/// Resolves a config-driven `oauth:` block to the generic provider, or falls back to `stock`.
+/// Returns the provider and whether the stock provider is in use.
+fn oauth_provider_for_client(
+    client_config: &ClientConfig,
+    all_provider_models: &[ProviderModels],
+    stock: fn() -> Box<dyn OAuthProvider>,
+) -> (Box<dyn OAuthProvider>, bool) {
+    let (client_name, _, _) = client_config_info(client_config);
+    match config_oauth_for_client(client_config, all_provider_models) {
+        Some(merged) => (
+            Box::new(OpenAICompatibleOAuthProvider {
+                config: merged,
+                client_name: client_name.to_string(),
+                requires_issuer_stamp: true,
+            }),
+            false,
+        ),
+        None => (stock(), true),
+    }
+}
+
+pub(crate) fn claude_oauth_provider_for_client(
+    client_config: &ClientConfig,
+    all_provider_models: &[ProviderModels],
+) -> (Box<dyn OAuthProvider>, bool) {
+    oauth_provider_for_client(client_config, all_provider_models, || {
+        Box::new(ClaudeOAuthProvider)
+    })
+}
+
+pub(crate) fn openai_oauth_provider_for_client(
+    client_config: &ClientConfig,
+    all_provider_models: &[ProviderModels],
+) -> (Box<dyn OAuthProvider>, bool) {
+    oauth_provider_for_client(client_config, all_provider_models, || {
+        Box::new(OpenAIOAuthProvider)
+    })
+}
+
+pub(crate) fn gemini_oauth_provider_for_client(
+    client_config: &ClientConfig,
+    all_provider_models: &[ProviderModels],
+) -> (Box<dyn OAuthProvider>, bool) {
+    oauth_provider_for_client(client_config, all_provider_models, || {
+        Box::new(GeminiOAuthProvider)
+    })
+}
+
 pub fn get_oauth_provider_for_client(
     client_config: &ClientConfig,
     all_provider_models: &[ProviderModels],
@@ -1015,23 +1148,29 @@ pub fn get_oauth_provider_for_client(
     }
 
     match client_config {
-        ClientConfig::OpenAICompatibleConfig(c) => {
+        ClientConfig::OpenAICompatibleConfig(_) => {
-            let base = all_provider_models
+            let merged = config_oauth_for_client(client_config, all_provider_models)?;
-                .iter()
-                .find(|p| p.provider == client_name)
-                .and_then(|p| p.oauth.clone());
-            let user_oauth = c.oauth.clone().map(|b| *b);
-            let merged = match (base, user_oauth) {
-                (None, None) => return None,
-                (Some(b), None) => b,
-                (None, Some(u)) => u,
-                (Some(b), Some(u)) => b.merge(u),
-            };
             Some(Box::new(OpenAICompatibleOAuthProvider {
                 config: merged,
                 client_name: client_name.to_string(),
+                requires_issuer_stamp: false,
             }))
         }
+        ClientConfig::ClaudeConfig(_) => {
+            let (provider, _) =
+                claude_oauth_provider_for_client(client_config, all_provider_models);
+            Some(provider)
+        }
+        ClientConfig::OpenAIConfig(_) => {
+            let (provider, _) =
+                openai_oauth_provider_for_client(client_config, all_provider_models);
+            Some(provider)
+        }
+        ClientConfig::GeminiConfig(_) => {
+            let (provider, _) =
+                gemini_oauth_provider_for_client(client_config, all_provider_models);
+            Some(provider)
+        }
         _ => get_oauth_provider(provider_type),
     }
 }
@@ -1097,6 +1236,9 @@ mod tests {
 
     use super::*;
     use crate::client::access_token::{distrust_access_token, get_access_token};
+    use crate::client::claude::ClaudeConfig;
+    use crate::client::gemini::GeminiConfig;
+    use crate::client::openai::OpenAIConfig;
     use crate::client::openai_compatible::OpenAICompatibleConfig;
     use crate::client::{ModelData, ProviderModels};
     use crate::utils::get_env_name;
@@ -1318,6 +1460,61 @@ echo_pkce_in_token_exchange: true
             api_key: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
+            wire_api: None,
+            models: vec![],
+            patch: None,
+            extra: None,
+        })
+    }
+
+    fn make_claude_client(
+        name: &str,
+        auth: Option<&str>,
+        oauth: Option<OAuthConfig>,
+    ) -> ClientConfig {
+        ClientConfig::ClaudeConfig(ClaudeConfig {
+            name: Some(name.into()),
+            api_key: None,
+            api_base: None,
+            auth: auth.map(str::to_string),
+            oauth: oauth.map(Box::new),
+            models: vec![],
+            prompt_cache: None,
+            patch: None,
+            extra: None,
+        })
+    }
+
+    fn make_openai_client(
+        name: &str,
+        auth: Option<&str>,
+        oauth: Option<OAuthConfig>,
+    ) -> ClientConfig {
+        ClientConfig::OpenAIConfig(OpenAIConfig {
+            name: Some(name.into()),
+            api_key: None,
+            api_base: None,
+            organization_id: None,
+            auth: auth.map(str::to_string),
+            oauth: oauth.map(Box::new),
+            wire_api: None,
+            models: vec![],
+            patch: None,
+            extra: None,
+        })
+    }
+
+    fn make_gemini_client(
+        name: &str,
+        auth: Option<&str>,
+        oauth: Option<OAuthConfig>,
+    ) -> ClientConfig {
+        ClientConfig::GeminiConfig(GeminiConfig {
+            name: Some(name.into()),
+            api_key: None,
+            api_base: None,
+            auth: auth.map(str::to_string),
+            oauth: oauth.map(Box::new),
             models: vec![],
             patch: None,
             extra: None,
@@ -1386,6 +1583,173 @@ echo_pkce_in_token_exchange: true
         assert!(get_oauth_provider_for_client(&cc, &models).is_none());
     }
 
+    #[test]
+    fn claude_client_with_user_oauth_block_uses_generic_provider() {
+        let mut user = empty_user_override("gateway-id", "https://gateway.example/token");
+        user.device_authorization_url = Some("https://gateway.example/device".into());
+        let cc = make_claude_client("claude", Some("oauth"), Some(user));
+
+        let provider = get_oauth_provider_for_client(&cc, &[]).unwrap();
+
+        assert_eq!(provider.provider_name(), "claude");
+        assert_eq!(provider.client_id(), "gateway-id");
+        assert_eq!(provider.token_url(), "https://gateway.example/token");
+        assert_eq!(
+            provider.device_authorization_url(),
+            Some("https://gateway.example/device")
+        );
+    }
+
+    #[test]
+    fn claude_client_without_oauth_block_falls_back_to_stock_provider() {
+        let cc = make_claude_client("claude", Some("oauth"), None);
+
+        let provider = get_oauth_provider_for_client(&cc, &[]).unwrap();
+
+        assert_eq!(provider.provider_name(), "claude");
+        assert_eq!(provider.client_id(), "9d1c250a-e61b-44d9-88ed-5944d1962f5e");
+        assert_eq!(
+            provider.extra_request_headers(),
+            vec![("anthropic-beta", "oauth-2025-04-20")]
+        );
+    }
+
+    #[test]
+    fn claude_client_merges_bundled_defaults_with_user_override() {
+        let base = base_config();
+        let user = empty_user_override("user-id", "https://user.example/token");
+        let models = vec![make_provider_models("claude", Some(base))];
+        let cc = make_claude_client("claude", Some("oauth"), Some(user));
+
+        let provider = get_oauth_provider_for_client(&cc, &models).unwrap();
+
+        assert_eq!(provider.provider_name(), "claude");
+        assert_eq!(provider.client_id(), "user-id");
+        assert_eq!(provider.token_url(), "https://user.example/token");
+        assert_eq!(provider.authorize_url(), "https://base.example/authorize");
+    }
+
+    #[test]
+    fn claude_bundled_only_oauth_block_uses_generic_provider() {
+        let base = base_config();
+        let models = vec![make_provider_models("claude", Some(base))];
+        let cc = make_claude_client("claude", Some("oauth"), None);
+
+        let (provider, is_stock) = claude_oauth_provider_for_client(&cc, &models);
+
+        assert!(!is_stock);
+        assert_eq!(provider.client_id(), "base-id");
+        assert_eq!(provider.token_url(), "https://base.example/token");
+        assert!(provider.extra_request_headers().is_empty());
+    }
+
+    #[test]
+    fn claude_config_provider_requires_issuer_stamp() {
+        let user = empty_user_override("gateway-id", "https://gateway.example/token");
+        let cc = make_claude_client("claude", Some("oauth"), Some(user));
+
+        let (provider, is_stock) = claude_oauth_provider_for_client(&cc, &[]);
+
+        assert!(!is_stock);
+        assert!(provider.requires_issuer_stamp());
+    }
+
+    #[test]
+    fn claude_stock_provider_grandfathers_legacy_tokens() {
+        let cc = make_claude_client("claude", Some("oauth"), None);
+
+        let (provider, is_stock) = claude_oauth_provider_for_client(&cc, &[]);
+
+        assert!(is_stock);
+        assert!(!provider.requires_issuer_stamp());
+    }
+
+    #[test]
+    fn openai_client_with_user_oauth_block_uses_generic_provider() {
+        let user = empty_user_override("gateway-id", "https://gateway.example/token");
+        let cc = make_openai_client("openai", Some("oauth"), Some(user));
+
+        let provider = get_oauth_provider_for_client(&cc, &[]).unwrap();
+
+        assert_eq!(provider.provider_name(), "openai");
+        assert_eq!(provider.client_id(), "gateway-id");
+        assert_eq!(provider.token_url(), "https://gateway.example/token");
+    }
+
+    #[test]
+    fn openai_client_without_oauth_block_falls_back_to_stock_provider() {
+        let cc = make_openai_client("openai", Some("oauth"), None);
+
+        let provider = get_oauth_provider_for_client(&cc, &[]).unwrap();
+
+        assert_eq!(provider.provider_name(), "openai");
+        assert_eq!(provider.client_id(), "app_EMoamEEZ73f0CkXaXp7hrann");
+    }
+
+    #[test]
+    fn openai_config_provider_requires_issuer_stamp() {
+        let user = empty_user_override("gateway-id", "https://gateway.example/token");
+        let cc = make_openai_client("openai", Some("oauth"), Some(user));
+
+        let (provider, is_stock) = openai_oauth_provider_for_client(&cc, &[]);
+
+        assert!(!is_stock);
+        assert!(provider.requires_issuer_stamp());
+    }
+
+    #[test]
+    fn openai_stock_provider_grandfathers_legacy_tokens() {
+        let cc = make_openai_client("openai", Some("oauth"), None);
+
+        let (provider, is_stock) = openai_oauth_provider_for_client(&cc, &[]);
+
+        assert!(is_stock);
+        assert!(!provider.requires_issuer_stamp());
+    }
+
+    #[test]
+    fn gemini_client_with_user_oauth_block_uses_generic_provider() {
+        let user = empty_user_override("gateway-id", "https://gateway.example/token");
+        let cc = make_gemini_client("gemini", Some("oauth"), Some(user));
+
+        let provider = get_oauth_provider_for_client(&cc, &[]).unwrap();
+
+        assert_eq!(provider.provider_name(), "gemini");
+        assert_eq!(provider.client_id(), "gateway-id");
+        assert_eq!(provider.token_url(), "https://gateway.example/token");
+    }
+
+    #[test]
+    fn gemini_client_without_oauth_block_falls_back_to_stock_provider() {
+        let cc = make_gemini_client("gemini", Some("oauth"), None);
+
+        let provider = get_oauth_provider_for_client(&cc, &[]).unwrap();
+
+        assert_eq!(provider.provider_name(), "gemini");
+        assert_eq!(provider.token_url(), "https://oauth2.googleapis.com/token");
+    }
+
+    #[test]
+    fn gemini_config_provider_requires_issuer_stamp() {
+        let user = empty_user_override("gateway-id", "https://gateway.example/token");
+        let cc = make_gemini_client("gemini", Some("oauth"), Some(user));
+
+        let (provider, is_stock) = gemini_oauth_provider_for_client(&cc, &[]);
+
+        assert!(!is_stock);
+        assert!(provider.requires_issuer_stamp());
+    }
+
+    #[test]
+    fn gemini_stock_provider_grandfathers_legacy_tokens() {
+        let cc = make_gemini_client("gemini", Some("oauth"), None);
+
+        let (provider, is_stock) = gemini_oauth_provider_for_client(&cc, &[]);
+
+        assert!(is_stock);
+        assert!(!provider.requires_issuer_stamp());
+    }
+
     #[test]
     fn openai_compatible_provider_joins_scopes_with_spaces() {
         let mut cfg = base_config();
@@ -1394,6 +1758,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert_eq!(provider.scopes(), "one two three");
@@ -1408,6 +1773,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert_eq!(
@@ -1425,6 +1791,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert!(provider.uses_localhost_redirect());
@@ -1436,6 +1803,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: base_config(),
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert!(provider.extra_token_params().is_empty());
@@ -1546,6 +1914,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert_eq!(
@@ -1559,6 +1928,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: base_config(),
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert!(provider.device_authorization_url().is_none());
@@ -1569,6 +1939,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: base_config(),
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert!(!provider.use_pkce_in_device_flow());
@@ -1582,6 +1953,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert!(provider.use_pkce_in_device_flow());
@@ -1596,6 +1968,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert_eq!(provider.resource(), Some("https://rs.example/"));
@@ -1655,6 +2028,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert!(provider.fixed_redirect_uri().is_none());
@@ -1669,6 +2043,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert_eq!(
@@ -1686,6 +2061,7 @@ echo_pkce_in_token_exchange: true
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         assert_eq!(
@@ -1815,6 +2191,7 @@ extra_token_params:
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         let request = build_token_request(
@@ -1967,6 +2344,7 @@ extra_token_params:
         let provider = OpenAICompatibleOAuthProvider {
             config: base_config(),
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         let request = build_token_request(
@@ -1991,6 +2369,7 @@ extra_token_params:
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         let url = build_authorize_url(
@@ -2010,6 +2389,7 @@ extra_token_params:
         let provider = OpenAICompatibleOAuthProvider {
             config: base_config(),
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         let url = build_authorize_url(
@@ -2032,6 +2412,7 @@ extra_token_params:
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         let url = build_authorize_url(
@@ -2062,6 +2443,7 @@ extra_token_params:
         let provider = OpenAICompatibleOAuthProvider {
             config: cfg,
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         let params = build_device_authorization_params(&provider, "a b", None);
@@ -2076,6 +2458,7 @@ extra_token_params:
         let provider = OpenAICompatibleOAuthProvider {
             config: base_config(),
             client_name: "test".into(),
+            requires_issuer_stamp: false,
         };
 
         let params = build_device_authorization_params(&provider, "a b", Some("challenge"));
@@ -2094,9 +2477,10 @@ extra_token_params:
                 refresh_token: Some("rt-456".into()),
                 expires_at: 1234567890,
                 account_id: Some("acct-789".into()),
+                issuer: None,
             };
 
-            save_oauth_tokens("atomic-test", &tokens).unwrap();
+            save_oauth_tokens("atomic-test", &ResourceStubProvider, &tokens).unwrap();
 
             let loaded = load_oauth_tokens("atomic-test").unwrap();
             assert_eq!(loaded.access_token, "at-123");
@@ -2130,11 +2514,13 @@ extra_token_params:
             let expires_at = Utc::now().timestamp() + 3600;
             save_oauth_tokens(
                 client_name,
+                &ResourceStubProvider,
                 &OAuthTokens {
                     access_token: "rejected-at".into(),
                     refresh_token: None,
                     expires_at,
                     account_id: None,
+                    issuer: None,
                 },
             )
             .unwrap();
@@ -2169,11 +2555,13 @@ extra_token_params:
             assert!(distrust_access_token(client_name, "rejected-at"));
             save_oauth_tokens(
                 client_name,
+                &ResourceStubProvider,
                 &OAuthTokens {
                     access_token: "fresh-at".into(),
                     refresh_token: None,
                     expires_at,
                     account_id: None,
+                    issuer: None,
                 },
             )
             .unwrap();
@@ -2198,6 +2586,219 @@ extra_token_params:
         });
     }
 
+    #[test]
+    #[serial]
+    fn store_tokens_caches_token_and_clears_rejection() {
+        with_temp_cache(|| {
+            let client_name = "store-tokens-test";
+            let expires_at = Utc::now().timestamp() + 3600;
+            set_access_token(client_name, "old-at".into(), expires_at, None);
+            assert!(distrust_access_token(client_name, "old-at"));
+
+            store_tokens(
+                client_name,
+                &ResourceStubProvider,
+                OAuthTokens {
+                    access_token: "fresh-at".into(),
+                    refresh_token: None,
+                    expires_at,
+                    account_id: None,
+                    issuer: None,
+                },
+            )
+            .unwrap();
+
+            assert_eq!(get_access_token(client_name).unwrap(), "fresh-at");
+            assert!(is_valid_access_token(client_name));
+            assert!(
+                !is_rejected(client_name, "old-at"),
+                "rejection marker not cleared by store_tokens"
+            );
+        });
+    }
+
+    fn write_raw_token_file(client_name: &str, json: &str) {
+        let path = paths::token_file(client_name);
+        fs::create_dir_all(path.parent().unwrap()).unwrap();
+        fs::write(path, json).unwrap();
+    }
+
+    #[test]
+    #[serial]
+    fn save_oauth_tokens_stamps_issuer_fingerprint() {
+        with_temp_cache(|| {
+            save_oauth_tokens(
+                "issuer-stamp-test",
+                &ResourceStubProvider,
+                &OAuthTokens {
+                    access_token: "at".into(),
+                    refresh_token: None,
+                    expires_at: 1234567890,
+                    account_id: None,
+                    issuer: None,
+                },
+            )
+            .unwrap();
+
+            let loaded = load_oauth_tokens("issuer-stamp-test").unwrap();
+            assert_eq!(
+                loaded.issuer.as_deref(),
+                Some("https://as.example/token|stub-client")
+            );
+        });
+    }
+
+    #[test]
+    #[serial]
+    fn prepare_rejects_unexpired_tokens_with_mismatched_issuer() {
+        with_temp_cache(|| {
+            let client_name = "issuer-mismatch-valid-test";
+            let expires_at = Utc::now().timestamp() + 3600;
+            write_raw_token_file(
+                client_name,
+                &format!(
+                    r#"{{"access_token":"foreign-at","expires_at":{expires_at},"issuer":"https://old.example/token|old-client"}}"#
+                ),
+            );
+
+            let ready = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .unwrap()
+                .block_on(prepare_oauth_access_token(
+                    &ReqwestClient::new(),
+                    &ResourceStubProvider,
+                    client_name,
+                ))
+                .unwrap();
+
+            assert!(!ready);
+            assert!(
+                get_access_token(client_name).is_err(),
+                "foreign token must not enter the cache"
+            );
+        });
+    }
+
+    #[test]
+    #[serial]
+    fn prepare_rejects_expired_mismatched_issuer_without_refreshing() {
+        with_temp_cache(|| {
+            let client_name = "issuer-mismatch-expired-test";
+            write_raw_token_file(
+                client_name,
+                r#"{"access_token":"foreign-at","refresh_token":"foreign-rt","expires_at":0,"issuer":"https://old.example/token|old-client"}"#,
+            );
+
+            // A refresh attempt would POST to the stub's token_url and fail
+            // with a transport error; Ok(false) proves the refresh token was
+            // never forwarded.
+            let ready = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .unwrap()
+                .block_on(prepare_oauth_access_token(
+                    &ReqwestClient::new(),
+                    &ResourceStubProvider,
+                    client_name,
+                ))
+                .unwrap();
+
+            assert!(!ready);
+        });
+    }
+
+    #[test]
+    #[serial]
+    fn prepare_accepts_legacy_tokens_without_issuer() {
+        with_temp_cache(|| {
+            let client_name = "issuer-legacy-test";
+            let expires_at = Utc::now().timestamp() + 3600;
+            write_raw_token_file(
+                client_name,
+                &format!(r#"{{"access_token":"legacy-at","expires_at":{expires_at}}}"#),
+            );
+
+            let ready = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .unwrap()
+                .block_on(prepare_oauth_access_token(
+                    &ReqwestClient::new(),
+                    &ResourceStubProvider,
+                    client_name,
+                ))
+                .unwrap();
+
+            assert!(ready);
+            assert_eq!(get_access_token(client_name).unwrap(), "legacy-at");
+        });
+    }
+
+    #[test]
+    #[serial]
+    fn prepare_rejects_legacy_tokens_for_claude_config_provider() {
+        with_temp_cache(|| {
+            let client_name = "issuer-legacy-claude-config-test";
+            let user = empty_user_override("gateway-id", "https://gateway.example/token");
+            let cc = make_claude_client(client_name, Some("oauth"), Some(user));
+            let (provider, _) = claude_oauth_provider_for_client(&cc, &[]);
+            write_raw_token_file(
+                client_name,
+                r#"{"access_token":"legacy-at","refresh_token":"legacy-rt","expires_at":0}"#,
+            );
+
+            // Legacy files predate config-driven claude oauth, so they are
+            // Anthropic-issued; Ok(false) proves neither the access token
+            // nor the refresh token reaches the configured endpoint.
+            let ready = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .unwrap()
+                .block_on(prepare_oauth_access_token(
+                    &ReqwestClient::new(),
+                    &*provider,
+                    client_name,
+                ))
+                .unwrap();
+
+            assert!(!ready);
+            assert!(
+                get_access_token(client_name).is_err(),
+                "legacy token must not enter the cache"
+            );
+        });
+    }
+
+    #[test]
+    #[serial]
+    fn prepare_accepts_legacy_tokens_for_stock_claude_provider() {
+        with_temp_cache(|| {
+            let client_name = "issuer-legacy-claude-stock-test";
+            let cc = make_claude_client(client_name, Some("oauth"), None);
+            let (provider, _) = claude_oauth_provider_for_client(&cc, &[]);
+            let expires_at = Utc::now().timestamp() + 3600;
+            write_raw_token_file(
+                client_name,
+                &format!(r#"{{"access_token":"legacy-at","expires_at":{expires_at}}}"#),
+            );
+
+            let ready = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()
+                .unwrap()
+                .block_on(prepare_oauth_access_token(
+                    &ReqwestClient::new(),
+                    &*provider,
+                    client_name,
+                ))
+                .unwrap();
+
+            assert!(ready);
+            assert_eq!(get_access_token(client_name).unwrap(), "legacy-at");
+        });
+    }
+
     #[test]
     fn parse_refresh_response_invalid_grant_redacts_and_prompts_reauth() {
         let response = serde_json::json!({

src/client/openai_compatible.rs

@@ -16,6 +16,7 @@ pub struct OpenAICompatibleConfig {
     pub api_key: Option<String>,
     pub auth: Option<String>,
     pub oauth: Option<Box<OAuthConfig>>,
+    pub wire_api: Option<WireApi>,
     #[serde(default)]
     pub models: Vec<ModelData>,
     pub patch: Option<RequestPatch>,
@@ -42,10 +43,13 @@ impl Client for OpenAICompatibleClient {
         client: &ReqwestClient,
         data: ChatCompletionsData,
     ) -> Result<ChatCompletionsOutput> {
-        let request_data = prepare_chat_completions(self, client, data).await?;
+        let (request_data, wire) = prepare_chat_completions(self, client, data).await?;
         let builder = self.request_builder(client, request_data);
 
-        openai_chat_completions(builder, self.model()).await
+        match wire {
+            WireApi::Responses => openai_responses_chat_completions(builder, self.model()).await,
+            WireApi::Chat => openai_chat_completions(builder, self.model()).await,
+        }
     }
 
     async fn chat_completions_streaming_inner(
@@ -54,10 +58,15 @@ impl Client for OpenAICompatibleClient {
         handler: &mut SseHandler,
         data: ChatCompletionsData,
     ) -> Result<()> {
-        let request_data = prepare_chat_completions(self, client, data).await?;
+        let (request_data, wire) = prepare_chat_completions(self, client, data).await?;
         let builder = self.request_builder(client, request_data);
 
-        openai_chat_completions_streaming(builder, handler, self.model()).await
+        match wire {
+            WireApi::Responses => openai_responses_streaming(builder, handler).await,
+            WireApi::Chat => {
+                openai_chat_completions_streaming(builder, handler, self.model()).await
+            }
+        }
     }
 
     async fn embeddings_inner(
@@ -87,15 +96,22 @@ async fn prepare_chat_completions(
     self_: &OpenAICompatibleClient,
     client: &ReqwestClient,
     data: ChatCompletionsData,
-) -> Result<RequestData> {
+) -> Result<(RequestData, WireApi)> {
+    let wire = resolve_wire_api(self_.config.wire_api, false, false)?;
     let api_base = get_api_base_ext(self_)?;
-    let url = format!("{api_base}/chat/completions");
+    let url = match wire {
-    let body = openai_build_chat_completions_body(data, &self_.model);
+        WireApi::Responses => format!("{api_base}/responses"),
-    let mut request_data = RequestData::new(url, body);
+        WireApi::Chat => format!("{api_base}/chat/completions"),
+    };
+    let body = match wire {
+        WireApi::Responses => openai_build_responses_body(data, &self_.model),
+        WireApi::Chat => openai_build_chat_completions_body(data, &self_.model),
+    };
+    let mut request_data = RequestData::new(url, body).wire(wire);
 
     apply_auth(self_, client, &mut request_data).await?;
 
-    Ok(request_data)
+    Ok((request_data, wire))
 }
 
 async fn prepare_embeddings(
@@ -246,3 +262,137 @@ pub fn generic_build_rerank_body(data: &RerankData, model: &Model) -> Value {
     }
     body
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::config::AppConfig;
+    use std::sync::Arc;
+
+    fn compat_config(wire_api: Option<WireApi>) -> OpenAICompatibleConfig {
+        OpenAICompatibleConfig {
+            name: Some("compat-test".into()),
+            api_base: Some("https://compat.example/v1".into()),
+            api_key: Some("sk-test".into()),
+            auth: None,
+            oauth: None,
+            wire_api,
+            models: vec![],
+            patch: None,
+            extra: None,
+        }
+    }
+
+    fn make_client(config: OpenAICompatibleConfig) -> OpenAICompatibleClient {
+        OpenAICompatibleClient {
+            app_config: Arc::new(AppConfig::default()),
+            config,
+            model: Model::new("compat-test", "gpt-test"),
+        }
+    }
+
+    fn prepare(
+        client: &OpenAICompatibleClient,
+        stream: bool,
+    ) -> Result<(RequestData, WireApi)> {
+        let data = ChatCompletionsData {
+            messages: vec![Message::new(
+                MessageRole::User,
+                MessageContent::Text("hello".to_string()),
+            )],
+            temperature: None,
+            top_p: None,
+            reasoning_effort: None,
+            functions: None,
+            stream,
+        };
+        tokio::runtime::Builder::new_current_thread()
+            .enable_all()
+            .build()
+            .unwrap()
+            .block_on(prepare_chat_completions(
+                client,
+                &ReqwestClient::new(),
+                data,
+            ))
+    }
+
+    #[test]
+    fn wire_api_deserializes_on_openai_compatible_config() {
+        let config: OpenAICompatibleConfig = serde_yaml::from_str("wire_api: responses").unwrap();
+        assert_eq!(config.wire_api, Some(WireApi::Responses));
+
+        let config: OpenAICompatibleConfig = serde_yaml::from_str("wire_api: chat").unwrap();
+        assert_eq!(config.wire_api, Some(WireApi::Chat));
+    }
+
+    #[test]
+    fn bogus_wire_api_is_a_config_error() {
+        let err = serde_yaml::from_str::<OpenAICompatibleConfig>("wire_api: bogus")
+            .unwrap_err()
+            .to_string();
+
+        assert!(
+            err.contains("responses") && err.contains("chat"),
+            "unexpected error: {err}"
+        );
+    }
+
+    #[test]
+    fn default_wire_is_chat() {
+        let client = make_client(compat_config(None));
+
+        let (request_data, wire) = prepare(&client, false).unwrap();
+
+        assert_eq!(wire, WireApi::Chat);
+        assert_eq!(
+            request_data.url,
+            "https://compat.example/v1/chat/completions"
+        );
+        assert!(
+            request_data.body.get("messages").is_some(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn explicit_responses_wire_posts_a_responses_body_to_the_responses_endpoint() {
+        let client = make_client(compat_config(Some(WireApi::Responses)));
+
+        let (request_data, wire) = prepare(&client, false).unwrap();
+
+        assert_eq!(wire, WireApi::Responses);
+        assert_eq!(request_data.url, "https://compat.example/v1/responses");
+        assert_eq!(request_data.body["store"], json!(false));
+        assert!(
+            request_data.body.get("input").is_some() && request_data.body.get("messages").is_none(),
+            "body: {}",
+            request_data.body
+        );
+    }
+
+    #[test]
+    fn explicit_responses_wire_forks_the_streaming_path_too() {
+        let client = make_client(compat_config(Some(WireApi::Responses)));
+
+        let (request_data, wire) = prepare(&client, true).unwrap();
+
+        assert_eq!(wire, WireApi::Responses);
+        assert_eq!(request_data.url, "https://compat.example/v1/responses");
+        assert_eq!(request_data.body["stream"], json!(true));
+    }
+
+    #[test]
+    fn explicit_chat_wire_keeps_the_chat_endpoint() {
+        let client = make_client(compat_config(Some(WireApi::Chat)));
+
+        let (request_data, wire) = prepare(&client, false).unwrap();
+
+        assert_eq!(wire, WireApi::Chat);
+        assert_eq!(
+            request_data.url,
+            "https://compat.example/v1/chat/completions"
+        );
+    }
+}

src/client/openai_compatible_oauth.rs

@@ -5,6 +5,7 @@ use super::oauth::{OAuthConfig, OAuthFlow, OAuthProvider, TokenRequestFormat};
 pub struct OpenAICompatibleOAuthProvider {
     pub config: OAuthConfig,
     pub client_name: String,
+    pub requires_issuer_stamp: bool,
 }
 
 fn is_loopback_uri(uri: &str) -> bool {
@@ -122,4 +123,8 @@ impl OAuthProvider for OpenAICompatibleOAuthProvider {
     fn use_pkce_in_device_flow(&self) -> bool {
         self.config.use_pkce_in_device_flow
     }
+
+    fn requires_issuer_stamp(&self) -> bool {
+        self.requires_issuer_stamp
+    }
 }

src/client/stream.rs

@@ -215,6 +215,14 @@ impl SseHandler {
         !self.buffer.is_empty() || !self.tool_calls.is_empty() || !self.thinking.is_empty()
     }
 
+    /// Whether visible output (text or tool calls) has been accumulated.
+    /// Unlike [`Self::has_received_content`], thinking blocks do not count:
+    /// a stream truncated before any visible output is still an empty
+    /// response to the caller.
+    pub fn has_received_visible_output(&self) -> bool {
+        !self.buffer.is_empty() || !self.tool_calls.is_empty()
+    }
+
     pub fn abort(&self) -> AbortSignal {
         self.abort_signal.clone()
     }
@@ -544,6 +552,23 @@ mod tests {
         assert!(handler.has_received_content());
     }
 
+    /// Pins the deliberate exclusion: thinking blocks count as received
+    /// content but not as visible output, so a thinking-only stream is
+    /// still an empty response to the caller.
+    #[test]
+    fn thinking_blocks_do_not_count_as_visible_output() {
+        let (mut handler, _rx) = new_handler();
+        handler.thinking_block(ThinkingBlock::Thinking {
+            thinking: "hmm".to_string(),
+            signature: "sig".to_string(),
+        });
+        assert!(handler.has_received_content());
+        assert!(!handler.has_received_visible_output());
+
+        handler.text("hello").unwrap();
+        assert!(handler.has_received_visible_output());
+    }
+
     /// Claude splits usage across events: `message_start` carries the input
     /// and cache counts with a provisional output count, `message_delta`
     /// carries only the final output count. Later non-None fields must win.

src/config/agent.rs

@@ -1,5 +1,6 @@
 use super::*;
 
+use crate::hooks::HooksMap;
 use crate::{
     client::Model,
     config::memory,
@@ -12,6 +13,7 @@ use crate::{
 };
 
 use super::rag_cache::RagKey;
+use crate::config::builtin_manifest;
 use crate::config::paths;
 use crate::config::prompts::{
     DEFAULT_JOB_INSTRUCTIONS, DEFAULT_SPAWN_INSTRUCTIONS, DEFAULT_TEAMMATE_INSTRUCTIONS,
@@ -27,6 +29,7 @@ use fancy_regex::Captures;
 use inquire::{Text, validator::Validation};
 use rust_embed::Embed;
 use serde::{Deserialize, Serialize};
+use std::collections::BTreeSet;
 use std::{env, ffi::OsStr, path::Path};
 
 const DEFAULT_AGENT_NAME: &str = "rag";
@@ -46,6 +49,20 @@ pub type AgentVariables = IndexMap<String, String>;
 #[folder = "assets/agents/"]
 struct AgentAssets;
 
+/// Splits an embedded asset path of the form `<agent>/hooks/<file>` into
+/// its agent and hook-file names. Only direct children of `hooks/` count:
+/// they are the only shape the builtin manifest tracks.
+fn parse_direct_hook_path(path: &str) -> Option<(&str, &str)> {
+    let (agent, rest) = path.split_once('/')?;
+    let hook = direct_hook_name(rest)?;
+    Some((agent, hook))
+}
+
+fn direct_hook_name(rest: &str) -> Option<&str> {
+    let name = rest.strip_prefix("hooks/")?;
+    (!name.is_empty() && !name.contains('/')).then_some(name)
+}
+
 #[derive(Debug, Clone)]
 pub struct Agent {
     name: String,
@@ -70,6 +87,7 @@ impl Agent {
             paths::agents_data_dir().display()
         );
 
+        let mut written_hooks: HashMap<String, BTreeSet<String>> = HashMap::new();
         for file in AgentAssets::iter() {
             debug!("Processing agent file: {}", file.as_ref());
 
@@ -96,6 +114,12 @@ impl Agent {
             info!("Creating agent file: {}", file_path.display());
             let mut agent_file = File::create(&file_path)?;
             agent_file.write_all(content.as_bytes())?;
+            if let Some((agent, hook)) = parse_direct_hook_path(file.as_ref()) {
+                written_hooks
+                    .entry(agent.to_string())
+                    .or_default()
+                    .insert(hook.to_string());
+            }
 
             #[cfg(unix)]
             if is_script {
@@ -134,6 +158,27 @@ impl Agent {
             }
         }
 
+        // Hook filenames are open-ended (unlike AGENT_DEFINITION_FILES), so
+        // each bundled agent's hooks/ directory reconciles through its
+        // builtin manifest: only files the installer previously shipped are
+        // removal candidates, and user-created files in the same directory
+        // are never touched. Only direct children of hooks/ are tracked;
+        // nested shipped files install but are not reconciled.
+        for (agent, files) in &bundled_files {
+            let shipped: BTreeSet<String> = files
+                .iter()
+                .filter_map(|rest| direct_hook_name(rest))
+                .map(str::to_string)
+                .collect();
+            let written = written_hooks.remove(agent.as_str()).unwrap_or_default();
+            let hooks_dir = paths::agents_data_dir().join(agent).join("hooks");
+            if let Err(err) =
+                builtin_manifest::reconcile_builtin_dir(&hooks_dir, &shipped, &written)
+            {
+                warn!("Failed to reconcile builtin hooks for agent '{agent}': {err}");
+            }
+        }
+
         Ok(())
     }
 
@@ -639,6 +684,14 @@ impl Agent {
         self.config.compression_model.as_deref()
     }
 
+    pub fn hooks(&self) -> &HooksMap {
+        &self.config.hooks
+    }
+
+    pub fn global_hooks(&self) -> &[String] {
+        &self.config.global_hooks
+    }
+
     pub fn is_dynamic_instructions(&self) -> bool {
         self.config.dynamic_instructions
     }
@@ -848,6 +901,10 @@ pub struct AgentConfig {
     pub mcp_tools: Option<IndexMap<String, Vec<String>>>,
     #[serde(default)]
     pub global_tools: Vec<String>,
+    #[serde(default)]
+    pub hooks: HooksMap,
+    #[serde(default)]
+    pub global_hooks: Vec<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub skills_enabled: Option<bool>,
     #[serde(skip_serializing_if = "Option::is_none")]
@@ -917,6 +974,8 @@ impl AgentConfig {
             reasoning_effort: graph.reasoning_effort.clone(),
             description: graph.description.clone(),
             global_tools: graph.global_tools.clone(),
+            hooks: graph.hooks.clone(),
+            global_hooks: graph.global_hooks.clone(),
             mcp_servers: graph.mcp_servers.clone(),
             mcp_tools: graph.mcp_tools.clone(),
             skills_enabled: graph.skills_enabled,
@@ -965,6 +1024,14 @@ impl AgentConfig {
         {
             self.global_tools = v;
         }
+        if let Ok(v) = env::var(with_prefix("global_hooks")) {
+            match serde_json::from_str(&v) {
+                Ok(v) => self.global_hooks = v,
+                Err(err) => {
+                    debug!("Ignoring malformed global_hooks env override for agent '{name}': {err}")
+                }
+            }
+        }
         if let Ok(v) = env::var(with_prefix("mcp_servers"))
             && let Ok(v) = serde_json::from_str(&v)
         {
@@ -1295,6 +1362,16 @@ pub fn complete_agent_variables(agent_name: &str) -> Vec<(String, Option<String>
 mod tests {
     use super::*;
 
+    #[test]
+    fn parse_direct_hook_path_accepts_only_direct_hook_children() {
+        assert_eq!(parse_direct_hook_path("x/hooks/a.sh"), Some(("x", "a.sh")));
+        assert_eq!(parse_direct_hook_path("x/hooks/nested/a.sh"), None);
+        assert_eq!(parse_direct_hook_path("hooks/a.sh"), None);
+        assert_eq!(parse_direct_hook_path("x/hooks/"), None);
+        assert_eq!(parse_direct_hook_path("x/config.yaml"), None);
+        assert_eq!(parse_direct_hook_path("config.yaml"), None);
+    }
+
     #[test]
     fn agent_config_parses_from_yaml() {
         let yaml = r#"
@@ -1336,6 +1413,92 @@ variables:
         assert_eq!(config.variables[0].name, "username");
     }
 
+    #[test]
+    fn agent_config_hooks_and_global_hooks_round_trip() {
+        let yaml = "\
+name: hooked
+instructions: hi
+hooks:
+  tool.started:
+    - name: notify
+      command: ./hooks/notify.sh
+global_hooks:
+  - tool.started.notify
+";
+        let config: AgentConfig = serde_yaml::from_str(yaml).unwrap();
+
+        assert_eq!(config.hooks["tool.started"][0].name, "notify");
+        assert_eq!(config.hooks["tool.started"][0].command, "./hooks/notify.sh");
+        assert_eq!(config.global_hooks, vec!["tool.started.notify"]);
+
+        let serialized = serde_yaml::to_string(&config).unwrap();
+        let reparsed: AgentConfig = serde_yaml::from_str(&serialized).unwrap();
+
+        assert_eq!(reparsed.hooks, config.hooks);
+        assert_eq!(reparsed.global_hooks, config.global_hooks);
+    }
+
+    #[test]
+    fn load_envs_overrides_global_hooks() {
+        let yaml = "name: hooks-env-probe\ninstructions: hi\nglobal_hooks:\n  - initial.hook\n";
+        let mut config: AgentConfig = serde_yaml::from_str(yaml).unwrap();
+        let env_name = normalize_env_name("hooks-env-probe_global_hooks");
+        let prev = env::var_os(&env_name);
+
+        unsafe {
+            env::set_var(
+                &env_name,
+                r#"["tool.started.notify","turn.completed.webhook"]"#,
+            )
+        };
+        config.load_envs(&AppConfig::default());
+        assert_eq!(
+            config.global_hooks,
+            vec!["tool.started.notify", "turn.completed.webhook"]
+        );
+
+        unsafe { env::set_var(&env_name, "not json") };
+        config.load_envs(&AppConfig::default());
+        assert_eq!(
+            config.global_hooks,
+            vec!["tool.started.notify", "turn.completed.webhook"]
+        );
+
+        unsafe {
+            match prev {
+                Some(v) => env::set_var(&env_name, v),
+                None => env::remove_var(&env_name),
+            }
+        }
+    }
+
+    #[test]
+    fn from_graph_carries_hooks_and_global_hooks() {
+        let yaml = "\
+name: g
+start: e
+hooks:
+  turn.completed:
+    - name: webhook
+      command: curl -s https://example.com/hook
+global_hooks:
+  - turn.completed.webhook
+nodes:
+  e:
+    id: e
+    type: end
+    output: done
+";
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+
+        let config = AgentConfig::from_graph("g", &graph);
+
+        assert_eq!(config.hooks, graph.hooks);
+        assert_eq!(config.global_hooks, graph.global_hooks);
+        assert_eq!(config.hooks["turn.completed"][0].name, "webhook");
+        assert_eq!(config.global_hooks, vec!["turn.completed.webhook"]);
+    }
+
     #[test]
     fn agent_config_defaults() {
         let yaml = "name: minimal\ninstructions: hi\n";
@@ -1350,6 +1513,8 @@ variables:
         assert_eq!(config.escalation_timeout, 0);
         assert!(config.mcp_servers.is_empty());
         assert!(config.global_tools.is_empty());
+        assert!(config.hooks.is_empty());
+        assert!(config.global_hooks.is_empty());
         assert!(config.conversation_starters.is_empty());
         assert!(config.variables.is_empty());
         assert!(config.model_id.is_none());

src/config/app_config.rs

@@ -1,4 +1,5 @@
 use crate::client::{ClientConfig, Model, ModelType, list_models};
+use crate::hooks::HooksMap;
 use crate::render::{MarkdownRender, RenderOptions};
 use crate::utils::{IS_STDOUT_TERMINAL, NO_COLOR, decode_bin, drain_stale_tty_input, get_env_name};
 
@@ -52,6 +53,9 @@ pub struct AppConfig {
     pub enabled_mcp_servers: Option<Vec<String>>,
     pub mcp_tools: Option<IndexMap<String, Vec<String>>>,
 
+    #[serde(default)]
+    pub hooks: HooksMap,
+
     pub auto_continue: bool,
     pub max_auto_continues: usize,
     pub inject_todo_instructions: bool,
@@ -143,6 +147,8 @@ impl Default for AppConfig {
             enabled_mcp_servers: None,
             mcp_tools: None,
 
+            hooks: Default::default(),
+
             auto_continue: false,
             max_auto_continues: 10,
             inject_todo_instructions: true,
@@ -235,6 +241,8 @@ impl AppConfig {
             enabled_mcp_servers: config.enabled_mcp_servers,
             mcp_tools: config.mcp_tools,
 
+            hooks: config.hooks,
+
             auto_continue: config.auto_continue,
             max_auto_continues: config.max_auto_continues,
             inject_todo_instructions: config.inject_todo_instructions,
@@ -572,6 +580,15 @@ impl AppConfig {
             self.enabled_mcp_servers = v.map(|raw| super::csv_to_vec(&raw));
         }
 
+        if let Ok(v) = env::var(get_env_name("hooks")) {
+            match serde_json::from_str(&v) {
+                Ok(v) => self.hooks = v,
+                Err(err) => {
+                    debug!("Ignoring malformed hooks env override: {err}")
+                }
+            }
+        }
+
         if let Some(v) = super::read_env_value::<String>(&get_env_name("repl_prelude")) {
             self.repl_prelude = v;
         }
@@ -788,6 +805,77 @@ mod tests {
         assert_eq!(app.clients.len(), 1);
     }
 
+    #[test]
+    fn from_config_copies_hooks() {
+        let mut hooks = HooksMap::new();
+        hooks.insert(
+            "turn.completed".to_string(),
+            vec![crate::hooks::HookDef {
+                name: "notify".to_string(),
+                command: "./hooks/notify.sh".to_string(),
+            }],
+        );
+        let cfg = Config {
+            model_id: "test-model".to_string(),
+            clients: vec![ClientConfig::default()],
+            hooks: hooks.clone(),
+            ..Config::default()
+        };
+
+        let app = AppConfig::from_config(cfg).unwrap();
+
+        assert_eq!(app.hooks, hooks);
+    }
+
+    #[test]
+    fn from_config_defaults_hooks_to_empty() {
+        let cfg = Config {
+            model_id: "test-model".to_string(),
+            clients: vec![ClientConfig::default()],
+            ..Config::default()
+        };
+        let app = AppConfig::from_config(cfg).unwrap();
+
+        assert!(app.hooks.is_empty());
+    }
+
+    #[test]
+    #[serial_test::serial]
+    fn load_envs_overrides_hooks() {
+        let env_name = get_env_name("hooks");
+        let prev = env::var_os(&env_name);
+
+        let mut hooks = HooksMap::new();
+        hooks.insert(
+            "turn.completed".to_string(),
+            vec![crate::hooks::HookDef {
+                name: "notify".to_string(),
+                command: "./hooks/notify.sh".to_string(),
+            }],
+        );
+
+        let mut app = AppConfig::default();
+
+        unsafe { env::set_var(&env_name, serde_json::to_string(&hooks).unwrap()) };
+        app.load_envs();
+        assert_eq!(app.hooks, hooks);
+
+        unsafe { env::set_var(&env_name, "[not json") };
+        app.load_envs();
+        assert_eq!(app.hooks, hooks);
+
+        unsafe { env::remove_var(&env_name) };
+        app.load_envs();
+        assert_eq!(app.hooks, hooks);
+
+        unsafe {
+            match prev {
+                Some(v) => env::set_var(&env_name, v),
+                None => env::remove_var(&env_name),
+            }
+        }
+    }
+
     #[test]
     fn from_config_copies_mapping_fields() {
         let mut cfg = Config {

src/config/builtin_manifest.rs

@@ -0,0 +1,293 @@
+//! Per-directory tracking of files the builtin installer shipped, so a later
+//! release that stops shipping an asset can remove the stale copy without
+//! ever touching user-created files that live in the same directory.
+//!
+//! Unlike agent definition files, hook filenames are open-ended: no closed
+//! candidate list can distinguish "previously bundled" from "user-authored".
+//! The manifest records exactly what the installer shipped; anything absent
+//! from it is user-owned and untouchable.
+
+use crate::config::ensure_parent_exists;
+use crate::function::write_file_atomic;
+
+use anyhow::{Context, Result};
+use std::collections::BTreeSet;
+use std::fs;
+use std::path::Path;
+
+pub(crate) const BUILTIN_MANIFEST_FILE: &str = ".builtin-manifest";
+
+pub(crate) fn is_builtin_manifest_name(name: &str) -> bool {
+    name.trim_end_matches(['.', ' '])
+        .to_uppercase()
+        .eq_ignore_ascii_case(BUILTIN_MANIFEST_FILE)
+}
+
+/// Reconciles `dir` against the currently shipped set of builtin filenames:
+/// a file is removed ONLY if it appears in the previous manifest AND is
+/// absent from `shipped`. The manifest is then rewritten to the names this
+/// installer actually owns: files written this run (`written`), plus shipped
+/// names it already owned, plus stale files whose removal failed (kept so a
+/// later run retries). A shipped name the installer declined to write (e.g., a
+/// pre-existing user file with a colliding name) is never claimed.
+///
+/// Failure modes degrade toward keeping files: a missing or unreadable
+/// manifest yields no deletions, and entries that are not plain filenames
+/// are ignored.
+pub(crate) fn reconcile_builtin_dir(
+    dir: &Path,
+    shipped: &BTreeSet<String>,
+    written: &BTreeSet<String>,
+) -> Result<()> {
+    let previous = read_manifest(dir);
+    let mut retained: BTreeSet<String> = written.clone();
+    retained.extend(shipped.intersection(&previous).cloned());
+    for name in previous.difference(shipped) {
+        let path = dir.join(name);
+        if !path.is_file() {
+            continue;
+        }
+        info!(
+            "Removing stale builtin file no longer shipped: {}",
+            path.display()
+        );
+        if let Err(err) = fs::remove_file(&path) {
+            warn!(
+                "Failed to remove stale builtin file {}: {err}",
+                path.display()
+            );
+            retained.insert(name.clone());
+        }
+    }
+
+    write_manifest(dir, &retained)
+}
+
+fn read_manifest(dir: &Path) -> BTreeSet<String> {
+    let path = dir.join(BUILTIN_MANIFEST_FILE);
+    let content = match fs::read_to_string(&path) {
+        Ok(content) => content,
+        Err(err) => {
+            debug!(
+                "No readable builtin manifest at {} ({err}); skipping stale-file removal",
+                path.display()
+            );
+            return BTreeSet::new();
+        }
+    };
+
+    content
+        .lines()
+        .map(str::trim)
+        .filter(|line| {
+            if line.is_empty() || is_builtin_manifest_name(line) {
+                return false;
+            }
+            if !is_plain_file_name(line) {
+                debug!(
+                    "Ignoring suspicious builtin manifest entry in {}: {line:?}",
+                    path.display()
+                );
+                return false;
+            }
+            true
+        })
+        .map(str::to_string)
+        .collect()
+}
+
+/// Manifest entries name direct children of the manifest's directory and
+/// nothing else; anything path-like is rejected so a corrupted or crafted
+/// manifest can never direct a deletion outside that directory. The same
+/// component rules the bundle store applies to recorded paths are reused so
+/// Windows drive prefixes (`C:x`), ADS colons, trailing dots/spaces, and
+/// reserved device names are rejected too.
+fn is_plain_file_name(name: &str) -> bool {
+    !name.contains(['/', '\\'])
+        && name != "."
+        && name != ".."
+        && super::install_remote::is_safe_component(name)
+}
+
+fn write_manifest(dir: &Path, names: &BTreeSet<String>) -> Result<()> {
+    let path = dir.join(BUILTIN_MANIFEST_FILE);
+    if names.is_empty() {
+        if path.is_file() {
+            fs::remove_file(&path)
+                .with_context(|| format!("failed to remove builtin manifest {}", path.display()))?;
+        }
+        return Ok(());
+    }
+
+    let mut content = names.iter().cloned().collect::<Vec<_>>().join("\n");
+    content.push('\n');
+    ensure_parent_exists(&path)?;
+    write_file_atomic(&path, &content, None)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::utils;
+    use std::path::PathBuf;
+
+    fn fresh_dir(label: &str) -> PathBuf {
+        let dir = utils::temp_file(label, "");
+        fs::create_dir_all(&dir).unwrap();
+        dir
+    }
+
+    fn shipped(names: &[&str]) -> BTreeSet<String> {
+        names.iter().map(|n| n.to_string()).collect()
+    }
+
+    #[test]
+    fn removes_only_manifest_listed_files_absent_from_shipped() {
+        let dir = fresh_dir("builtin-manifest-stale-");
+        fs::write(dir.join(BUILTIN_MANIFEST_FILE), "old.sh\nkept.sh\n").unwrap();
+        fs::write(dir.join("old.sh"), "stale").unwrap();
+        fs::write(dir.join("kept.sh"), "current").unwrap();
+        fs::write(dir.join("user.sh"), "user-owned").unwrap();
+
+        reconcile_builtin_dir(&dir, &shipped(&["kept.sh"]), &shipped(&[])).unwrap();
+
+        assert!(!dir.join("old.sh").exists(), "stale bundled file removed");
+        assert!(dir.join("kept.sh").exists(), "still-shipped file kept");
+        assert!(dir.join("user.sh").exists(), "unlisted user file untouched");
+        assert_eq!(
+            fs::read_to_string(dir.join(BUILTIN_MANIFEST_FILE)).unwrap(),
+            "kept.sh\n"
+        );
+        let _ = fs::remove_dir_all(&dir);
+    }
+
+    #[test]
+    fn missing_manifest_deletes_nothing_and_writes_shipped_set() {
+        let dir = fresh_dir("builtin-manifest-missing-");
+        fs::write(dir.join("user.sh"), "user-owned").unwrap();
+
+        reconcile_builtin_dir(&dir, &shipped(&["new.sh"]), &shipped(&["new.sh"])).unwrap();
+
+        assert!(dir.join("user.sh").exists());
+        assert_eq!(
+            fs::read_to_string(dir.join(BUILTIN_MANIFEST_FILE)).unwrap(),
+            "new.sh\n"
+        );
+        let _ = fs::remove_dir_all(&dir);
+    }
+
+    /// A shipped name the installer skipped (pre-existing user file with a
+    /// colliding name) is never claimed by the manifest, so a later release
+    /// dropping that hook can never delete the user's file.
+    #[test]
+    fn skipped_preexisting_user_file_is_never_claimed() {
+        let dir = fresh_dir("builtin-manifest-unclaimed-");
+        fs::write(dir.join("user.sh"), "user-owned").unwrap();
+
+        reconcile_builtin_dir(&dir, &shipped(&["user.sh"]), &shipped(&[])).unwrap();
+        assert!(
+            !dir.join(BUILTIN_MANIFEST_FILE).exists(),
+            "nothing was written this run and nothing was owned before"
+        );
+
+        reconcile_builtin_dir(&dir, &shipped(&[]), &shipped(&[])).unwrap();
+        assert!(
+            dir.join("user.sh").exists(),
+            "the unclaimed user file survives the hook being dropped"
+        );
+        let _ = fs::remove_dir_all(&dir);
+    }
+
+    #[test]
+    fn suspicious_manifest_entries_never_direct_deletions() {
+        let dir = fresh_dir("builtin-manifest-suspicious-");
+        let outside = fresh_dir("builtin-manifest-outside-");
+        let escape = format!(
+            "../{}/victim.sh",
+            outside.file_name().unwrap().to_string_lossy()
+        );
+        fs::write(
+            dir.join(BUILTIN_MANIFEST_FILE),
+            format!("{escape}\nsub/nested.sh\nC:victim.sh\ntrailing.\n..\n.\n\n"),
+        )
+        .unwrap();
+        fs::write(outside.join("victim.sh"), "keep").unwrap();
+        fs::create_dir_all(dir.join("sub")).unwrap();
+        fs::write(dir.join("sub/nested.sh"), "keep").unwrap();
+
+        reconcile_builtin_dir(&dir, &BTreeSet::new(), &BTreeSet::new()).unwrap();
+
+        assert!(outside.join("victim.sh").exists());
+        assert!(dir.join("sub/nested.sh").exists());
+        let _ = fs::remove_dir_all(&dir);
+        let _ = fs::remove_dir_all(&outside);
+    }
+
+    #[test]
+    fn unreadable_manifest_deletes_nothing() {
+        let dir = fresh_dir("builtin-manifest-unreadable-");
+        fs::write(dir.join(BUILTIN_MANIFEST_FILE), [0xff, 0xfe, 0x00]).unwrap();
+        fs::write(dir.join("old.sh"), "keep").unwrap();
+
+        reconcile_builtin_dir(&dir, &shipped(&["new.sh"]), &shipped(&["new.sh"])).unwrap();
+
+        assert!(
+            dir.join("old.sh").exists(),
+            "a bad manifest must fail safe toward keeping files"
+        );
+        assert_eq!(
+            fs::read_to_string(dir.join(BUILTIN_MANIFEST_FILE)).unwrap(),
+            "new.sh\n",
+            "manifest self-heals to the current shipped set"
+        );
+        let _ = fs::remove_dir_all(&dir);
+    }
+
+    #[test]
+    fn empty_shipped_set_removes_manifest_and_creates_nothing() {
+        let dir = fresh_dir("builtin-manifest-empty-");
+        fs::write(dir.join(BUILTIN_MANIFEST_FILE), "old.sh\n").unwrap();
+        fs::write(dir.join("old.sh"), "stale").unwrap();
+        fs::write(dir.join("user.sh"), "user-owned").unwrap();
+
+        reconcile_builtin_dir(&dir, &BTreeSet::new(), &BTreeSet::new()).unwrap();
+
+        assert!(!dir.join("old.sh").exists());
+        assert!(dir.join("user.sh").exists());
+        assert!(!dir.join(BUILTIN_MANIFEST_FILE).exists());
+
+        let absent = dir.join("never-created");
+        reconcile_builtin_dir(&absent, &BTreeSet::new(), &BTreeSet::new()).unwrap();
+        assert!(!absent.exists(), "no directory is created for an empty set");
+        let _ = fs::remove_dir_all(&dir);
+    }
+
+    #[test]
+    fn manifest_listing_itself_never_deletes_it() {
+        let dir = fresh_dir("builtin-manifest-self-");
+        fs::write(
+            dir.join(BUILTIN_MANIFEST_FILE),
+            format!("{BUILTIN_MANIFEST_FILE}\n.BUILTIN-MANIFEST\nkept.sh\n"),
+        )
+        .unwrap();
+        fs::write(dir.join("kept.sh"), "current").unwrap();
+
+        reconcile_builtin_dir(&dir, &shipped(&["kept.sh"]), &shipped(&[])).unwrap();
+
+        assert!(dir.join(BUILTIN_MANIFEST_FILE).exists());
+        assert!(dir.join("kept.sh").exists());
+        let _ = fs::remove_dir_all(&dir);
+    }
+
+    #[test]
+    fn manifest_name_matcher_covers_filesystem_aliases() {
+        assert!(is_builtin_manifest_name(".builtin-manifest"));
+        assert!(is_builtin_manifest_name(".BUILTIN-MANIFEST"));
+        assert!(is_builtin_manifest_name(".Builtin-Manifest."));
+        assert!(is_builtin_manifest_name(".builtin-manifest  "));
+        assert!(is_builtin_manifest_name(".builtin-manifeſt"));
+        assert!(!is_builtin_manifest_name("builtin-manifest"));
+        assert!(!is_builtin_manifest_name(".builtin-manifesto"));
+        assert!(!is_builtin_manifest_name("notify.sh"));
+    }
+}

src/config/bundles.rs

@@ -1183,6 +1183,13 @@ mod tests {
 
         assert_eq!(resolved.name, "y/mcp_config");
         assert_eq!(resolved.qualified_from.as_deref(), Some("mcp_config"));
+
+        let resolved = store
+            .resolve_bundle_name("https://github.com/z/hooks", None)
+            .unwrap();
+
+        assert_eq!(resolved.name, "z/hooks");
+        assert_eq!(resolved.qualified_from.as_deref(), Some("hooks"));
     }
 
     #[test]

src/config/install_remote.rs

@@ -2,6 +2,7 @@ use super::bundles::{
     BundleStore, FileAction, FileRecord, InstallMetadata, McpAction, McpServerRecord, hash_bytes,
     hash_file,
 };
+use crate::config::builtin_manifest::is_builtin_manifest_name;
 use crate::config::{AssetCategory, BUNDLE_MANIFEST_FILE, InstallFilter, paths};
 #[cfg(not(windows))]
 use crate::function::Language;
@@ -32,7 +33,7 @@ pub fn install_remote(git_url: &str, filter: Option<InstallFilter>, force: bool)
     if layout.is_empty() {
         println!(
             "No recognized assets found in {git_url}. Expected one or more of: \
-             agents/, roles/, skills/, macros/, functions/tools/, mcp.json"
+             agents/, roles/, skills/, macros/, functions/tools/, hooks/, mcp.json"
         );
         return Ok(());
     }
@@ -805,7 +806,7 @@ fn is_safe_relative_path(path: &str) -> bool {
 /// Rejects names Windows refuses or silently rewrites (alternate data stream
 /// colons, reserved device names, trailing dots or spaces) so a recorded path
 /// denotes the same regular file on every platform.
-fn is_safe_component(name: &str) -> bool {
+pub(crate) fn is_safe_component(name: &str) -> bool {
     !name.contains(':')
         && !name.ends_with('.')
         && !name.ends_with(' ')
@@ -1270,6 +1271,7 @@ struct RemoteLayout {
     roles: Option<PathBuf>,
     skills: Option<PathBuf>,
     macros: Option<PathBuf>,
+    hooks: Option<PathBuf>,
     functions_tools: Option<PathBuf>,
     mcp_json: Option<PathBuf>,
     manifest: Option<BundleManifest>,
@@ -1282,6 +1284,7 @@ impl RemoteLayout {
             && self.roles.is_none()
             && self.skills.is_none()
             && self.macros.is_none()
+            && self.hooks.is_none()
             && self.functions_tools.is_none()
             && self.mcp_json.is_none()
     }
@@ -1313,6 +1316,11 @@ fn scan_remote_layout(root: &Path) -> Result<RemoteLayout> {
         layout.macros = Some(macros);
     }
 
+    let hooks = root.join("hooks");
+    if hooks.is_dir() {
+        layout.hooks = Some(hooks);
+    }
+
     let root_mcp = root.join("mcp.json");
     if root_mcp.is_file() {
         layout.mcp_json = Some(root_mcp);
@@ -1540,6 +1548,10 @@ fn apply_filter(mut layout: RemoteLayout, filter: Option<InstallFilter>) -> Remo
             functions_tools: layout.functions_tools.take(),
             ..base
         },
+        InstallFilter::Hooks => RemoteLayout {
+            hooks: layout.hooks.take(),
+            ..base
+        },
         InstallFilter::McpConfig => RemoteLayout {
             mcp_json: layout.mcp_json.take(),
             ..base
@@ -1591,6 +1603,7 @@ enum TopCategory {
     Roles,
     Skills,
     Macros,
+    Hooks,
     FunctionsTools,
 }
 
@@ -1601,6 +1614,7 @@ impl TopCategory {
             TopCategory::Roles => "roles",
             TopCategory::Skills => "skills",
             TopCategory::Macros => "macros",
+            TopCategory::Hooks => "hooks",
             TopCategory::FunctionsTools => "functions/tools",
         }
     }
@@ -1619,6 +1633,8 @@ enum PlannedKind {
 struct PlannedFile {
     src: PathBuf,
     dst: PathBuf,
+    /// Path relative to the category's source directory in the bundle.
+    rel: PathBuf,
     kind: PlannedKind,
     top_category: TopCategory,
 }
@@ -1660,6 +1676,9 @@ fn plan_changes(layout: &RemoteLayout) -> Result<InstallPlan> {
             &mut files,
         )?;
     }
+    if let Some(src_dir) = &layout.hooks {
+        plan_dir_into(src_dir, &paths::hooks_dir(), TopCategory::Hooks, &mut files)?;
+    }
     if let Some(src_dir) = &layout.functions_tools {
         plan_dir_into(
             src_dir,
@@ -1686,7 +1705,28 @@ fn plan_dir_into(
     for src in walk_files(src_dir)? {
         let rel = src
             .strip_prefix(src_dir)
-            .expect("walk_files only returns paths under src_dir");
+            .expect("walk_files only returns paths under src_dir")
+            .to_path_buf();
+
+        // The builtin installer's per-directory manifests drive stale-file
+        // deletion; letting a bundle install one would hand it control over
+        // which local files the next builtin reconcile removes. Every path
+        // component is checked (a bundle-shipped DIRECTORY of that name would
+        // permanently occupy the manifest path and disable reconciliation),
+        // under the filesystem-alias-aware match of is_builtin_manifest_name.
+        let is_builtin_manifest = rel.components().any(|c| match c.as_os_str().to_str() {
+            Some(name) => is_builtin_manifest_name(name),
+            // A non-UTF-8 name can never equal the ASCII manifest constant.
+            None => false,
+        });
+        if is_builtin_manifest {
+            log::warn!(
+                "Ignoring bundle file {} ({}): the name is reserved for the builtin installer",
+                rel.display(),
+                category.label()
+            );
+            continue;
+        }
 
         if category == TopCategory::Skills {
             let skill_name = rel
@@ -1707,11 +1747,12 @@ fn plan_dir_into(
             })?;
         }
 
-        let dst = dst_dir.join(rel);
+        let dst = dst_dir.join(&rel);
         let kind = classify_file(&src, &dst)?;
         out.push(PlannedFile {
             src,
             dst,
+            rel,
             kind,
             top_category: category,
         });
@@ -1790,6 +1831,7 @@ fn print_plan_summary(plan: &InstallPlan) {
         TopCategory::Roles,
         TopCategory::Skills,
         TopCategory::Macros,
+        TopCategory::Hooks,
         TopCategory::FunctionsTools,
     ] {
         let new_ = count_kind(plan, cat, PlannedKind::New);
@@ -1808,6 +1850,33 @@ fn print_plan_summary(plan: &InstallPlan) {
             println!("{line}");
         }
     }
+
+    for line in hook_script_lines(plan) {
+        println!("{line}");
+    }
+}
+
+/// Bundle-shipped hook scripts execute on the user's machine once wired into
+/// config, so every planned file landing under a hooks/ directory is called
+/// out individually. Visibility only: installing them needs no extra approval.
+fn hook_script_lines(plan: &InstallPlan) -> Vec<String> {
+    plan.files
+        .iter()
+        .filter(|planned| {
+            planned.top_category == TopCategory::Hooks
+                || planned
+                    .rel
+                    .parent()
+                    .is_some_and(|parent| parent.components().any(|c| c.as_os_str() == "hooks"))
+        })
+        .map(|planned| {
+            let rel = planned.rel.to_string_lossy().replace('\\', "/");
+            format!(
+                "bundle defines hook script: {}/{rel}",
+                planned.top_category.label()
+            )
+        })
+        .collect()
 }
 
 fn count_kind(plan: &InstallPlan, cat: TopCategory, kind: PlannedKind) -> usize {
@@ -2349,6 +2418,8 @@ fn print_secret_summary(added: &[String], deferred: &[String]) {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::config;
+    use crate::config::builtin_manifest::BUILTIN_MANIFEST_FILE;
     use crate::sandbox::SANDBOX_ENV_FLAG;
     use crate::utils::get_env_name;
     use serial_test::serial;
@@ -2551,6 +2622,7 @@ mod tests {
             roles: Some(PathBuf::from("r")),
             skills: Some(PathBuf::from("s")),
             macros: Some(PathBuf::from("m")),
+            hooks: Some(PathBuf::from("h")),
             functions_tools: Some(PathBuf::from("f")),
             mcp_json: Some(PathBuf::from("j")),
             ..RemoteLayout::default()
@@ -2560,6 +2632,7 @@ mod tests {
 
         assert!(out.agents.is_some() && out.roles.is_some() && out.skills.is_some());
         assert!(out.macros.is_some() && out.functions_tools.is_some() && out.mcp_json.is_some());
+        assert!(out.hooks.is_some());
     }
 
     #[test]
@@ -2638,6 +2711,37 @@ mod tests {
         assert!(out.functions_tools.is_none() && out.mcp_json.is_none());
     }
 
+    #[test]
+    fn apply_filter_hooks_keeps_only_hooks() {
+        let l = RemoteLayout {
+            agents: Some(PathBuf::from("a")),
+            roles: Some(PathBuf::from("r")),
+            skills: Some(PathBuf::from("s")),
+            macros: Some(PathBuf::from("m")),
+            hooks: Some(PathBuf::from("h")),
+            functions_tools: Some(PathBuf::from("f")),
+            mcp_json: Some(PathBuf::from("j")),
+            ..RemoteLayout::default()
+        };
+
+        let out = apply_filter(l, Some(InstallFilter::Hooks));
+
+        assert_eq!(out.hooks, Some(PathBuf::from("h")));
+        assert!(!out.is_empty());
+        assert!(out.agents.is_none() && out.roles.is_none() && out.skills.is_none());
+        assert!(out.macros.is_none() && out.functions_tools.is_none() && out.mcp_json.is_none());
+    }
+
+    #[test]
+    fn remote_layout_with_only_hooks_is_not_empty() {
+        let l = RemoteLayout {
+            hooks: Some(PathBuf::from("h")),
+            ..RemoteLayout::default()
+        };
+
+        assert!(!l.is_empty());
+    }
+
     #[test]
     fn walk_files_skips_dot_git_and_collects_regular_files() {
         let root = fresh_temp_dir("walk-test-");
@@ -2684,6 +2788,7 @@ mod tests {
         fs::create_dir_all(root.join("roles")).unwrap();
         fs::create_dir_all(root.join("skills")).unwrap();
         fs::create_dir_all(root.join("macros")).unwrap();
+        fs::create_dir_all(root.join("hooks")).unwrap();
         fs::create_dir_all(root.join("functions/tools")).unwrap();
         touch(&root.join("functions/mcp.json"));
         touch(&root.join("README.md"));
@@ -2693,11 +2798,29 @@ mod tests {
         assert!(layout.roles.is_some());
         assert!(layout.skills.is_some());
         assert!(layout.macros.is_some());
+        assert!(layout.hooks.is_some());
         assert!(layout.functions_tools.is_some());
         assert!(layout.mcp_json.is_some());
         let _ = fs::remove_dir_all(&root);
     }
 
+    #[test]
+    fn scan_remote_layout_finds_hooks_only() {
+        let root = fresh_temp_dir("scan-hooks-only-");
+        fs::create_dir_all(root.join("hooks")).unwrap();
+        touch(&root.join("hooks/notify.sh"));
+
+        let layout = scan_remote_layout(&root).unwrap();
+
+        assert_eq!(layout.hooks, Some(root.join("hooks")));
+        assert!(layout.agents.is_none());
+        assert!(layout.roles.is_none());
+        assert!(layout.macros.is_none());
+        assert!(layout.functions_tools.is_none());
+        assert!(layout.mcp_json.is_none());
+        let _ = fs::remove_dir_all(&root);
+    }
+
     #[test]
     fn scan_remote_layout_finds_root_mcp_json() {
         let root = fresh_temp_dir("scan-root-mcp-test-");
@@ -2752,6 +2875,71 @@ mod tests {
         let _ = fs::remove_dir_all(&root);
     }
 
+    #[test]
+    fn plan_dir_into_skips_bundle_shipped_builtin_manifests() {
+        let root = fresh_temp_dir("plan-manifest-skip-");
+        let src_dir = root.join("hooks");
+        touch(&src_dir.join("notify.sh"));
+        touch(&src_dir.join(BUILTIN_MANIFEST_FILE));
+        touch(&src_dir.join(format!("sub/{BUILTIN_MANIFEST_FILE}")));
+        // Case and trailing-dot variants alias the real manifest path on
+        // case-insensitive filesystems; they live in separate subdirs so this
+        // fixture also builds on such filesystems without name collisions.
+        touch(&src_dir.join("sub2/.BUILTIN-MANIFEST"));
+        touch(&src_dir.join("sub3/.Builtin-Manifest."));
+        // A DIRECTORY of the manifest name would occupy the manifest path and
+        // disable reconciliation; a Unicode case-fold alias (U+017F ſ → s)
+        // aliases it on case-insensitive APFS/NTFS volumes.
+        touch(&src_dir.join("sub4/.builtin-manifest/payload.sh"));
+        touch(&src_dir.join("sub5/.builtin-manifeſt"));
+        let dst_dir = root.join("dst");
+
+        let mut files = Vec::new();
+        plan_dir_into(&src_dir, &dst_dir, TopCategory::Hooks, &mut files).unwrap();
+
+        let rels: Vec<&Path> = files.iter().map(|p| p.rel.as_path()).collect();
+        assert_eq!(
+            rels,
+            vec![Path::new("notify.sh")],
+            "a bundle must never install a builtin manifest: it would hand the \
+             bundle control over builtin stale-file deletion"
+        );
+        let _ = fs::remove_dir_all(&root);
+    }
+
+    #[test]
+    fn hook_script_lines_cover_every_hooks_dir_and_nothing_else() {
+        let file = |rel: &str, cat: TopCategory| PlannedFile {
+            src: PathBuf::from("src").join(rel),
+            dst: PathBuf::from("dst").join(rel),
+            rel: PathBuf::from(rel),
+            kind: PlannedKind::New,
+            top_category: cat,
+        };
+        let plan = InstallPlan {
+            files: vec![
+                file("notify.sh", TopCategory::Hooks),
+                file("x/hooks/pre.sh", TopCategory::Agents),
+                file("hooks/role-hook.sh", TopCategory::Roles),
+                file("x/config.yaml", TopCategory::Agents),
+                file("reviewer.md", TopCategory::Roles),
+                file("hello.yaml", TopCategory::Macros),
+            ],
+            mcp_json: None,
+        };
+
+        let lines = hook_script_lines(&plan);
+
+        assert_eq!(
+            lines,
+            vec![
+                "bundle defines hook script: hooks/notify.sh",
+                "bundle defines hook script: agents/x/hooks/pre.sh",
+                "bundle defines hook script: roles/hooks/role-hook.sh",
+            ]
+        );
+    }
+
     #[test]
     fn classify_file_new_when_dst_missing() {
         let dir = fresh_temp_dir("classify-new-");
@@ -3420,6 +3608,91 @@ mod tests {
         let _ = fs::remove_dir_all(&src_root);
     }
 
+    fn hooks_fixture_bundle(label: &str) -> (PathBuf, PathBuf) {
+        let src_root = fresh_temp_dir(label);
+        let repo = src_root.join("hooky");
+        write_src(&repo, "hooks/notify-me.sh", "#!/bin/sh\necho hi\n");
+        write_src(&repo, "roles/hooks/role-hook.sh", "#!/bin/sh\n");
+        write_src(&repo, "agents/x/hooks/pre.sh", "#!/bin/sh\n");
+        write_src(&repo, "macros/hello.yaml", "name: hello\n");
+        init_bundle_repo(&repo);
+        (src_root, repo)
+    }
+
+    #[cfg(unix)]
+    fn assert_executable(path: &Path) {
+        use std::os::unix::fs::PermissionsExt;
+        let mode = fs::metadata(path).unwrap().permissions().mode();
+        assert_ne!(
+            mode & 0o111,
+            0,
+            "{} must carry the executable bit",
+            path.display()
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn install_remote_installs_all_hooks_dirs_and_records_hooks_category() {
+        let _guard = TestVaultConfigGuard::new("prov-hooks-dirs");
+        let (src_root, repo) = hooks_fixture_bundle("prov-hooks-dirs-src-");
+
+        install_remote(repo.to_str().unwrap(), None, false).unwrap();
+
+        let top = paths::hooks_dir().join("notify-me.sh");
+        let role = paths::roles_dir().join("hooks/role-hook.sh");
+        let agent = paths::agents_data_dir().join("x/hooks/pre.sh");
+        assert!(top.is_file(), "top-level hooks/ installs to hooks_dir");
+        assert!(role.is_file(), "roles/hooks/ installs via the roles walk");
+        assert!(
+            agent.is_file(),
+            "agents/<name>/hooks/ installs via the agents walk"
+        );
+        #[cfg(unix)]
+        {
+            assert_executable(&top);
+            assert_executable(&role);
+            assert_executable(&agent);
+        }
+
+        let store = BundleStore::load().unwrap();
+        let record = store.get("hooky").unwrap();
+        let category_of = |path: &str| {
+            record
+                .files
+                .iter()
+                .find(|f| f.path == path)
+                .unwrap_or_else(|| panic!("no provenance row for {path}"))
+                .category
+                .clone()
+        };
+        assert_eq!(category_of("hooks/notify-me.sh"), "hooks");
+        assert_eq!(category_of("roles/hooks/role-hook.sh"), "roles");
+        assert_eq!(category_of("agents/x/hooks/pre.sh"), "agents");
+        let _ = fs::remove_dir_all(&src_root);
+    }
+
+    #[test]
+    #[serial]
+    fn install_remote_filter_hooks_restricts_to_top_level_hooks_dir() {
+        let _guard = TestVaultConfigGuard::new("prov-hooks-filter");
+        let (src_root, repo) = hooks_fixture_bundle("prov-hooks-filter-src-");
+
+        install_remote(repo.to_str().unwrap(), Some(InstallFilter::Hooks), false).unwrap();
+
+        assert!(paths::hooks_dir().join("notify-me.sh").is_file());
+        assert!(!paths::roles_dir().join("hooks/role-hook.sh").exists());
+        assert!(!paths::agents_data_dir().join("x/hooks/pre.sh").exists());
+        assert!(!paths::macros_dir().join("hello.yaml").exists());
+
+        let store = BundleStore::load().unwrap();
+        let record = store.get("hooky").unwrap();
+        assert_eq!(record.files.len(), 1);
+        assert_eq!(record.files[0].path, "hooks/notify-me.sh");
+        assert_eq!(record.files[0].category, "hooks");
+        let _ = fs::remove_dir_all(&src_root);
+    }
+
     #[test]
     #[serial]
     fn install_remote_without_manifest_uses_repo_slug_and_short_sha_version() {
@@ -3467,12 +3740,14 @@ mod tests {
                 PlannedFile {
                     src: src_new,
                     dst: dst_new.clone(),
+                    rel: PathBuf::from("new.yaml"),
                     kind: PlannedKind::New,
                     top_category: TopCategory::Macros,
                 },
                 PlannedFile {
                     src: src_conflict,
                     dst: dst_conflict.clone(),
+                    rel: PathBuf::from("conflict.yaml"),
                     kind: PlannedKind::Conflict,
                     top_category: TopCategory::Macros,
                 },
@@ -3525,6 +3800,7 @@ mod tests {
             files: vec![PlannedFile {
                 src,
                 dst: dst.clone(),
+                rel: PathBuf::from("owned.yaml"),
                 kind: PlannedKind::Conflict,
                 top_category: TopCategory::Macros,
             }],
@@ -3656,12 +3932,50 @@ mod tests {
         }
         let _guard = TestVaultConfigGuard::new("prov-builtin");
 
-        crate::config::install_assets(crate::config::AssetCategory::Macros).unwrap();
+        config::install_assets(config::AssetCategory::Macros).unwrap();
 
         assert!(fs::read_dir(paths::macros_dir()).unwrap().next().is_some());
         assert!(!paths::installed_bundles_file().exists());
     }
 
+    #[test]
+    #[serial]
+    fn builtin_hooks_category_installs_example_scripts() {
+        if *IS_STDOUT_TERMINAL {
+            eprintln!(
+                "Skipping builtin_hooks_category_installs_example_scripts: requires non-TTY stdout"
+            );
+            return;
+        }
+        let _guard = TestVaultConfigGuard::new("prov-hooks");
+        let hooks_key = get_env_name("hooks_dir");
+        let previous_hooks = env::var_os(&hooks_key);
+        let hooks_dir = fresh_temp_dir("prov-hooks-dir-");
+        unsafe {
+            env::set_var(&hooks_key, &hooks_dir);
+        }
+
+        // Capture outcomes before restoring the env var so a failed assertion
+        // cannot leave the hooks-dir override pointing at a deleted temp dir.
+        let result = config::install_assets(AssetCategory::Hooks);
+        let installed = (
+            hooks_dir.join("notify.sh").is_file(),
+            hooks_dir.join("log-events.sh").is_file(),
+        );
+
+        unsafe {
+            match previous_hooks {
+                Some(v) => env::set_var(&hooks_key, v),
+                None => env::remove_var(&hooks_key),
+            }
+        }
+        let _ = fs::remove_dir_all(&hooks_dir);
+
+        result.unwrap();
+        assert!(installed.0, "notify.sh must be installed");
+        assert!(installed.1, "log-events.sh must be installed");
+    }
+
     #[test]
     #[serial]
     fn update_silently_refreshes_owned_unmodified_files() {
@@ -3798,6 +4112,7 @@ mod tests {
             files: vec![PlannedFile {
                 src,
                 dst: dst.clone(),
+                rel: PathBuf::from("owned.yaml"),
                 kind: PlannedKind::Conflict,
                 top_category: TopCategory::Macros,
             }],
@@ -3844,6 +4159,7 @@ mod tests {
             files: vec![PlannedFile {
                 src,
                 dst: dst.clone(),
+                rel: PathBuf::from("owned.yaml"),
                 kind: PlannedKind::Conflict,
                 top_category: TopCategory::Macros,
             }],
@@ -3923,6 +4239,7 @@ mod tests {
             files: vec![PlannedFile {
                 src,
                 dst: dst.clone(),
+                rel: PathBuf::from("shared.yaml"),
                 kind: PlannedKind::Conflict,
                 top_category: TopCategory::Macros,
             }],
@@ -4195,6 +4512,7 @@ mod tests {
             files: vec![PlannedFile {
                 src: dir.join("bundle-src/agents/foo/graph.yaml"),
                 dst: dir.join("agents/foo/graph.yaml"),
+                rel: PathBuf::from("foo/graph.yaml"),
                 kind: PlannedKind::New,
                 top_category: TopCategory::Agents,
             }],
@@ -4237,6 +4555,7 @@ mod tests {
             files: vec![PlannedFile {
                 src: dir.join("bundle-src/agents/foo/graph.yaml"),
                 dst: dir.join("agents/foo/graph.yaml"),
+                rel: PathBuf::from("foo/graph.yaml"),
                 kind: PlannedKind::New,
                 top_category: TopCategory::Agents,
             }],

src/config/mod.rs

@@ -1,6 +1,7 @@
 mod agent;
 mod app_config;
 mod app_state;
+pub(crate) mod builtin_manifest;
 mod bundles;
 mod input;
 mod install_remote;
@@ -75,12 +76,14 @@ use crate::client::{
     oauth, set_client_models_config,
 };
 use crate::function::{FunctionDeclaration, Functions};
+use crate::hooks::HooksMap;
 use crate::rag::Rag;
 use crate::sandbox::SANDBOX_ENV_FLAG;
 use crate::utils::*;
 pub use macros::macro_execute;
 
 use crate::config::macros::Macro;
+use crate::hooks;
 use crate::vault::{
     GlobalVault, Vault, create_vault_password_file, interpolate_secrets, prompt_provider_choice,
 };
@@ -162,6 +165,7 @@ const AGENT_GRAPH_FILE_NAME: &str = "graph.yaml";
 const ROLES_DIR_NAME: &str = "roles";
 const SKILLS_DIR_NAME: &str = "skills";
 const MACROS_DIR_NAME: &str = "macros";
+const HOOKS_DIR_NAME: &str = "hooks";
 const ENV_FILE_NAME: &str = ".env";
 const MESSAGES_FILE_NAME: &str = "messages.md";
 const SESSIONS_DIR_NAME: &str = "sessions";
@@ -262,6 +266,9 @@ pub struct Config {
     pub enabled_mcp_servers: Option<Vec<String>>,
     pub mcp_tools: Option<IndexMap<String, Vec<String>>>,
 
+    #[serde(default)]
+    pub hooks: HooksMap,
+
     pub auto_continue: bool,
     pub max_auto_continues: usize,
     pub inject_todo_instructions: bool,
@@ -350,6 +357,8 @@ impl Default for Config {
             enabled_mcp_servers: None,
             mcp_tools: None,
 
+            hooks: Default::default(),
+
             auto_continue: false,
             max_auto_continues: 10,
             inject_todo_instructions: true,
@@ -412,6 +421,8 @@ pub fn install_builtins() -> Result<()> {
     Agent::install_builtin_agents(false)?;
     Macro::install_macros(false)?;
     Skill::install_builtin_skills(false)?;
+    hooks::install_builtin_hooks(false)?;
+    Role::install_builtin_role_hooks(false)?;
     Ok(())
 }
 
@@ -421,12 +432,20 @@ pub enum AssetCategory {
     Macros,
     Functions,
     Skills,
+    Hooks,
     #[value(name = "mcp-config", alias = "mcp_config")]
     McpConfig,
 }
 
 impl AssetCategory {
-    pub const NAMES: [&'static str; 5] = ["agents", "macros", "functions", "skills", "mcp-config"];
+    pub const NAMES: [&'static str; 6] = [
+        "agents",
+        "macros",
+        "functions",
+        "skills",
+        "hooks",
+        "mcp-config",
+    ];
 
     pub fn parse(name: &str) -> Option<Self> {
         match name {
@@ -434,6 +453,7 @@ impl AssetCategory {
             "macros" => Some(Self::Macros),
             "functions" => Some(Self::Functions),
             "skills" => Some(Self::Skills),
+            "hooks" => Some(Self::Hooks),
             "mcp-config" | "mcp_config" => Some(Self::McpConfig),
             _ => None,
         }
@@ -453,17 +473,19 @@ pub enum InstallFilter {
     Skills,
     Macros,
     Functions,
+    Hooks,
     #[value(name = "mcp-config", alias = "mcp_config")]
     McpConfig,
 }
 
 impl InstallFilter {
-    pub const NAMES: [&'static str; 6] = [
+    pub const NAMES: [&'static str; 7] = [
         "agents",
         "roles",
         "skills",
         "macros",
         "functions",
+        "hooks",
         "mcp-config",
     ];
 
@@ -474,6 +496,7 @@ impl InstallFilter {
             "skills" => Some(Self::Skills),
             "macros" => Some(Self::Macros),
             "functions" => Some(Self::Functions),
+            "hooks" => Some(Self::Hooks),
             "mcp-config" | "mcp_config" => Some(Self::McpConfig),
             _ => None,
         }
@@ -486,6 +509,7 @@ pub fn install_assets(category: AssetCategory) -> Result<()> {
         AssetCategory::Macros => ("macros", paths::macros_dir()),
         AssetCategory::Functions => ("functions", paths::functions_dir()),
         AssetCategory::Skills => ("skills", paths::skills_dir()),
+        AssetCategory::Hooks => ("hooks", paths::hooks_dir()),
         AssetCategory::McpConfig => ("MCP config", paths::mcp_config_file()),
     };
 
@@ -499,6 +523,7 @@ pub fn install_assets(category: AssetCategory) -> Result<()> {
         AssetCategory::Macros => Macro::install_macros(true)?,
         AssetCategory::Functions => Functions::install_builtin_global_tools(true)?,
         AssetCategory::Skills => Skill::install_builtin_skills(true)?,
+        AssetCategory::Hooks => hooks::install_builtin_hooks(true)?,
         AssetCategory::McpConfig => Functions::install_mcp_config()?,
     }
 
@@ -1393,6 +1418,59 @@ clients:
         assert!(!CONFIG_TEMPLATE.contains("escalation_timeout"));
     }
 
+    #[test]
+    fn config_template_carries_hooks_block_without_global_hooks() {
+        // `global_hooks` is a per-agent whitelist; the global template must never grow it.
+        assert!(CONFIG_TEMPLATE.contains("\nhooks:"));
+        assert!(!CONFIG_TEMPLATE.contains("global_hooks"));
+    }
+
+    #[test]
+    fn config_template_renders_with_empty_hooks() {
+        let clients = json!([{ "type": "openai", "api_key": "sk-test" }]);
+
+        let rendered = render_config_template("openai:gpt-4o", None, &clients).unwrap();
+
+        assert!(rendered.contains("\nhooks:"));
+        assert!(!rendered.contains("global_hooks"));
+
+        let cfg = Config::load_from_str(&rendered).unwrap();
+        assert!(cfg.hooks.is_empty());
+    }
+
+    #[test]
+    fn config_parses_hooks_map_preserving_order() {
+        let yaml = "\
+hooks:
+  tool.started:
+    - name: notify
+      command: ./hooks/notify.sh
+    - name: audit
+      command: ./hooks/audit.sh
+  turn.completed:
+    - name: webhook
+      command: curl -s https://example.com/hook
+";
+        let cfg: Config = serde_yaml::from_str(yaml).unwrap();
+
+        assert_eq!(
+            cfg.hooks.keys().collect::<Vec<_>>(),
+            vec!["tool.started", "turn.completed"]
+        );
+        assert_eq!(cfg.hooks["tool.started"].len(), 2);
+        assert_eq!(cfg.hooks["tool.started"][0].name, "notify");
+        assert_eq!(cfg.hooks["tool.started"][0].command, "./hooks/notify.sh");
+        assert_eq!(cfg.hooks["turn.completed"][0].name, "webhook");
+    }
+
+    #[test]
+    fn config_without_hooks_parses_unchanged() {
+        let cfg: Config = serde_yaml::from_str("model: openai:gpt-4o").unwrap();
+
+        assert!(cfg.hooks.is_empty());
+        assert_eq!(cfg.model_id, "openai:gpt-4o");
+    }
+
     #[test]
     fn config_enabled_macros_empty_string_is_some_empty() {
         let cfg: Config = serde_yaml::from_str("enabled_macros: \"\"").unwrap();

src/config/paths.rs

@@ -2,7 +2,7 @@ use super::role::Role;
 use super::{
     AGENT_GRAPH_FILE_NAME, AGENTS_DIR_NAME, BASH_PROMPT_UTILS_FILE_NAME, CONFIG_FILE_NAME,
     ENV_FILE_NAME, FUNCTIONS_BIN_DIR_NAME, FUNCTIONS_DIR_NAME, GLOBAL_TOOLS_DIR_NAME,
-    GLOBAL_TOOLS_UTILS_DIR_NAME, HIDDEN_MCP_FILE_NAME, INSTALLED_BUNDLES_FILE_NAME,
+    GLOBAL_TOOLS_UTILS_DIR_NAME, HIDDEN_MCP_FILE_NAME, HOOKS_DIR_NAME, INSTALLED_BUNDLES_FILE_NAME,
     MACROS_DIR_NAME, MCP_FILE_NAME, MEMORY_DIR_NAME, MEMORY_INDEX_FILE_NAME, ModelsOverride,
     RAGS_DIR_NAME, ROLES_DIR_NAME, SBX_KIT_DIR_NAME, SBX_KIT_HASH_FILE, SBX_MIXIN_FILE_NAME,
     SBX_MIXIN_KITS_DIR_NAME, SKILLS_DIR_NAME, WORKSPACE_COYOTE_DIR_NAME,
@@ -184,6 +184,13 @@ pub fn role_file(name: &str) -> PathBuf {
     roles_dir().join(format!("{name}.md"))
 }
 
+pub fn hooks_dir() -> PathBuf {
+    match env::var(get_env_name("hooks_dir")) {
+        Ok(value) => PathBuf::from(value),
+        Err(_) => local_dir(HOOKS_DIR_NAME),
+    }
+}
+
 pub fn skills_dir() -> PathBuf {
     match env::var(get_env_name("skills_dir")) {
         Ok(value) => PathBuf::from(value),
@@ -947,6 +954,31 @@ mod tests {
         }
     }
 
+    #[test]
+    #[serial_test::serial]
+    fn hooks_dir_reflects_env_var_state() {
+        let env_name = get_env_name("hooks_dir");
+        let prev = env::var_os(&env_name);
+
+        unsafe {
+            env::remove_var(&env_name);
+        }
+        assert_eq!(hooks_dir(), config_dir().join("hooks"));
+
+        let probe = PathBuf::from("/tmp/coyote-hooks-dir-probe");
+        unsafe {
+            env::set_var(&env_name, &probe);
+        }
+        assert_eq!(hooks_dir(), probe);
+
+        unsafe {
+            match prev {
+                Some(v) => env::set_var(&env_name, v),
+                None => env::remove_var(&env_name),
+            }
+        }
+    }
+
     #[test]
     fn list_skills_skips_invalid_directory_names() {
         let unique = time::SystemTime::now()

src/config/request_context.rs

@@ -50,6 +50,7 @@ use super::memory::{
     DEFAULT_MEMORY_CAP_WITH_TOOLS, DEFAULT_MEMORY_CAP_WITHOUT_TOOLS, MemoryStore, WorkspaceMemory,
 };
 use crate::graph;
+use crate::hooks::{self, HookEvent};
 use anyhow::{Context, Error, Result, bail};
 use colored::Colorize;
 use gman::providers::SupportedProvider;
@@ -59,6 +60,7 @@ use inquire::{Confirm, MultiSelect, Text, list_option::ListOption, validator::Va
 use log::warn;
 use parking_lot::RwLock;
 use prompts::DEFAULT_SKILL_INSTRUCTIONS;
+use rand::distr::{Alphanumeric, SampleString};
 use std::collections::{BTreeSet, HashMap, HashSet};
 use std::fs::{File, OpenOptions, read_dir, read_to_string, remove_dir_all, remove_file};
 use std::io::Write;
@@ -354,6 +356,13 @@ pub struct RequestContext {
 
     pub session_abort: Option<AbortSignal>,
 
+    /// Synthesized `COYOTE_AGENT_ID` for a top-level agent run (headless
+    /// `--agent` dispatch or an interactive agent context). Scheme:
+    /// `top-<agent-name>-<8-char alphanumeric nonce>`; spawned sub-agents
+    /// carry supervisor-issued ids instead. `Some` exactly while the
+    /// top-level `agent.*` bracket is open.
+    pub top_level_agent_id: Option<String>,
+
     pub render_mode: RenderMode,
 }
 
@@ -398,6 +407,7 @@ impl RequestContext {
             auto_continue_paused: None,
             pending_prefill: None,
             session_abort: None,
+            top_level_agent_id: None,
             render_mode: RenderMode::default(),
         }
     }
@@ -469,6 +479,7 @@ impl RequestContext {
             auto_continue_paused: None,
             pending_prefill: None,
             session_abort: None,
+            top_level_agent_id: None,
             render_mode: RenderMode::default(),
         };
         ctx.refresh_mcp_tool_filters();
@@ -529,6 +540,9 @@ impl RequestContext {
             auto_continue_paused: self.auto_continue_paused.clone(),
             pending_prefill: None,
             session_abort: self.session_abort.clone(),
+            // Branches never own the top-level `agent.*` bracket; only the
+            // root flow that opened it may fire its terminal event.
+            top_level_agent_id: None,
             render_mode: self.render_mode,
         }
     }
@@ -585,6 +599,7 @@ impl RequestContext {
             auto_continue_paused: None,
             pending_prefill: None,
             session_abort: None,
+            top_level_agent_id: None,
             render_mode: parent.render_mode,
         }
     }
@@ -1054,6 +1069,12 @@ impl RequestContext {
     }
 
     pub fn exit_session(&mut self) -> Result<()> {
+        // Fired while the session is still attached so the hook sees
+        // COYOTE_SESSION_ID and session-held role hooks still resolve; no
+        // session means no event.
+        if self.session.is_some() {
+            hooks::fire(HookEvent::SessionEnded, self, &[], None);
+        }
         if let Some(mut session) = self.session.take() {
             let sessions_dir = self.sessions_dir();
             session.exit(&sessions_dir, self.working_mode.is_repl())?;
@@ -4613,6 +4634,7 @@ impl RequestContext {
             );
         }
         let mut session;
+        let mut created_new_session = false;
         match session_name {
             None | Some(TEMP_SESSION_NAME) => {
                 let session_file = self.session_file(TEMP_SESSION_NAME);
@@ -4622,11 +4644,13 @@ impl RequestContext {
                     })?;
                 }
                 session = Some(Session::new_from_ctx(self, app, TEMP_SESSION_NAME)?);
+                created_new_session = true;
             }
             Some(name) => {
                 let session_path = self.session_file(name);
                 if !session_path.exists() {
                     session = Some(Session::new_from_ctx(self, app, name)?);
+                    created_new_session = true;
                 } else {
                     session = Some(Session::load_from_ctx(self, app, name, &session_path)?);
                 }
@@ -4709,6 +4733,9 @@ impl RequestContext {
         }
         self.refresh_mcp_tool_filters();
         self.init_agent_session_variables(new_session)?;
+        if created_new_session {
+            hooks::fire(HookEvent::SessionStarted, self, &[], None);
+        }
         Ok(())
     }
 
@@ -4874,6 +4901,9 @@ impl RequestContext {
             tool_tracker,
         };
 
+        // Interactive switch-away closes the top-level agent bracket while
+        // the agent is still attached, so agent-scoped hooks resolve.
+        self.top_level_agent_finished(None);
         if self.agent.take().is_some() {
             if let Some(supervisor) = self.supervisor.clone() {
                 supervisor.read().cancel_recursive();
@@ -4901,6 +4931,50 @@ impl RequestContext {
         Ok(())
     }
 
+    pub fn top_level_agent_started(&mut self) {
+        if self.top_level_agent_id.is_some() {
+            return;
+        }
+
+        let Some(agent) = self.agent.as_ref() else {
+            return;
+        };
+        let nonce = Alphanumeric.sample_string(&mut rand::rng(), 8);
+        let id = format!("top-{}-{nonce}", agent.name());
+        self.top_level_agent_id = Some(id.clone());
+
+        hooks::fire(
+            HookEvent::AgentStarted,
+            self,
+            &[("COYOTE_AGENT_ID", id)],
+            None,
+        );
+    }
+
+    pub fn top_level_agent_finished(&mut self, error: Option<&Error>) {
+        let Some(id) = self.top_level_agent_id.take() else {
+            return;
+        };
+
+        match error {
+            None => hooks::fire(
+                HookEvent::AgentCompleted,
+                self,
+                &[("COYOTE_AGENT_ID", id)],
+                None,
+            ),
+            Some(err) => hooks::fire(
+                HookEvent::AgentFailed,
+                self,
+                &[
+                    ("COYOTE_AGENT_ID", id),
+                    ("COYOTE_AGENT_ERROR", format!("{err:#}")),
+                ],
+                None,
+            ),
+        }
+    }
+
     pub async fn edit_role(&mut self, app: &AppConfig, abort_signal: AbortSignal) -> Result<()> {
         let role_name;
         if let Some(session) = self.session.as_ref() {
@@ -5421,6 +5495,7 @@ mod tests {
     use crate::config::tool_scope::test_fixtures::{FixtureServer, fixture_runtime};
     use crate::function::jobs::RingBuf;
     use crate::function::{ToolCall, skill};
+    use crate::hooks::{HookDef, HooksMap, test_sink};
     use crate::mcp::{McpServer, McpServerFeatures, McpServersConfig, McpTransportType};
     use crate::supervisor::{
         AgentExitStatus, AgentHandle, AgentResult, JobHandle, JobResult, JobState, JobStatus,
@@ -5428,6 +5503,7 @@ mod tests {
     use crate::utils;
     use crate::utils::get_env_name;
     use crate::vault::Vault;
+    use anyhow::anyhow;
     use rmcp::model::PromptArgument;
     use serde_json::json;
     use serial_test::serial;
@@ -8230,6 +8306,349 @@ mod tests {
         assert!(ctx.session.is_none());
     }
 
+    fn hooks_map_of(events: &[&str], marker: &str) -> HooksMap {
+        let mut map = HooksMap::default();
+        for event in events {
+            map.insert(
+                event.to_string(),
+                vec![HookDef {
+                    name: format!("{marker}-{event}"),
+                    command: "true".to_string(),
+                }],
+            );
+        }
+        map
+    }
+
+    fn marker_captures(marker: &str) -> Vec<test_sink::Capture> {
+        test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name.starts_with(marker))
+            .collect()
+    }
+
+    /// Writes an agent whose config carries agent-scoped hooks for every
+    /// `agent.*` event, named `<marker>-<event>`.
+    fn seed_agent_with_hooks(agent_name: &str, marker: &str) {
+        let agent_dir = paths::agent_data_dir(agent_name);
+        create_dir_all(&agent_dir).unwrap();
+        let mut config = format!("name: {agent_name}\ninstructions: hi\nhooks:\n");
+        for event in ["agent.started", "agent.completed", "agent.failed"] {
+            config.push_str(&format!(
+                "  {event}:\n    - name: {marker}-{event}\n      command: 'true'\n"
+            ));
+        }
+        write(agent_dir.join("config.yaml"), config).unwrap();
+    }
+
+    fn unique_name(prefix: &str) -> String {
+        format!(
+            "{prefix}_{}",
+            SystemTime::now()
+                .duration_since(UNIX_EPOCH)
+                .unwrap()
+                .as_nanos()
+        )
+    }
+
+    #[test]
+    #[serial]
+    fn use_session_fires_session_started_for_new_sessions_only() {
+        let _guard = TestConfigDirGuard::new();
+        let sessions_dir = paths::local_dir("sessions");
+        create_dir_all(&sessions_dir).unwrap();
+        let _sink = test_sink::install();
+        let marker = "sess-started-q8n";
+
+        let mut ctx = create_test_ctx();
+        ctx.update_app_config(|app| app.hooks = hooks_map_of(&["session.started"], marker));
+        let app = ctx.app.config.clone();
+        let abort = utils::create_abort_signal();
+        run_async(ctx.use_session(&app, Some("hook-fresh"), abort.clone())).unwrap();
+
+        let captures = marker_captures(marker);
+        assert_eq!(captures.len(), 1, "a new session fires exactly one event");
+        assert_eq!(
+            captures[0]
+                .envs
+                .get("COYOTE_SESSION_ID")
+                .map(String::as_str),
+            Some("hook-fresh")
+        );
+
+        // Resuming a persisted session fires nothing.
+        write_paused_todo_session(&ctx, "hook-resume");
+        let mut resumed_ctx = create_test_ctx();
+        resumed_ctx.update_app_config(|app| app.hooks = hooks_map_of(&["session.started"], marker));
+        let resumed_app = resumed_ctx.app.config.clone();
+        run_async(resumed_ctx.use_session(&resumed_app, Some("hook-resume"), abort)).unwrap();
+        assert_eq!(
+            marker_captures(marker).len(),
+            1,
+            "resume must not fire session.started"
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn exit_session_fires_session_ended_only_with_a_session() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = test_sink::install();
+        let marker = "sess-ended-w5c";
+
+        let mut ctx = create_test_ctx();
+        ctx.update_app_config(|app| app.hooks = hooks_map_of(&["session.ended"], marker));
+
+        // Sessionless (headless) exit path: nothing fires.
+        ctx.exit_session().unwrap();
+        assert!(marker_captures(marker).is_empty());
+
+        ctx.session = Some(Session::default());
+        ctx.exit_session().unwrap();
+        ctx.exit_session().unwrap();
+        assert_eq!(
+            marker_captures(marker).len(),
+            1,
+            "session.ended fires exactly once, only while a session is attached"
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn chat_completion_seams_fire_no_turn_events_in_child_contexts() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = test_sink::install();
+        let marker = "child-turn-b4h";
+
+        let mut ctx = create_test_ctx();
+        ctx.update_app_config(|app| {
+            app.hooks = hooks_map_of(
+                &[
+                    "turn.started",
+                    "turn.completed",
+                    "turn.interrupted",
+                    "turn.failed",
+                ],
+                marker,
+            )
+        });
+        let app = ctx.app.config.clone();
+
+        let input = Input::from_str(&ctx, "hello", None).unwrap();
+        ctx.before_chat_completion(&input).unwrap();
+        ctx.after_chat_completion(&app, &input, "output", &[])
+            .unwrap();
+
+        assert!(
+            marker_captures(marker).is_empty(),
+            "per-round chat-completion seams must never fire turn events"
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn top_level_agent_bracket_fires_started_and_completed_once() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = test_sink::install();
+        let marker = "agent-top-ok-m2s";
+        let agent_name = unique_name("hook_agent");
+        seed_agent_with_hooks(&agent_name, marker);
+
+        let mut ctx = create_test_ctx();
+        let app = ctx.app.config.clone();
+        let abort = utils::create_abort_signal();
+        run_async(ctx.use_agent(&app, &agent_name, None, abort)).unwrap();
+
+        ctx.top_level_agent_started();
+        // Per agent RUN, never per message: re-entering while open is a no-op.
+        ctx.top_level_agent_started();
+        ctx.top_level_agent_finished(None);
+        ctx.top_level_agent_finished(None);
+
+        let captures = marker_captures(marker);
+        let started: Vec<_> = captures
+            .iter()
+            .filter(|capture| capture.hook_name == format!("{marker}-agent.started"))
+            .collect();
+        let completed: Vec<_> = captures
+            .iter()
+            .filter(|capture| capture.hook_name == format!("{marker}-agent.completed"))
+            .collect();
+        assert_eq!(started.len(), 1);
+        assert_eq!(completed.len(), 1);
+        assert!(
+            captures
+                .iter()
+                .all(|capture| capture.hook_name != format!("{marker}-agent.failed"))
+        );
+        let id = started[0]
+            .envs
+            .get("COYOTE_AGENT_ID")
+            .expect("agent id env");
+        assert!(
+            id.starts_with(&format!("top-{agent_name}-")),
+            "synthesized id must follow the top-<agent>-<nonce> scheme: {id}"
+        );
+        assert_eq!(completed[0].envs.get("COYOTE_AGENT_ID"), Some(id));
+        assert_eq!(
+            started[0].envs.get("COYOTE_AGENT_NAME").map(String::as_str),
+            Some(agent_name.as_str())
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn top_level_agent_failure_fires_agent_failed_with_error() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = test_sink::install();
+        let marker = "agent-top-err-f7d";
+        let agent_name = unique_name("hook_agent");
+        seed_agent_with_hooks(&agent_name, marker);
+
+        let mut ctx = create_test_ctx();
+        let app = ctx.app.config.clone();
+        let abort = utils::create_abort_signal();
+        run_async(ctx.use_agent(&app, &agent_name, None, abort)).unwrap();
+
+        ctx.top_level_agent_started();
+        let err = anyhow!("dispatch exploded");
+        ctx.top_level_agent_finished(Some(&err));
+
+        let captures = marker_captures(marker);
+        let failed: Vec<_> = captures
+            .iter()
+            .filter(|capture| capture.hook_name == format!("{marker}-agent.failed"))
+            .collect();
+        assert_eq!(failed.len(), 1);
+        assert!(
+            captures
+                .iter()
+                .all(|capture| capture.hook_name != format!("{marker}-agent.completed"))
+        );
+        assert_eq!(
+            failed[0].envs.get("COYOTE_AGENT_ERROR").map(String::as_str),
+            Some("dispatch exploded")
+        );
+        assert!(failed[0].envs.contains_key("COYOTE_AGENT_ID"));
+    }
+
+    #[test]
+    #[serial]
+    fn top_level_agent_helpers_noop_without_agent() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = test_sink::install();
+        let marker = "agent-top-role-only-c9k";
+
+        let mut ctx = create_test_ctx();
+        ctx.update_app_config(|app| {
+            app.hooks = hooks_map_of(
+                &["agent.started", "agent.completed", "agent.failed"],
+                marker,
+            )
+        });
+        ctx.role = Some(Role::new("plain", "prompt"));
+
+        ctx.top_level_agent_started();
+        ctx.top_level_agent_finished(None);
+
+        assert!(
+            marker_captures(marker).is_empty(),
+            "a role-only context must fire no agent events"
+        );
+        assert!(ctx.top_level_agent_id.is_none());
+    }
+
+    #[test]
+    #[serial]
+    fn exit_agent_closes_top_level_agent_bracket() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = test_sink::install();
+        let marker = "agent-top-exit-v3p";
+        let agent_name = unique_name("hook_agent");
+        seed_agent_with_hooks(&agent_name, marker);
+
+        let mut ctx = create_test_ctx();
+        let app = ctx.app.config.clone();
+        let abort = utils::create_abort_signal();
+        run_async(ctx.use_agent(&app, &agent_name, None, abort)).unwrap();
+        ctx.top_level_agent_started();
+
+        ctx.exit_agent(&app).unwrap();
+        // A later exit seam (REPL teardown) must not double-fire.
+        ctx.top_level_agent_finished(None);
+
+        let captures = marker_captures(marker);
+        assert_eq!(
+            captures
+                .iter()
+                .filter(|capture| capture.hook_name == format!("{marker}-agent.completed"))
+                .count(),
+            1,
+            "switch-away fires the terminal event exactly once"
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn resolved_hooks_resolves_role_hooks_held_by_fresh_session() {
+        let _guard = TestConfigDirGuard::new();
+        let sessions_dir = paths::local_dir("sessions");
+        create_dir_all(&sessions_dir).unwrap();
+
+        let mut ctx = create_test_ctx();
+        let app = ctx.app.config.clone();
+        let abort = utils::create_abort_signal();
+        run_async(ctx.use_session(&app, Some("role-holder"), abort)).unwrap();
+
+        let role_content = "---\nhooks:\n  turn.completed:\n    - name: session-role-probe\n      command: role-cmd\n---\nPrompt";
+        ctx.use_role_obj(Role::new("hooked-role", role_content))
+            .unwrap();
+        assert!(
+            ctx.role.is_none(),
+            "use_role_obj must move the role into the active session"
+        );
+
+        let resolved = ctx.resolved_hooks(HookEvent::TurnCompleted);
+        assert_eq!(resolved.len(), 1);
+        assert_eq!(resolved[0].name, "session-role-probe");
+        assert_eq!(resolved[0].command, "role-cmd");
+        assert_eq!(resolved[0].cwd, paths::roles_dir());
+    }
+
+    #[test]
+    #[serial]
+    fn resolved_hooks_resolves_role_hooks_after_session_resume() {
+        let _guard = TestConfigDirGuard::new();
+        let sessions_dir = paths::local_dir("sessions");
+        create_dir_all(&sessions_dir).unwrap();
+        let roles_dir = paths::roles_dir();
+        create_dir_all(&roles_dir).unwrap();
+        write(
+            roles_dir.join("resume-hooked.md"),
+            "---\nhooks:\n  session.ended:\n    - name: resume-role-probe\n      command: role-cmd\n---\nYou are hooked.",
+        )
+        .unwrap();
+
+        let seed_ctx = create_test_ctx();
+        let session_path = seed_ctx.session_file("resume-role");
+        ensure_parent_exists(&session_path).unwrap();
+        write(
+            &session_path,
+            "model: test-seeded:test-chat\nrole_name: resume-hooked\nmessages: []\n",
+        )
+        .unwrap();
+
+        let mut ctx = create_test_ctx();
+        let app = ctx.app.config.clone();
+        let abort = utils::create_abort_signal();
+        run_async(ctx.use_session(&app, Some("resume-role"), abort)).unwrap();
+        assert!(ctx.role.is_none());
+
+        let resolved = ctx.resolved_hooks(HookEvent::SessionEnded);
+        assert_eq!(resolved.len(), 1, "resumed session must restore role hooks");
+        assert_eq!(resolved[0].name, "resume-role-probe");
+    }
+
     fn write_paused_todo_session(ctx: &RequestContext, name: &str) {
         let session_path = ctx.session_file(name);
         ensure_parent_exists(&session_path).unwrap();
@@ -8859,6 +9278,53 @@ mod tests {
         assert!(agents_dir.join("architect").join("config.yaml").exists());
     }
 
+    #[test]
+    #[serial]
+    fn install_builtin_agents_reconciles_hooks_subdir_via_manifest() {
+        use crate::config::builtin_manifest::BUILTIN_MANIFEST_FILE;
+
+        let _guard = TestConfigDirGuard::new();
+
+        Agent::install_builtin_agents(false).unwrap();
+
+        let agents_dir = paths::agents_data_dir();
+        // Simulate an upgrade from an older install whose coder shipped a
+        // hook script that the current embed no longer contains: the manifest
+        // records it, so reconciliation removes it — while a user-created
+        // script in the same directory (absent from the manifest) survives.
+        let hooks_dir = agents_dir.join("coder").join("hooks");
+        create_dir_all(&hooks_dir).unwrap();
+        write(hooks_dir.join(BUILTIN_MANIFEST_FILE), "old-hook.sh\n").unwrap();
+        write(hooks_dir.join("old-hook.sh"), "stale").unwrap();
+        write(hooks_dir.join("user-hook.sh"), "user-owned").unwrap();
+        // A custom agent outside the bundle is never reconciled, even with a
+        // manifest present.
+        let custom_hooks = agents_dir.join("myagent").join("hooks");
+        create_dir_all(&custom_hooks).unwrap();
+        write(custom_hooks.join(BUILTIN_MANIFEST_FILE), "custom.sh\n").unwrap();
+        write(custom_hooks.join("custom.sh"), "keep").unwrap();
+
+        Agent::install_builtin_agents(false).unwrap();
+
+        assert!(
+            !hooks_dir.join("old-hook.sh").exists(),
+            "manifest-listed hook absent from the embed must be removed"
+        );
+        assert!(
+            hooks_dir.join("user-hook.sh").exists(),
+            "user-created hook files must survive reconciliation"
+        );
+        assert!(
+            !hooks_dir.join(BUILTIN_MANIFEST_FILE).exists(),
+            "an empty shipped set removes the manifest itself"
+        );
+        assert!(
+            custom_hooks.join("custom.sh").exists(),
+            "custom agents outside the bundle must survive reconciliation"
+        );
+        assert!(custom_hooks.join(BUILTIN_MANIFEST_FILE).exists());
+    }
+
     #[test]
     #[serial]
     fn install_builtin_skills_force_overwrites_only_with_force() {
@@ -11545,7 +12011,7 @@ mod tests {
         let NodeType::Llm(holistic) = &holistic.node_type else {
             panic!("holistic must be an llm node");
         };
-        assert_eq!(holistic.max_iterations, 20);
+        assert_eq!(holistic.max_iterations, 45);
     }
 
     const BUNDLED_GRAPHS: [&str; 6] = [
@@ -14601,6 +15067,16 @@ mod tests {
             .map(str::to_owned)
     }
 
+    fn fv_soft_note(out: &serde_json::Value) -> Option<String> {
+        out["verdict_out"]["attention"]
+            .as_array()
+            .unwrap()
+            .iter()
+            .filter_map(|a| a.as_str())
+            .find(|a| a.starts_with("Verifier: ") && a.contains("could not be verified"))
+            .map(str::to_owned)
+    }
+
     #[test]
     fn code_reviewer_verdict_fv_duplicate_unknown_faults_count_individually() {
         if !cmd_available("python3") {
@@ -14609,6 +15085,9 @@ mod tests {
         }
         // finding-verifier's crash guard emits every fault entry under the
         // same "unknown" id; an id-indexed dict would collapse them to one.
+        // Non-sentinel faults are SOFT: the findings stand unverified with a
+        // human-attention note, but the lane is NOT flagged as a re-runnable
+        // pipeline fault.
         let entry = json!({
             "id": "unknown",
             "verdict": "UNVERIFIABLE",
@@ -14622,10 +15101,23 @@ mod tests {
         });
         let out = run_code_reviewer_script("verdict.py", &state);
         assert_eq!(out["verdict_out"]["verdict"], "NEEDS-HUMAN", "{out}");
-        let fault = fv_degraded_fault(&out).unwrap_or_else(|| panic!("{out}"));
         assert!(
-            fault.contains("2 verifier verdict(s)"),
+            fv_degraded_fault(&out).is_none(),
-            "each crash-guard entry must count: {fault}"
+            "crash-guard entries are soft faults, not a degraded lane: {out}"
+        );
+        let note = fv_soft_note(&out).unwrap_or_else(|| panic!("{out}"));
+        assert!(
+            note.contains("2 finding(s) could not be verified"),
+            "each crash-guard entry must count: {note}"
+        );
+        let reason = out["verdict_out"]["reason"].as_str().unwrap();
+        assert!(
+            reason.contains("2 finding(s) unverified (verifier branch fault)"),
+            "the reason must count the unverified findings: {out}"
+        );
+        assert!(
+            !reason.contains("pipeline fault(s) recorded"),
+            "soft faults must not trip the gauntlet's degraded-run anchor: {out}"
         );
     }
 
@@ -14638,6 +15130,8 @@ mod tests {
         // finding-verifier completes "successfully" with parse_fault's
         // sentinel entry inside the payload — not an "Agent node failed:"
         // banner — so the gate must read the sentinel id as a fault.
+        // The sentinel means the verifier verified NOTHING: this is the HARD,
+        // lane-degrading path.
         let state = json!({
             "changed_files": ["a.rs"],
             "domain_reports": ["clean report. DOMAIN_REVIEW_COMPLETE"],
@@ -14665,8 +15159,12 @@ mod tests {
             panic!("the degraded-verification fault must be in attention: {out}")
         });
         assert!(
-            fault.contains("1 verifier verdict(s) carry a pipeline fault"),
+            fault.contains("the verifier verified nothing"),
-            "the fault must count the faulted verdicts: {fault}"
+            "the fault must state that nothing was verified: {fault}"
+        );
+        assert!(
+            fault.contains("parse failed"),
+            "the fault must carry the sentinel's detail: {fault}"
         );
     }
 
@@ -14678,6 +15176,10 @@ mod tests {
         }
         // verify_fault's per-finding entry keeps the real finding id; the
         // fault is recognized by the note's PIPELINE-FAULT prefix.
+        // Per-finding faults are SOFT: the finding stands unverified with a
+        // human-attention note instead of a lane-degrading pipeline fault
+        // (re-running an entire ~1h lane over a few unverified findings is
+        // the wrong trade).
         let state = json!({
             "changed_files": ["a.rs"],
             "domain_reports": ["clean report. DOMAIN_REVIEW_COMPLETE"],
@@ -14694,12 +15196,24 @@ mod tests {
             v["verdict"], "NEEDS-HUMAN",
             "a lane-faulted verifier verdict must block: {out}"
         );
-        let fault = fv_degraded_fault(&out).unwrap_or_else(|| {
-            panic!("the degraded-verification fault must be in attention: {out}")
-        });
         assert!(
-            fault.contains("verifier lane failed after retries"),
+            fv_degraded_fault(&out).is_none(),
-            "the fault must carry the verifier's note: {fault}"
+            "a per-finding fault must not degrade the lane: {out}"
+        );
+        let note = fv_soft_note(&out)
+            .unwrap_or_else(|| panic!("the unverified-findings note must be in attention: {out}"));
+        assert!(
+            note.contains("verifier lane failed after retries"),
+            "the note must carry the verifier's fault detail: {note}"
+        );
+        let reason = v["reason"].as_str().unwrap();
+        assert!(
+            reason.contains("1 finding(s) unverified (verifier branch fault)"),
+            "the reason must count the unverified finding: {out}"
+        );
+        assert!(
+            !reason.contains("pipeline fault(s) recorded"),
+            "soft faults must not trip the gauntlet's degraded-run anchor: {out}"
         );
     }
 

src/config/role.rs

@@ -1,12 +1,17 @@
 use super::*;
 
 use crate::client::{Message, MessageContent, MessageRole, Model};
+use crate::config::builtin_manifest;
+use crate::function::write_file_atomic;
+use crate::hooks::HooksMap;
 
 use anyhow::Result;
 use fancy_regex::Regex;
 use rust_embed::Embed;
 use serde::{Deserialize, Serialize};
 use serde_json::Value;
+use std::collections::BTreeSet;
+use std::path::Path;
 use std::sync::LazyLock;
 
 pub const SHELL_ROLE: &str = "shell";
@@ -99,6 +104,8 @@ pub struct Role {
     skill_instructions: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     memory: Option<bool>,
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    hooks: Option<HooksMap>,
 
     #[serde(skip)]
     model: Model,
@@ -161,6 +168,7 @@ impl Role {
                         role.skill_instructions = value.as_str().map(|v| v.to_string())
                     }
                     "memory" => role.memory = value.as_bool(),
+                    "hooks" => role.hooks = parse_hooks_map(value),
                     _ => (),
                 }
             }
@@ -181,6 +189,26 @@ impl Role {
             .collect()
     }
 
+    /// Installs builtin role hook scripts into `<roles_dir>/hooks/` and
+    /// reconciles ones a release stopped shipping. This is the only builtin
+    /// install machinery roles have: general role installation deliberately
+    /// does not exist (builtin roles load straight from the embed).
+    pub fn install_builtin_role_hooks(force: bool) -> Result<()> {
+        let shipped: Vec<(String, String)> = RolesAsset::iter()
+            .filter_map(|file| {
+                let name = file.as_ref().strip_prefix("hooks/")?;
+                if name.is_empty() || name.contains('/') {
+                    return None;
+                }
+                let embedded = RolesAsset::get(file.as_ref())?;
+                let content = unsafe { std::str::from_utf8_unchecked(&embedded.data) };
+                Some((name.to_string(), content.to_string()))
+            })
+            .collect();
+
+        install_and_reconcile_role_hooks(&paths::roles_dir().join("hooks"), &shipped, force)
+    }
+
     pub fn has_args(&self) -> bool {
         self.name.contains('#')
     }
@@ -248,6 +276,10 @@ impl Role {
         if let Some(memory) = self.memory {
             metadata.push(format!("memory: {memory}"));
         }
+        if let Some(hooks) = &self.hooks {
+            let inline = serde_json::to_string(hooks).unwrap_or_else(|_| "{}".to_string());
+            metadata.push(format!("hooks: {inline}"));
+        }
         if metadata.is_empty() {
             format!("{}\n", self.prompt)
         } else if self.prompt.is_empty() {
@@ -380,6 +412,10 @@ impl Role {
         self.memory
     }
 
+    pub fn hooks(&self) -> Option<&HooksMap> {
+        self.hooks.as_ref()
+    }
+
     pub fn skills_enabled(&self) -> Option<bool> {
         self.skills_enabled
     }
@@ -544,6 +580,16 @@ fn parse_mcp_tools_map(value: &Value) -> Option<IndexMap<String, Vec<String>>> {
     Some(mcp_tools)
 }
 
+fn parse_hooks_map(value: &Value) -> Option<HooksMap> {
+    match serde_json::from_value(value.clone()) {
+        Ok(map) => Some(map),
+        Err(err) => {
+            debug!("Ignoring malformed hooks configuration: {err}");
+            None
+        }
+    }
+}
+
 fn parse_structure_prompt(prompt: &str) -> (&str, Vec<(&str, &str)>) {
     let mut text = prompt;
     let mut search_input = true;
@@ -592,6 +638,46 @@ fn parse_structure_prompt(prompt: &str) -> (&str, Vec<(&str, &str)>) {
     (prompt, vec![])
 }
 
+/// Only direct children of the hooks/ directory are supported: they are the
+/// only shape the builtin manifest tracks, so nested asset paths are skipped
+/// by the caller rather than installed unreconciled.
+fn install_and_reconcile_role_hooks(
+    dir: &Path,
+    shipped: &[(String, String)],
+    force: bool,
+) -> Result<()> {
+    if !shipped.is_empty() {
+        info!("Installing built-in role hooks in {}", dir.display());
+    }
+    let mut written = BTreeSet::new();
+    for (name, content) in shipped {
+        let path = dir.join(name);
+        if path.exists() && !force {
+            debug!(
+                "Role hook file already exists, skipping: {}",
+                path.display()
+            );
+            continue;
+        }
+        ensure_parent_exists(&path)?;
+        info!("Creating role hook file: {}", path.display());
+        write_file_atomic(&path, content, Some(0o755))?;
+        written.insert(name.clone());
+    }
+
+    let names: BTreeSet<String> = shipped.iter().map(|(name, _)| name.clone()).collect();
+    // Reconciliation is best-effort housekeeping: a failure here must not
+    // abort startup (install_builtins), matching the agent-side policy.
+    if let Err(err) = builtin_manifest::reconcile_builtin_dir(dir, &names, &written) {
+        warn!(
+            "Failed to reconcile builtin role hooks in {}: {err}",
+            dir.display()
+        );
+    }
+
+    Ok(())
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -641,6 +727,42 @@ mod tests {
         );
     }
 
+    #[test]
+    fn role_hooks_round_trip_through_export() {
+        let content = "---\nhooks:\n  turn.completed:\n    - name: notify\n      command: ./hooks/notify.sh\n---\nPrompt";
+
+        let role = Role::new("test", content);
+
+        let hooks = role.hooks().expect("hooks should be parsed");
+        assert_eq!(hooks["turn.completed"][0].name, "notify");
+        assert_eq!(hooks["turn.completed"][0].command, "./hooks/notify.sh");
+
+        let exported = role.export();
+        assert!(exported.contains("hooks:"));
+
+        let reparsed = Role::new("test", &exported);
+        assert_eq!(reparsed.hooks(), role.hooks());
+        assert_eq!(reparsed.prompt(), "Prompt");
+    }
+
+    #[test]
+    fn role_without_hooks_has_none_and_export_omits_key() {
+        let role = Role::new("test", "---\nmemory: true\n---\nPrompt");
+
+        assert!(role.hooks().is_none());
+        assert!(!role.export().contains("hooks:"));
+    }
+
+    #[test]
+    fn role_malformed_hooks_degrades_to_none() {
+        let content = "---\nhooks: [not, a, map]\n---\nPrompt";
+
+        let role = Role::new("test", content);
+
+        assert!(role.hooks().is_none());
+        assert_eq!(role.prompt(), "Prompt");
+    }
+
     #[test]
     fn role_new_no_metadata_has_none_fields() {
         let role = Role::new("test", "Just a prompt");
@@ -909,4 +1031,122 @@ Input 1
 
         assert_eq!(parse_structure_prompt(prompt), (prompt, vec![]));
     }
+
+    fn fixture(entries: &[(&str, &str)]) -> Vec<(String, String)> {
+        entries
+            .iter()
+            .map(|(name, content)| (name.to_string(), content.to_string()))
+            .collect()
+    }
+
+    fn hooks_fixture_dir(label: &str) -> PathBuf {
+        let dir = temp_file(label, "");
+        create_dir_all(&dir).unwrap();
+        dir.join("hooks")
+    }
+
+    #[test]
+    fn role_hooks_install_writes_scripts_and_manifest() {
+        let dir = hooks_fixture_dir("role-hooks-install-");
+
+        install_and_reconcile_role_hooks(&dir, &fixture(&[("a.sh", "#!/bin/sh\n")]), false)
+            .unwrap();
+
+        assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "#!/bin/sh\n");
+        assert_eq!(
+            read_to_string(dir.join(builtin_manifest::BUILTIN_MANIFEST_FILE)).unwrap(),
+            "a.sh\n"
+        );
+        #[cfg(unix)]
+        {
+            use std::os::unix::fs::PermissionsExt;
+            let mode = fs::metadata(dir.join("a.sh")).unwrap().permissions().mode();
+            assert_eq!(mode & 0o777, 0o755, "role hook scripts install executable");
+            let manifest_mode = fs::metadata(dir.join(builtin_manifest::BUILTIN_MANIFEST_FILE))
+                .unwrap()
+                .permissions()
+                .mode();
+            assert_eq!(
+                manifest_mode & 0o111,
+                0,
+                "the manifest must never be executable"
+            );
+        }
+        let _ = fs::remove_dir_all(dir.parent().unwrap());
+    }
+
+    #[test]
+    fn role_hooks_install_overwrites_only_with_force() {
+        let dir = hooks_fixture_dir("role-hooks-force-");
+        let shipped = fixture(&[("a.sh", "new content\n")]);
+        create_dir_all(&dir).unwrap();
+        fs::write(dir.join("a.sh"), "SENTINEL").unwrap();
+
+        install_and_reconcile_role_hooks(&dir, &shipped, false).unwrap();
+        assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "SENTINEL");
+
+        install_and_reconcile_role_hooks(&dir, &shipped, true).unwrap();
+        assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "new content\n");
+        let _ = fs::remove_dir_all(dir.parent().unwrap());
+    }
+
+    #[test]
+    fn role_hooks_reconcile_removes_dropped_hook_and_keeps_user_files() {
+        let dir = hooks_fixture_dir("role-hooks-reconcile-");
+
+        install_and_reconcile_role_hooks(
+            &dir,
+            &fixture(&[("keep.sh", "#!/bin/sh\n"), ("drop.sh", "#!/bin/sh\n")]),
+            false,
+        )
+        .unwrap();
+        fs::write(dir.join("user.sh"), "user-owned").unwrap();
+
+        install_and_reconcile_role_hooks(&dir, &fixture(&[("keep.sh", "#!/bin/sh\n")]), false)
+            .unwrap();
+
+        assert!(
+            !dir.join("drop.sh").exists(),
+            "dropped builtin hook removed"
+        );
+        assert!(dir.join("keep.sh").exists());
+        assert!(dir.join("user.sh").exists(), "user file survives reconcile");
+        assert_eq!(
+            read_to_string(dir.join(builtin_manifest::BUILTIN_MANIFEST_FILE)).unwrap(),
+            "keep.sh\n"
+        );
+        let _ = fs::remove_dir_all(dir.parent().unwrap());
+    }
+
+    #[test]
+    fn role_hooks_never_claim_a_preexisting_user_file() {
+        let dir = hooks_fixture_dir("role-hooks-unclaimed-");
+        create_dir_all(&dir).unwrap();
+        fs::write(dir.join("a.sh"), "user-owned").unwrap();
+
+        install_and_reconcile_role_hooks(&dir, &fixture(&[("a.sh", "#!/bin/sh\n")]), false)
+            .unwrap();
+        assert!(
+            !dir.join(builtin_manifest::BUILTIN_MANIFEST_FILE).exists(),
+            "a skipped pre-existing file must not be claimed by the manifest"
+        );
+
+        install_and_reconcile_role_hooks(&dir, &[], false).unwrap();
+        assert_eq!(
+            read_to_string(dir.join("a.sh")).unwrap(),
+            "user-owned",
+            "the user file survives the hook being dropped from the embed"
+        );
+        let _ = fs::remove_dir_all(dir.parent().unwrap());
+    }
+
+    #[test]
+    fn role_hooks_empty_shipped_set_creates_nothing() {
+        let dir = hooks_fixture_dir("role-hooks-empty-");
+
+        install_and_reconcile_role_hooks(&dir, &[], false).unwrap();
+
+        assert!(!dir.exists(), "an empty shipped set must not create hooks/");
+        let _ = fs::remove_dir_all(dir.parent().unwrap());
+    }
 }

src/config/session.rs

@@ -3,6 +3,7 @@ use super::todo::TodoList;
 use super::*;
 
 use crate::client::{Message, MessageContent, MessageRole, TokenUsage};
+use crate::hooks::HooksMap;
 use crate::render::MarkdownRender;
 
 use anyhow::{Context, Result, bail};
@@ -113,6 +114,8 @@ pub struct Session {
     #[serde(skip)]
     role_prompt: String,
     #[serde(skip)]
+    role_hooks: Option<HooksMap>,
+    #[serde(skip)]
     name: String,
     #[serde(skip)]
     path: Option<String>,
@@ -193,6 +196,7 @@ impl Session {
             && let Ok(role) = ctx.retrieve_role(app, role_name)
         {
             session.role_prompt = role.prompt().to_string();
+            session.role_hooks = role.hooks().cloned();
         }
 
         session.update_tokens();
@@ -254,6 +258,13 @@ impl Session {
         self.role_name.as_deref()
     }
 
+    /// Hooks of the role this session holds. `set_role` snapshots them
+    /// because only the frontmatter-stripped role prompt is persisted;
+    /// `load_from_ctx` restores them by re-reading the role file on resume.
+    pub fn role_hooks(&self) -> Option<&HooksMap> {
+        self.role_hooks.as_ref()
+    }
+
     pub fn dirty(&self) -> bool {
         self.dirty
     }
@@ -561,6 +572,7 @@ impl Session {
         self.model = role.model().clone();
         self.role_name = convert_option_string(role.name());
         self.role_prompt = role.prompt().to_string();
+        self.role_hooks = role.hooks().cloned();
         self.dirty = true;
         self.update_tokens();
     }
@@ -568,11 +580,13 @@ impl Session {
     pub fn clear_role(&mut self) {
         self.role_name = None;
         self.role_prompt.clear();
+        self.role_hooks = None;
     }
 
     pub fn sync_agent(&mut self, agent: &Agent) {
         self.role_name = None;
         self.role_prompt = agent.interpolated_instructions();
+        self.role_hooks = None;
         self.agent_variables = agent.variables().clone();
         self.agent_instructions = self.role_prompt.clone();
         if let Some(threshold) = agent.compression_threshold() {
@@ -1111,6 +1125,25 @@ mod tests {
         assert!(!session.dirty());
     }
 
+    #[test]
+    fn set_role_captures_and_clear_role_drops_role_hooks() {
+        let content = "---\nhooks:\n  turn.completed:\n    - name: role-probe\n      command: role-cmd\n---\nPrompt";
+        let mut session = Session::default();
+
+        session.set_role(Role::new("hooked", content));
+        let hooks = session.role_hooks().expect("set_role must snapshot hooks");
+        assert_eq!(hooks["turn.completed"][0].name, "role-probe");
+
+        session.clear_role();
+        assert!(session.role_hooks().is_none());
+
+        session.set_role(Role::new("plain", "No frontmatter"));
+        assert!(
+            session.role_hooks().is_none(),
+            "a role without hooks must not leave a stale snapshot"
+        );
+    }
+
     fn push_interrupted_turn(session: &mut Session) {
         session.messages.push(Message::new(
             MessageRole::User,
@@ -1233,6 +1266,37 @@ mod tests {
         assert!(!yaml.contains("token_usage"));
     }
 
+    #[test]
+    fn session_role_hooks_is_not_serialized() {
+        let content = "---\nhooks:\n  turn.completed:\n    - name: role-probe\n      command: role-cmd\n---\nPrompt";
+        let mut session = Session::default();
+        session.set_role(Role::new("hooked", content));
+        assert!(session.role_hooks().is_some());
+
+        let yaml = serde_yaml::to_string(&session).unwrap();
+        assert!(
+            !yaml.contains("role_hooks"),
+            "the role-hooks snapshot must never reach session YAML"
+        );
+        assert!(
+            !yaml.contains("role-cmd"),
+            "no hook command text may leak into session YAML under any key"
+        );
+    }
+
+    #[test]
+    fn session_deserialization_ignores_injected_role_hooks() {
+        // A session file is attacker-writable data: a `role_hooks:` key
+        // crafted into it must never deserialize into executable hook
+        // config. Hooks are only ever re-read from the role file itself.
+        let yaml = "model: ''\nmessages: []\nrole_hooks:\n  session.started:\n    - name: injected\n      command: touch /tmp/pwned\n";
+        let session: Session = serde_yaml::from_str(yaml).unwrap();
+        assert!(
+            session.role_hooks().is_none(),
+            "injected role_hooks in session YAML must be ignored"
+        );
+    }
+
     #[test]
     fn session_cost_accumulates_and_survives_yaml_round_trip() {
         let mut session = Session::default();

src/function/agents.rs

@@ -4,8 +4,9 @@ use crate::client::{Model, ModelType, call_chat_completions};
 use crate::config::{
     Agent, AgentVariable, AgentVariables, AppState, Input, RequestContext, Role, RoleLike,
     default_max_agent_depth, effective_max_concurrent_jobs, jobs_enabled,
-    list_agents_with_descriptions, load_agent_variables,
+    list_agents_with_descriptions, load_agent_variables, paths,
 };
+use crate::hooks::{self, HookEvent, ResolvedHook};
 use crate::supervisor::mailbox::{Envelope, EnvelopePayload, Inbox, PeerRegistry, graph_agent_id};
 use crate::supervisor::notification::agent_notification;
 use crate::supervisor::{AgentExitStatus, AgentHandle, AgentResult, Supervisor, TaskKind};
@@ -14,7 +15,7 @@ use crate::utils::{AbortSignal, create_abort_signal, wait_abort_signal, wait_use
 use crate::graph;
 use crate::repl::DEFAULT_CONTINUATION_PROMPT;
 use anyhow::{Context, Result, anyhow, bail};
-use chrono::Utc;
+use chrono::{SecondsFormat, Utc};
 use indexmap::IndexMap;
 use log::{debug, warn};
 use parking_lot::RwLock;
@@ -996,6 +997,86 @@ fn sync_agent_functions_to_ctx(ctx: &mut RequestContext) -> Result<()> {
     Ok(())
 }
 
+/// Mirrors the base-env contract `hooks::fire` assembles from a live context,
+/// for detached call sites that dispatch pre-resolved hook snapshots after
+/// the context they were resolved from is gone. The names are captured by
+/// the caller when it takes the snapshot; the timestamp is taken here, at
+/// fire time, so it reflects when the event actually happened.
+pub(crate) fn hook_base_envs(
+    event: HookEvent,
+    session_name: Option<&str>,
+    agent_name: Option<&str>,
+) -> Vec<(String, String)> {
+    let mut envs = vec![
+        ("COYOTE_EVENT".to_string(), event.as_str().to_string()),
+        (
+            "COYOTE_CONFIG_DIR".to_string(),
+            paths::config_dir().display().to_string(),
+        ),
+        (
+            "COYOTE_EVENT_TIMESTAMP".to_string(),
+            Utc::now().to_rfc3339_opts(SecondsFormat::Secs, true),
+        ),
+    ];
+    if let Some(name) = session_name {
+        envs.push(("COYOTE_SESSION_ID".to_string(), name.to_string()));
+    }
+    if let Some(name) = agent_name {
+        envs.push(("COYOTE_AGENT_NAME".to_string(), name.to_string()));
+    }
+    envs
+}
+
+/// Pre-resolved `agent.completed`/`agent.failed` snapshots for a spawned
+/// agent's result arms, captured from the child context before the spawn
+/// task takes ownership of it. Resolving against the child keeps global
+/// hooks gated by the child's own whitelist, the same gate every other
+/// event fired from the child's context goes through.
+struct SpawnResultHooks {
+    completed: Vec<ResolvedHook>,
+    failed: Vec<ResolvedHook>,
+    session_name: Option<String>,
+    agent_id: String,
+    agent_name: String,
+}
+
+impl SpawnResultHooks {
+    fn resolve(child_ctx: &RequestContext, agent_id: &str, agent_name: &str) -> Self {
+        Self {
+            completed: child_ctx.resolved_hooks(HookEvent::AgentCompleted),
+            failed: child_ctx.resolved_hooks(HookEvent::AgentFailed),
+            session_name: child_ctx
+                .session
+                .as_ref()
+                .map(|session| session.name().to_string()),
+            agent_id: agent_id.to_string(),
+            agent_name: agent_name.to_string(),
+        }
+    }
+
+    /// Fires `agent.completed`, or `agent.failed` when `error` is given.
+    fn fire(self, error: Option<&str>) {
+        let mut extras = vec![
+            ("COYOTE_AGENT_ID", self.agent_id),
+            ("COYOTE_AGENT_NAME", self.agent_name.clone()),
+        ];
+        let (event, resolved) = match error {
+            None => (HookEvent::AgentCompleted, self.completed),
+            Some(error) => {
+                extras.push(("COYOTE_AGENT_ERROR", error.to_string()));
+                (HookEvent::AgentFailed, self.failed)
+            }
+        };
+        hooks::fire_resolved(
+            event,
+            resolved,
+            hook_base_envs(event, self.session_name.as_deref(), Some(&self.agent_name)),
+            &extras,
+            None,
+        );
+    }
+}
+
 async fn handle_spawn(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
     let agent_name = args
         .get("agent")
@@ -1149,6 +1230,19 @@ async fn handle_spawn(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
 
     debug!("Spawning child agent '{agent_name}' as '{agent_id}'");
 
+    hooks::fire(
+        HookEvent::AgentStarted,
+        &child_ctx,
+        &[
+            ("COYOTE_AGENT_ID", agent_id.clone()),
+            ("COYOTE_AGENT_NAME", agent_name.clone()),
+        ],
+        None,
+    );
+    // Resolved before the spawn: the result arms outlive the child context
+    // the snapshots come from.
+    let result_hooks = SpawnResultHooks::resolve(&child_ctx, &agent_id, &agent_name);
+
     let spawn_agent_id = agent_id.clone();
     let spawn_agent_name = agent_name.clone();
     let spawn_abort = child_abort.clone();
@@ -1173,6 +1267,10 @@ async fn handle_spawn(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
             },
         };
         let success = agent_result.exit_status == AgentExitStatus::Completed;
+        match &agent_result.exit_status {
+            AgentExitStatus::Completed => result_hooks.fire(None),
+            AgentExitStatus::Failed(e) => result_hooks.fire(Some(e)),
+        }
         spawn_notifications.push(agent_notification(
             &agent_result.id,
             &agent_result.agent_name,
@@ -2154,6 +2252,155 @@ mod tests {
         .unwrap();
     }
 
+    /// A graph agent whose graph.yaml wires `agent.*` hooks at its top
+    /// level. With `failing`, the start node references a script that does
+    /// not exist, so the child run fails at runtime — after the spawn seam
+    /// has already fired `agent.started`.
+    fn write_graph_agent_with_hooks(agent_name: &str, marker: &str, failing: bool) {
+        let agent_dir = paths::agent_data_dir(agent_name);
+        create_dir_all(&agent_dir).unwrap();
+        let (start, nodes) = if failing {
+            (
+                "work",
+                "  work:\n    type: script\n    script: missing.sh\n    next: done\n  done:\n    type: end\n    output: done\n",
+            )
+        } else {
+            ("done", "  done:\n    type: end\n    output: done\n")
+        };
+        write(
+            agent_dir.join("graph.yaml"),
+            format!(
+                "name: {agent_name}\n\
+                 start: {start}\n\
+                 settings:\n\
+                 \x20 validate_before_run: false\n\
+                 hooks:\n\
+                 \x20 agent.started:\n\
+                 \x20   - name: {marker}_started\n\
+                 \x20     command: \"true\"\n\
+                 \x20 agent.completed:\n\
+                 \x20   - name: {marker}_completed\n\
+                 \x20     command: \"true\"\n\
+                 \x20 agent.failed:\n\
+                 \x20   - name: {marker}_failed\n\
+                 \x20     command: \"true\"\n\
+                 nodes:\n\
+                 {nodes}"
+            ),
+        )
+        .unwrap();
+    }
+
+    fn hook_captures_named(name: &str) -> Vec<hooks::test_sink::Capture> {
+        hooks::test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name == name)
+            .collect()
+    }
+
+    /// Spawns an agent through the supervisor seam and awaits its spawn
+    /// task, returning the spawn id. The result arms fire their hooks
+    /// before that task returns, so the sink is complete afterwards.
+    fn spawn_and_collect(agent_name: &str) -> String {
+        run_async(async {
+            let mut ctx = ctx_with_supervisor(4, 3);
+            let spawned = handle_spawn(&mut ctx, &json!({"agent": agent_name, "prompt": "hi"}))
+                .await
+                .unwrap();
+            assert_eq!(spawned["status"], "ok", "{spawned}");
+            let id = spawned["id"].as_str().unwrap().to_string();
+            let handle = ctx
+                .supervisor
+                .as_ref()
+                .unwrap()
+                .write()
+                .take(&id)
+                .expect("spawned agent must be registered");
+            handle
+                .join_handle
+                .await
+                .expect("spawn task must not panic")
+                .expect("spawn task must return an AgentResult");
+            id
+        })
+    }
+
+    #[test]
+    #[serial]
+    fn spawned_agent_success_fires_started_and_completed_with_matching_id() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = hooks::test_sink::install();
+        let agent_name = unique_agent_name("test_hook_spawn_ok");
+        write_graph_agent_with_hooks(&agent_name, "t037_spawn_ok", false);
+
+        let id = spawn_and_collect(&agent_name);
+
+        let started = hook_captures_named("t037_spawn_ok_started");
+        assert_eq!(started.len(), 1, "{started:?}");
+        assert_eq!(started[0].envs["COYOTE_EVENT"], "agent.started");
+        assert_eq!(started[0].envs["COYOTE_AGENT_ID"], id);
+        assert_eq!(started[0].envs["COYOTE_AGENT_NAME"], agent_name);
+
+        let completed = hook_captures_named("t037_spawn_ok_completed");
+        assert_eq!(completed.len(), 1, "{completed:?}");
+        assert_eq!(completed[0].envs["COYOTE_EVENT"], "agent.completed");
+        assert_eq!(completed[0].envs["COYOTE_AGENT_ID"], id);
+        assert_eq!(completed[0].envs["COYOTE_AGENT_NAME"], agent_name);
+
+        assert!(hook_captures_named("t037_spawn_ok_failed").is_empty());
+    }
+
+    #[test]
+    #[serial]
+    fn spawned_agent_failure_fires_started_and_failed_with_matching_id() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = hooks::test_sink::install();
+        let agent_name = unique_agent_name("test_hook_spawn_fail");
+        write_graph_agent_with_hooks(&agent_name, "t037_spawn_fail", true);
+
+        let id = spawn_and_collect(&agent_name);
+
+        let started = hook_captures_named("t037_spawn_fail_started");
+        assert_eq!(started.len(), 1, "{started:?}");
+        assert_eq!(started[0].envs["COYOTE_AGENT_ID"], id);
+
+        let failed = hook_captures_named("t037_spawn_fail_failed");
+        assert_eq!(failed.len(), 1, "{failed:?}");
+        assert_eq!(failed[0].envs["COYOTE_EVENT"], "agent.failed");
+        assert_eq!(failed[0].envs["COYOTE_AGENT_ID"], id);
+        assert!(
+            !failed[0].envs["COYOTE_AGENT_ERROR"].is_empty(),
+            "a failed spawn must carry its error"
+        );
+
+        assert!(hook_captures_named("t037_spawn_fail_completed").is_empty());
+    }
+
+    #[test]
+    fn hook_base_envs_carries_optional_names_only_when_present() {
+        let envs = hook_base_envs(HookEvent::AgentCompleted, None, None);
+        let keys: Vec<&str> = envs.iter().map(|(key, _)| key.as_str()).collect();
+        assert!(keys.contains(&"COYOTE_EVENT"));
+        assert!(keys.contains(&"COYOTE_CONFIG_DIR"));
+        assert!(keys.contains(&"COYOTE_EVENT_TIMESTAMP"));
+        assert!(!keys.contains(&"COYOTE_SESSION_ID"));
+        assert!(!keys.contains(&"COYOTE_AGENT_NAME"));
+        assert!(
+            envs.iter()
+                .any(|(key, value)| key == "COYOTE_EVENT" && value == "agent.completed")
+        );
+
+        let envs = hook_base_envs(HookEvent::AgentFailed, Some("sess"), Some("bot"));
+        assert!(
+            envs.iter()
+                .any(|(key, value)| key == "COYOTE_SESSION_ID" && value == "sess")
+        );
+        assert!(
+            envs.iter()
+                .any(|(key, value)| key == "COYOTE_AGENT_NAME" && value == "bot")
+        );
+    }
+
     fn run_agent_for_graph_error(
         agent_name: &str,
         graph_inputs: Option<HashMap<String, Value>>,

src/function/jobs.rs

@@ -9,6 +9,7 @@ use crate::config::{
     McpRuntime, RequestContext, effective_max_concurrent_jobs, jobs_enabled, paths,
 };
 use crate::graph;
+use crate::hooks::{self, HookEvent, ResolvedHook};
 use crate::mcp::{
     MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX, MCP_INVOKE_META_FUNCTION_NAME_PREFIX,
     MCP_PROMPT_META_FUNCTION_NAME_PREFIX, MCP_READ_META_FUNCTION_NAME_PREFIX,
@@ -53,6 +54,63 @@ pub fn is_agent_task(supervisor: Option<&Arc<RwLock<Supervisor>>>, id: &str) ->
         || supervisor.is_some_and(|sup| sup.read().has_agent(id))
 }
 
+struct JobHookSnapshot {
+    completed: Vec<ResolvedHook>,
+    failed: Vec<ResolvedHook>,
+    session_name: Option<String>,
+    agent_name: Option<String>,
+    job_id: String,
+    tool: String,
+}
+
+impl JobHookSnapshot {
+    fn resolve(ctx: &RequestContext, job_id: &str, tool: &str) -> Self {
+        Self {
+            completed: ctx.resolved_hooks(HookEvent::JobCompleted),
+            failed: ctx.resolved_hooks(HookEvent::JobFailed),
+            session_name: ctx
+                .session
+                .as_ref()
+                .map(|session| session.name().to_string()),
+            agent_name: ctx.agent.as_ref().map(|agent| agent.name().to_string()),
+            job_id: job_id.to_string(),
+            tool: tool.to_string(),
+        }
+    }
+
+    /// Fires `job.completed` or `job.failed`. `fire_resolved` callers supply
+    /// their own base envs; the event name and timestamp are computed here so
+    /// they reflect the actual outcome rather than the moment the snapshot
+    /// was taken.
+    fn fire_terminal(self, success: bool, error: Option<String>) {
+        let (event, resolved) = if success {
+            (HookEvent::JobCompleted, self.completed)
+        } else {
+            (HookEvent::JobFailed, self.failed)
+        };
+
+        if resolved.is_empty() {
+            return;
+        }
+
+        let base_envs = hooks::base_envs_parts(
+            event,
+            self.session_name.as_deref(),
+            self.agent_name.as_deref(),
+        );
+        let mut extras = vec![
+            ("COYOTE_JOB_ID", self.job_id),
+            ("COYOTE_TOOL_NAME", self.tool),
+        ];
+
+        if let Some(error) = error {
+            extras.push(("COYOTE_JOB_ERROR", error));
+        }
+
+        hooks::fire_resolved(event, resolved, base_envs, &extras, None);
+    }
+}
+
 pub struct RingBuf {
     buf: Vec<u8>,
     capacity: usize,
@@ -470,15 +528,27 @@ async fn handle_start(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
         let task_notifications = Arc::clone(&ctx.notification_queue);
         let notify_id = job_id.clone();
         let notify_tool = tool.clone();
+        let hook_snapshot = JobHookSnapshot::resolve(ctx, &job_id, &tool);
+        hooks::fire(
+            HookEvent::JobStarted,
+            ctx,
+            &[
+                ("COYOTE_JOB_ID", job_id.clone()),
+                ("COYOTE_TOOL_NAME", tool.clone()),
+            ],
+            None,
+        );
         tokio::spawn(async move {
             let result = run_mcp_job(job_ctx, server, inner_tool, inner_args).await;
             let success = result.is_ok();
+            let error = result.as_ref().err().map(|err| err.to_string());
             task_state.lock().status = if success {
                 JobStatus::Completed
             } else {
                 JobStatus::Failed
             };
             task_notifications.push(job_notification(&notify_id, &notify_tool, success));
+            hook_snapshot.fire_terminal(success, error);
             result
         })
     } else {
@@ -488,9 +558,26 @@ async fn handle_start(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
         let task_notifications = Arc::clone(&ctx.notification_queue);
         let notify_id = job_id.clone();
         let notify_tool = tool.clone();
+        let hook_snapshot = JobHookSnapshot::resolve(ctx, &job_id, &tool);
+        hooks::fire(
+            HookEvent::JobStarted,
+            ctx,
+            &[
+                ("COYOTE_JOB_ID", job_id.clone()),
+                ("COYOTE_TOOL_NAME", tool.clone()),
+            ],
+            None,
+        );
         tokio::spawn(async move {
             let result = run_process_job(snapshot, Arc::clone(&task_state), task_buf).await;
             let success = matches!(&result, Ok(job_result) if job_result.exit_code == Some(0));
+            let error = (!success).then(|| match &result {
+                Err(err) => err.to_string(),
+                Ok(job_result) => match job_result.exit_code {
+                    Some(code) => format!("exited with code {code}"),
+                    None => "terminated without an exit code".to_string(),
+                },
+            });
             let mut job_state = task_state.lock();
             job_state.pgid = None;
             job_state.status = if success {
@@ -502,6 +589,7 @@ async fn handle_start(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
             drop(job_state);
 
             task_notifications.push(job_notification(&notify_id, &notify_tool, success));
+            hook_snapshot.fire_terminal(success, error);
             result
         })
     };
@@ -3119,4 +3207,190 @@ mod tests {
         );
         assert!(ctx.supervisor.is_none(), "no job may be spawned");
     }
+
+    fn job_hooks_map(marker: &str) -> hooks::HooksMap {
+        ["job.started", "job.completed", "job.failed"]
+            .into_iter()
+            .map(|event| {
+                (
+                    event.to_string(),
+                    vec![hooks::HookDef {
+                        name: marker.to_string(),
+                        command: "true".to_string(),
+                    }],
+                )
+            })
+            .collect()
+    }
+
+    fn job_hooked_ctx(marker: &str) -> RequestContext {
+        let app = app_state_with_config(|config| {
+            config.hooks = job_hooks_map(marker);
+        });
+        RequestContext::new(app, WorkingMode::Cmd)
+    }
+
+    fn job_captures(marker: &str) -> Vec<hooks::test_sink::Capture> {
+        hooks::test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name == marker)
+            .collect()
+    }
+
+    #[cfg(unix)]
+    #[test]
+    #[serial_test::serial]
+    fn job_hooks_fire_started_and_completed() {
+        run_async(async {
+            let marker = "job-hooks-ok-x7x";
+            let mut ctx = job_hooked_ctx(marker);
+            ctx.declared_function_names.insert("echo".into());
+            let _guard = hooks::test_sink::install();
+
+            let started = handle_start(&mut ctx, &json!({"tool": "echo", "arguments": {}}))
+                .await
+                .unwrap();
+            assert_eq!(started["status"], "ok");
+            let job_id = started["job_id"].as_str().unwrap().to_string();
+
+            // `job.started` is dispatched before `handle_start` returns.
+            let captures = job_captures(marker);
+            assert_eq!(captures.len(), 1, "{captures:?}");
+            assert_eq!(captures[0].event, HookEvent::JobStarted);
+            assert_eq!(
+                captures[0].envs.get("COYOTE_JOB_ID").map(String::as_str),
+                Some(job_id.as_str())
+            );
+            assert_eq!(
+                captures[0].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+                Some("echo")
+            );
+
+            let collected = handle_collect(&ctx, &json!({"id": job_id})).await.unwrap();
+            assert_eq!(collected["status"], "completed");
+
+            let captures = job_captures(marker);
+            assert_eq!(captures.len(), 2, "{captures:?}");
+            let completed = &captures[1];
+            assert_eq!(completed.event, HookEvent::JobCompleted);
+            assert_eq!(
+                completed.envs.get("COYOTE_EVENT").map(String::as_str),
+                Some("job.completed")
+            );
+            assert_eq!(
+                completed.envs.get("COYOTE_JOB_ID").map(String::as_str),
+                Some(job_id.as_str())
+            );
+            assert_eq!(
+                completed.envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+                Some("echo")
+            );
+            assert!(completed.envs.contains_key("COYOTE_CONFIG_DIR"));
+            assert!(completed.envs.contains_key("COYOTE_EVENT_TIMESTAMP"));
+            assert!(!completed.envs.contains_key("COYOTE_SESSION_ID"));
+            assert!(!completed.envs.contains_key("COYOTE_JOB_ERROR"));
+        });
+    }
+
+    #[cfg(unix)]
+    #[test]
+    #[serial_test::serial]
+    fn job_hooks_fire_failed_with_job_error() {
+        run_async(async {
+            let marker = "job-hooks-fail-x7x";
+            let mut ctx = job_hooked_ctx(marker);
+            ctx.declared_function_names.insert("false".into());
+            let _guard = hooks::test_sink::install();
+
+            let started = handle_start(&mut ctx, &json!({"tool": "false", "arguments": {}}))
+                .await
+                .unwrap();
+            let job_id = started["job_id"].as_str().unwrap().to_string();
+
+            let collected = handle_collect(&ctx, &json!({"id": job_id})).await.unwrap();
+            assert_eq!(collected["status"], "failed");
+
+            let captures = job_captures(marker);
+            assert_eq!(captures.len(), 2, "{captures:?}");
+            assert_eq!(captures[0].event, HookEvent::JobStarted);
+            let failed = &captures[1];
+            assert_eq!(failed.event, HookEvent::JobFailed);
+            assert_eq!(
+                failed.envs.get("COYOTE_EVENT").map(String::as_str),
+                Some("job.failed")
+            );
+            assert_eq!(
+                failed.envs.get("COYOTE_JOB_ID").map(String::as_str),
+                Some(job_id.as_str())
+            );
+            assert_eq!(
+                failed.envs.get("COYOTE_JOB_ERROR").map(String::as_str),
+                Some("exited with code 1")
+            );
+        });
+    }
+
+    #[test]
+    #[serial_test::serial]
+    fn job_hooks_fire_for_mcp_jobs() {
+        run_async(async {
+            let marker = "job-hooks-mcp-x7x";
+            let mut ctx = job_hooked_ctx(marker);
+            ctx.declared_function_names
+                .insert("mcp_invoke_fixture".into());
+            let fixture = FixtureServer::default();
+            let (mut runtime, _server) = fixture_runtime(fixture).await;
+            let mut filter = ToolFilter::default();
+            filter.push_layer(LayerSource::Global, &[]);
+            runtime.tool_filters.insert("fixture".to_string(), filter);
+            ctx.tool_scope.mcp_runtime = runtime;
+            let _guard = hooks::test_sink::install();
+
+            let started = handle_start(
+                &mut ctx,
+                &json!({"tool": "mcp_invoke_fixture", "arguments": {"tool": "dup"}}),
+            )
+            .await
+            .unwrap();
+            let job_id = started["job_id"].as_str().unwrap().to_string();
+
+            let collected = handle_collect(&ctx, &json!({"id": job_id})).await.unwrap();
+            assert_eq!(collected["status"], "failed");
+
+            let captures = job_captures(marker);
+            assert_eq!(captures.len(), 2, "{captures:?}");
+            assert_eq!(captures[0].event, HookEvent::JobStarted);
+            assert_eq!(
+                captures[0].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+                Some("mcp_invoke_fixture")
+            );
+            let failed = &captures[1];
+            assert_eq!(failed.event, HookEvent::JobFailed);
+            assert!(
+                failed
+                    .envs
+                    .get("COYOTE_JOB_ERROR")
+                    .unwrap()
+                    .contains("dup not found"),
+                "{failed:?}"
+            );
+        });
+    }
+
+    #[test]
+    #[serial_test::serial]
+    fn rejected_job_start_fires_no_hooks() {
+        let marker = "job-hooks-rejected-x7x";
+        let mut ctx = job_hooked_ctx(marker);
+        let _guard = hooks::test_sink::install();
+
+        let result = run_async(handle_start(
+            &mut ctx,
+            &json!({"tool": "undeclared_tool", "arguments": {}}),
+        ))
+        .unwrap();
+
+        assert_eq!(result["status"], "error");
+        assert!(job_captures(marker).is_empty());
+    }
 }

src/function/mod.rs

@@ -17,6 +17,7 @@ use crate::{
 
 use crate::config::ensure_parent_exists;
 use crate::config::paths;
+use crate::hooks::{self, HookEvent};
 use crate::mcp::{
     MCP_DESCRIBE_META_FUNCTION_NAME_PREFIX, MCP_INVOKE_META_FUNCTION_NAME_PREFIX,
     MCP_META_FUNCTION_PREFIXES, MCP_PROMPT_META_FUNCTION_NAME_PREFIX,
@@ -1539,6 +1540,22 @@ impl ToolCall {
     }
 
     pub async fn eval(&self, ctx: &mut RequestContext) -> Result<Value> {
+        let result = self.eval_inner(ctx).await;
+        if let Err(err) = &result {
+            hooks::fire(
+                HookEvent::ToolFailed,
+                ctx,
+                &[
+                    ("COYOTE_TOOL_NAME", self.name.clone()),
+                    ("COYOTE_TOOL_ERROR", err.to_string()),
+                ],
+                None,
+            );
+        }
+        result
+    }
+
+    async fn eval_inner(&self, ctx: &mut RequestContext) -> Result<Value> {
         let agent = ctx.agent.clone();
         let functions = ctx.tool_scope.functions.clone();
         let current_depth = ctx.current_depth;
@@ -1566,7 +1583,8 @@ impl ToolCall {
             );
         };
 
-        cmd_args.push(json_data.to_string());
+        let args_json = json_data.to_string();
+        cmd_args.push(args_json.clone());
 
         if (*IS_STDOUT_TERMINAL || *SHOW_TOOL_CALLS)
             && current_depth == 0
@@ -1575,6 +1593,14 @@ impl ToolCall {
             println!("{}", format_call_log(&cmd_name, &cmd_args, &json_data));
         }
 
+        hooks::fire(
+            HookEvent::ToolStarted,
+            ctx,
+            &[("COYOTE_TOOL_NAME", self.name.clone())],
+            Some(args_json.clone()),
+        );
+        let tool_started_at = Instant::now();
+
         let output = match cmd_name.as_str() {
             _ if cmd_name.starts_with(MCP_SEARCH_META_FUNCTION_NAME_PREFIX) => {
                 Self::search_mcp_tools(ctx, &cmd_name, &json_data)
@@ -1699,6 +1725,38 @@ impl ToolCall {
             },
         };
 
+        match output.get("tool_call_error") {
+            Some(error) => {
+                let error = error
+                    .as_str()
+                    .map(str::to_string)
+                    .unwrap_or_else(|| error.to_string());
+                hooks::fire(
+                    HookEvent::ToolFailed,
+                    ctx,
+                    &[
+                        ("COYOTE_TOOL_NAME", self.name.clone()),
+                        ("COYOTE_TOOL_ERROR", error),
+                    ],
+                    Some(args_json),
+                );
+            }
+            None => {
+                hooks::fire(
+                    HookEvent::ToolCompleted,
+                    ctx,
+                    &[
+                        ("COYOTE_TOOL_NAME", self.name.clone()),
+                        (
+                            "COYOTE_TOOL_DURATION_MS",
+                            tool_started_at.elapsed().as_millis().to_string(),
+                        ),
+                    ],
+                    Some(args_json),
+                );
+            }
+        }
+
         Ok(output)
     }
 
@@ -2518,13 +2576,16 @@ fn polyfill_cmd_name<T: AsRef<Path>>(cmd_name: &str, bin_dir: &[T]) -> String {
     cmd_name
 }
 
-// Polling tools are expected to repeat; recording them would also let them
+// Polling tools are expected to repeat with identical arguments (status probes,
-// break up detection of a real loop in the calls they interleave with.
+// list views, inbox checks); recording them would also let them break up
-const LOOP_TRACKER_EXEMPT_TOOLS: [&str; 4] = [
+// detection of a real loop in the calls they interleave with.
+const LOOP_TRACKER_EXEMPT_TOOLS: [&str; 6] = [
     "job__check",
     "job__list",
     "agent__check",
     "agent__list_running",
+    "agent__task_list",
+    "agent__check_inbox",
 ];
 
 fn is_loop_tracker_exempt(name: &str) -> bool {
@@ -3328,10 +3389,12 @@ mod tests {
             "job__list",
             "agent__check",
             "agent__list_running",
+            "agent__task_list",
+            "agent__check_inbox",
         ]
         .into_iter()
         .collect();
-        assert_eq!(LOOP_TRACKER_EXEMPT_TOOLS.len(), 4);
+        assert_eq!(LOOP_TRACKER_EXEMPT_TOOLS.len(), 6);
         assert_eq!(actual, expected);
     }
 
@@ -3368,6 +3431,29 @@ mod tests {
         assert!(tracker.check_loop(&x).is_some());
     }
 
+    /// Zero-argument polls (`agent__check_inbox`, `agent__task_list`) are
+    /// byte-identical on every call, so the protocol-mandated "check your inbox
+    /// after each round" cadence must never read as a loop — even when the
+    /// polls are back-to-back and well past the repeat threshold.
+    #[test]
+    fn tracker_zero_arg_polls_never_trip_even_when_consecutive() {
+        for name in ["agent__check_inbox", "agent__task_list"] {
+            let mut tracker = ToolCallTracker::default();
+            let poll = call_with_args(name, json!({}));
+            for _ in 0..10 {
+                assert!(
+                    tracker.check_loop(&poll).is_none(),
+                    "{name} must never trip the loop tracker"
+                );
+                tracker.record_call(poll.clone());
+            }
+            assert!(
+                tracker.last_calls.is_empty(),
+                "{name} must not be recorded in the call history"
+            );
+        }
+    }
+
     #[test]
     fn tracker_non_exempt_behavior_unchanged() {
         let mut tracker = ToolCallTracker::default();
@@ -5243,4 +5329,277 @@ mod tests {
             assert!(err.starts_with(expected), "{name}: {err}");
         }
     }
+
+    fn tool_hooks_map(marker: &str) -> hooks::HooksMap {
+        ["tool.started", "tool.completed", "tool.failed"]
+            .into_iter()
+            .map(|event| {
+                (
+                    event.to_string(),
+                    vec![hooks::HookDef {
+                        name: marker.to_string(),
+                        command: "true".to_string(),
+                    }],
+                )
+            })
+            .collect()
+    }
+
+    fn ctx_with_tool_hooks(marker: &str, update: impl FnOnce(&mut AppConfig)) -> RequestContext {
+        let mut app = AppState::test_default();
+        let mut config = AppConfig {
+            hooks: tool_hooks_map(marker),
+            ..Default::default()
+        };
+        update(&mut config);
+        app.config = Arc::new(config);
+        RequestContext::new(Arc::new(app), WorkingMode::Cmd)
+    }
+
+    fn tool_captures(marker: &str) -> Vec<hooks::test_sink::Capture> {
+        hooks::test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name == marker)
+            .collect()
+    }
+
+    #[test]
+    #[serial]
+    fn eval_fires_started_and_completed_for_builtin_tools() {
+        use crate::hooks::HookEvent;
+        let marker = "tool-hooks-builtin-ok-x7x";
+        let mut ctx = ctx_with_tool_hooks(marker, |config| {
+            config.function_calling_support = true;
+            config.auto_continue = true;
+        });
+        ctx.tool_scope.functions.append_todo_functions();
+        let _guard = hooks::test_sink::install();
+
+        let output =
+            run_async(call_with_args("todo__init", json!({"goal": "g"})).eval(&mut ctx)).unwrap();
+
+        assert_eq!(output["status"], "ok");
+        let captures = tool_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::ToolStarted);
+        assert_eq!(
+            captures[0].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+            Some("todo__init")
+        );
+        assert_eq!(captures[0].payload.as_deref(), Some(r#"{"goal":"g"}"#));
+        assert_eq!(captures[0].cwd, paths::config_dir());
+        assert_eq!(captures[1].event, HookEvent::ToolCompleted);
+        assert!(captures[1].envs.contains_key("COYOTE_TOOL_DURATION_MS"));
+        assert_eq!(captures[1].payload.as_deref(), Some(r#"{"goal":"g"}"#));
+    }
+
+    #[test]
+    #[serial]
+    fn eval_fires_started_and_completed_for_mcp_meta_tools() {
+        use crate::hooks::HookEvent;
+        let marker = "tool-hooks-mcp-ok-x7x";
+        run_async(async {
+            let mut result = CallToolResult::success(vec![ContentBlock::text("hi")]);
+            result.structured_content = Some(json!({"ok": true}));
+            let fixture = FixtureServer {
+                tool_result: Some(result),
+                ..Default::default()
+            };
+            let (runtime, _server) = fixture_runtime(fixture).await;
+            let mut ctx = ctx_with_tool_hooks(marker, |_| {});
+            ctx.tool_scope.mcp_runtime = runtime;
+            ctx.tool_scope
+                .functions
+                .append_mcp_meta_functions(vec![tools_only("fixture")]);
+            let _guard = hooks::test_sink::install();
+
+            let output = call_with_args("mcp_invoke_fixture", json!({"tool": "dup"}))
+                .eval(&mut ctx)
+                .await
+                .unwrap();
+
+            assert_eq!(output["isError"], false);
+            let captures = tool_captures(marker);
+            assert_eq!(captures.len(), 2, "{captures:?}");
+            assert_eq!(captures[0].event, HookEvent::ToolStarted);
+            assert_eq!(
+                captures[0].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+                Some("mcp_invoke_fixture")
+            );
+            assert_eq!(captures[0].payload.as_deref(), Some(r#"{"tool":"dup"}"#));
+            assert_eq!(captures[1].event, HookEvent::ToolCompleted);
+        });
+    }
+
+    #[cfg(unix)]
+    #[test]
+    #[serial]
+    fn eval_fires_started_and_completed_for_external_command_tools() {
+        use crate::hooks::HookEvent;
+        let marker = "tool-hooks-external-ok-x7x";
+        let mut ctx = ctx_with_tool_hooks(marker, |_| {});
+        ctx.tool_scope
+            .functions
+            .append_declaration(FunctionDeclaration {
+                name: "echo".to_string(),
+                description: String::new(),
+                parameters: JsonSchema::default(),
+                agent: false,
+            });
+        let _guard = hooks::test_sink::install();
+
+        let output = run_async(call_with_args("echo", json!({"x": 1})).eval(&mut ctx)).unwrap();
+
+        assert_eq!(output, Value::Null);
+        let captures = tool_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::ToolStarted);
+        assert_eq!(
+            captures[0].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+            Some("echo")
+        );
+        assert_eq!(captures[1].event, HookEvent::ToolCompleted);
+    }
+
+    #[cfg(unix)]
+    #[test]
+    #[serial]
+    fn eval_fires_failed_for_external_command_nonzero_exit() {
+        use crate::hooks::HookEvent;
+        let marker = "tool-hooks-external-fail-x7x";
+        let mut ctx = ctx_with_tool_hooks(marker, |_| {});
+        ctx.tool_scope
+            .functions
+            .append_declaration(FunctionDeclaration {
+                name: "false".to_string(),
+                description: String::new(),
+                parameters: JsonSchema::default(),
+                agent: false,
+            });
+        let _guard = hooks::test_sink::install();
+
+        let output = run_async(call_with_args("false", json!({})).eval(&mut ctx)).unwrap();
+
+        assert!(output["tool_call_error"].is_string());
+        let captures = tool_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::ToolStarted);
+        assert_eq!(captures[1].event, HookEvent::ToolFailed);
+        assert!(
+            captures[1]
+                .envs
+                .get("COYOTE_TOOL_ERROR")
+                .unwrap()
+                .contains("exited with code 1")
+        );
+        assert!(!captures[1].envs.contains_key("COYOTE_TOOL_DURATION_MS"));
+    }
+
+    #[test]
+    #[serial]
+    fn eval_fires_failed_on_error_shaped_output_with_identical_result() {
+        use crate::hooks::HookEvent;
+        let marker = "tool-hooks-error-shape-x7x";
+        // Default config leaves todo tools disabled, so the handler bails
+        // and eval shapes the failure as a `tool_call_error` output.
+        let mut hooked = ctx_with_tool_hooks(marker, |_| {});
+        hooked.tool_scope.functions.append_todo_functions();
+        let mut plain = RequestContext::new(Arc::new(AppState::test_default()), WorkingMode::Cmd);
+        plain.tool_scope.functions.append_todo_functions();
+        let call = call_with_args("todo__done", json!({}));
+        let _guard = hooks::test_sink::install();
+
+        let hooked_output = run_async(call.eval(&mut hooked)).unwrap();
+        let plain_output = run_async(call.eval(&mut plain)).unwrap();
+
+        assert_eq!(
+            hooked_output.to_string(),
+            plain_output.to_string(),
+            "hooks must not change the tool result"
+        );
+        let error = hooked_output["tool_call_error"].as_str().unwrap();
+        assert!(error.starts_with("Todo tool failed:"), "{error}");
+        let captures = tool_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::ToolStarted);
+        assert_eq!(captures[1].event, HookEvent::ToolFailed);
+        assert_eq!(
+            captures[1]
+                .envs
+                .get("COYOTE_TOOL_ERROR")
+                .map(String::as_str),
+            Some(error)
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn eval_fires_hooks_with_exact_user_prefixed_tool_name() {
+        use crate::hooks::HookEvent;
+        let marker = "tool-hooks-user-x7x";
+        let mut ctx = ctx_with_tool_hooks(marker, |_| {});
+        ctx.tool_scope.functions.append_user_interaction_functions();
+        let _guard = hooks::test_sink::install();
+
+        let output = run_async(call_with_args("user__confirm", json!({})).eval(&mut ctx)).unwrap();
+
+        // Without a question the user handler errors before prompting, so the
+        // error-shaped output must fire started + failed with the exact name.
+        let error = output["tool_call_error"].as_str().unwrap();
+        assert!(error.starts_with("User interaction failed"), "{error}");
+        let captures = tool_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::ToolStarted);
+        assert_eq!(
+            captures[0].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+            Some("user__confirm")
+        );
+        assert_eq!(captures[1].event, HookEvent::ToolFailed);
+        assert_eq!(
+            captures[1].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+            Some("user__confirm")
+        );
+        assert_eq!(
+            captures[1]
+                .envs
+                .get("COYOTE_TOOL_ERROR")
+                .map(String::as_str),
+            Some(error)
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn eval_err_fires_failed_without_started_and_identical_error() {
+        use crate::hooks::HookEvent;
+        let marker = "tool-hooks-eval-err-x7x";
+        let mut hooked = ctx_with_tool_hooks(marker, |_| {});
+        let mut plain = RequestContext::new(Arc::new(AppState::test_default()), WorkingMode::Cmd);
+        let call = call_with_args("nonexistent_tool", json!({}));
+        let _guard = hooks::test_sink::install();
+
+        let hooked_err = run_async(call.eval(&mut hooked)).unwrap_err();
+        let plain_err = run_async(call.eval(&mut plain)).unwrap_err();
+
+        assert_eq!(
+            hooked_err.to_string(),
+            plain_err.to_string(),
+            "hooks must not change the error"
+        );
+        let captures = tool_captures(marker);
+        assert_eq!(captures.len(), 1, "{captures:?}");
+        assert_eq!(captures[0].event, HookEvent::ToolFailed);
+        assert_eq!(
+            captures[0].envs.get("COYOTE_TOOL_NAME").map(String::as_str),
+            Some("nonexistent_tool")
+        );
+        assert!(
+            captures[0]
+                .envs
+                .get("COYOTE_TOOL_ERROR")
+                .unwrap()
+                .contains("Unexpected call")
+        );
+        assert!(captures[0].payload.is_none());
+    }
 }

src/graph/agent.rs

@@ -6,6 +6,7 @@ use super::types::AgentNode;
 use super::wall_clock;
 use crate::config::RequestContext;
 use crate::function::agents::run_agent_for_graph;
+use crate::hooks::{self, HookEvent};
 use crate::supervisor::mailbox::{Inbox, PeerRegistry};
 use crate::utils::create_abort_signal;
 use anyhow::{Context, Error, Result, anyhow};
@@ -35,6 +36,11 @@ impl AgentNodeExecutor {
         parent_ctx: &mut RequestContext,
         retire_peer_on_return: bool,
     ) -> Result<AgentExecutionOutcome> {
+        let agent_hook_id = parent_ctx
+            .peer_assignment
+            .as_ref()
+            .map(|(id, _)| id.clone())
+            .unwrap_or_else(|| node_id.to_string());
         let result = run(
             node_id,
             node,
@@ -43,6 +49,18 @@ impl AgentNodeExecutor {
             retire_peer_on_return,
         )
         .await;
+        if let Err(e) = &result {
+            hooks::fire(
+                HookEvent::AgentFailed,
+                parent_ctx,
+                &[
+                    ("COYOTE_AGENT_ID", agent_hook_id),
+                    ("COYOTE_AGENT_NAME", node.agent.clone()),
+                    ("COYOTE_AGENT_ERROR", format!("{e:#}")),
+                ],
+                None,
+            );
+        }
         outcome_from(node_id, node, state_manager, result)
     }
 }

src/graph/executor.rs

@@ -1,6 +1,6 @@
 use super::agent::{AgentExecutionOutcome, AgentNodeExecutor};
 use super::llm::{LlmExecutionOutcome, LlmNodeExecutor};
-use super::logging::{GraphLogger, narrate_node_complete, narrate_node_failed};
+use super::logging::{GraphLogger, narrate_node_complete, narrate_node_failed, node_type_label};
 use super::map::MapNodeExecutor;
 use super::rag::RagNodeExecutor;
 use super::script::ScriptExecutor;
@@ -11,6 +11,8 @@ use super::user_interaction::{ApprovalNodeExecutor, InputNodeExecutor};
 use super::validator::{AgentValidationContext, GraphValidator};
 use super::wall_clock;
 use crate::config::{AgentVariable, AgentVariables, RenderMode, RequestContext};
+use crate::function::agents::hook_base_envs;
+use crate::hooks::{self, HookEvent, ResolvedHook};
 use crate::supervisor::mailbox::{Inbox, PeerAssignment, PeerRegistry, graph_agent_id};
 use crate::utils::{AbortSignal, wait_abort_signal, wait_user_interrupt};
 use anyhow::{Context, Result, anyhow, bail};
@@ -234,6 +236,16 @@ impl GraphExecutor {
                     })?
                     .clone();
                 logger.node_start(&node, in_super_step);
+                let node_hooks = NodeHookEmitter::resolve(ctx, node_id, node_type_label(&node));
+                hooks::fire(
+                    HookEvent::GraphNodeStarted,
+                    ctx,
+                    &[
+                        ("COYOTE_NODE_ID", node_id.clone()),
+                        ("COYOTE_NODE_TYPE", node_hooks.node_type.to_string()),
+                    ],
+                    None,
+                );
                 let branch_state = state.fork_for_branch_state();
                 let mut branch_ctx = ctx.fork_for_branch();
                 let mut peer_id: Option<String> = None;
@@ -281,6 +293,7 @@ impl GraphExecutor {
                             "aborted",
                             in_super_step,
                         );
+                        node_hooks.failed(Duration::default(), "aborted");
                         return (
                             current.clone(),
                             branch_state,
@@ -315,6 +328,7 @@ impl GraphExecutor {
                                 route.as_deref(),
                                 in_super_step,
                             );
+                            node_hooks.completed(elapsed, route.as_deref());
                         }
                         Ok(StepResult::End(_)) => {
                             narrate_node_complete(
@@ -324,6 +338,7 @@ impl GraphExecutor {
                                 Some("END"),
                                 in_super_step,
                             );
+                            node_hooks.completed(elapsed, Some("END"));
                         }
                         Err(e) => {
                             narrate_node_failed(
@@ -333,6 +348,7 @@ impl GraphExecutor {
                                 &e.to_string(),
                                 in_super_step,
                             );
+                            node_hooks.failed(elapsed, &e.to_string());
                         }
                     }
                     (current, state, result, elapsed)
@@ -498,6 +514,67 @@ fn provision_frontier_peers(
     (Some(registry), assignments)
 }
 
+struct NodeHookEmitter {
+    completed: Vec<ResolvedHook>,
+    failed: Vec<ResolvedHook>,
+    session_name: Option<String>,
+    agent_name: Option<String>,
+    node_id: String,
+    node_type: &'static str,
+}
+
+impl NodeHookEmitter {
+    fn resolve(ctx: &RequestContext, node_id: &str, node_type: &'static str) -> Self {
+        Self {
+            completed: ctx.resolved_hooks(HookEvent::GraphNodeCompleted),
+            failed: ctx.resolved_hooks(HookEvent::GraphNodeFailed),
+            session_name: ctx
+                .session
+                .as_ref()
+                .map(|session| session.name().to_string()),
+            agent_name: ctx.agent.as_ref().map(|agent| agent.name().to_string()),
+            node_id: node_id.to_string(),
+            node_type,
+        }
+    }
+
+    fn extras(&self, elapsed: Duration) -> Vec<(&'static str, String)> {
+        vec![
+            ("COYOTE_NODE_ID", self.node_id.clone()),
+            ("COYOTE_NODE_TYPE", self.node_type.to_string()),
+            ("COYOTE_NODE_DURATION_MS", elapsed.as_millis().to_string()),
+        ]
+    }
+
+    fn dispatch(&self, event: HookEvent, resolved: &[ResolvedHook], extras: &[(&str, String)]) {
+        hooks::fire_resolved(
+            event,
+            resolved.to_vec(),
+            hook_base_envs(
+                event,
+                self.session_name.as_deref(),
+                self.agent_name.as_deref(),
+            ),
+            extras,
+            None,
+        );
+    }
+
+    fn completed(&self, elapsed: Duration, route: Option<&str>) {
+        let mut extras = self.extras(elapsed);
+        if let Some(route) = route {
+            extras.push(("COYOTE_NODE_ROUTE", route.to_string()));
+        }
+        self.dispatch(HookEvent::GraphNodeCompleted, &self.completed, &extras);
+    }
+
+    fn failed(&self, elapsed: Duration, error: &str) {
+        let mut extras = self.extras(elapsed);
+        extras.push(("COYOTE_NODE_ERROR", error.to_string()));
+        self.dispatch(HookEvent::GraphNodeFailed, &self.failed, &extras);
+    }
+}
+
 pub(super) struct TaskCancelGuard(Vec<AbortHandle>);
 
 impl TaskCancelGuard {
@@ -928,6 +1005,8 @@ mod tests {
             max_concurrent_agents: None,
             max_agent_depth: None,
             global_tools: Vec::new(),
+            hooks: Default::default(),
+            global_hooks: Vec::new(),
             mcp_servers: Vec::new(),
             mcp_tools: None,
             skills_enabled: None,
@@ -1048,9 +1127,10 @@ mod tests {
 mod integration_tests {
     use super::*;
     use crate::config::paths;
-    use crate::config::{AppState, WorkingMode};
+    use crate::config::{Agent, AgentConfig, AppConfig, AppState, WorkingMode};
     #[cfg(unix)]
     use crate::function::jobs::RingBuf;
+    use crate::hooks::HookDef;
     #[cfg(unix)]
     use crate::supervisor::{JobHandle, JobResult, JobState, JobStatus, Supervisor, notification};
     use crate::utils::{create_abort_signal, get_env_name, temp_file};
@@ -1066,6 +1146,33 @@ mod integration_tests {
         which::which(name).is_ok()
     }
 
+    fn hooks_config(entries: &[(&str, &str)]) -> hooks::HooksMap {
+        let mut map = hooks::HooksMap::new();
+        for (event, name) in entries {
+            map.entry((*event).to_string()).or_default().push(HookDef {
+                name: (*name).to_string(),
+                command: "true".to_string(),
+            });
+        }
+        map
+    }
+
+    fn ctx_with_global_hooks(hooks: hooks::HooksMap) -> RequestContext {
+        let mut app = AppState::test_default();
+        app.config = Arc::new(AppConfig {
+            hooks,
+            ..Default::default()
+        });
+        RequestContext::new(Arc::new(app), WorkingMode::Cmd)
+    }
+
+    fn hook_captures_named(name: &str) -> Vec<hooks::test_sink::Capture> {
+        hooks::test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name == name)
+            .collect()
+    }
+
     struct TestWorkspace {
         dir: PathBuf,
     }
@@ -1208,6 +1315,364 @@ nodes:
         assert_eq!(result, "held|held");
     }
 
+    /// An agent node that fails but declares a fallback must surface the
+    /// failure to observers as `agent.failed`, fired at the point of
+    /// failure, even though the fallback then converts it into a normal
+    /// node completion that routes to the fallback target — so the same
+    /// node also yields `graph.node.completed`, never `graph.node.failed`.
+    #[tokio::test]
+    async fn agent_node_failure_with_fallback_fires_agent_failed_and_node_completed() {
+        let _sink = hooks::test_sink::install();
+        let mut ctx = ctx_with_global_hooks(hooks_config(&[
+            ("agent.failed", "t037_fb_agent_failed"),
+            ("graph.node.completed", "t037_fb_node_completed"),
+            ("graph.node.failed", "t037_fb_node_failed"),
+        ]));
+        // Forces the agent node to fail before it ever loads the (absent)
+        // agent from disk, keeping the test hermetic.
+        ctx.current_depth = crate::config::default_max_agent_depth();
+
+        let yaml = r#"
+name: t
+settings:
+  validate_before_run: false
+start: worker
+nodes:
+  worker:
+    type: agent
+    agent: missing_agent
+    prompt: p
+    fallback: recover
+    next: done
+  recover:
+    type: end
+    output: recovered
+  done:
+    type: end
+    output: done
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+        let abort = create_abort_signal();
+        let result = GraphExecutor::new(graph, ".")
+            .execute(&mut ctx, abort)
+            .await
+            .unwrap_or_else(|e| panic!("executor failed: {e:#}"));
+        assert_eq!(result, "recovered");
+
+        let agent_failed = hook_captures_named("t037_fb_agent_failed");
+        assert_eq!(agent_failed.len(), 1, "{agent_failed:?}");
+        assert_eq!(agent_failed[0].envs["COYOTE_EVENT"], "agent.failed");
+        assert_eq!(agent_failed[0].envs["COYOTE_AGENT_ID"], "worker");
+        assert_eq!(agent_failed[0].envs["COYOTE_AGENT_NAME"], "missing_agent");
+        assert!(
+            agent_failed[0].envs["COYOTE_AGENT_ERROR"].contains("Max agent depth exceeded"),
+            "{:?}",
+            agent_failed[0].envs
+        );
+
+        let node_completed = hook_captures_named("t037_fb_node_completed");
+        let worker_completed: Vec<_> = node_completed
+            .iter()
+            .filter(|capture| capture.envs["COYOTE_NODE_ID"] == "worker")
+            .collect();
+        assert_eq!(worker_completed.len(), 1, "{node_completed:?}");
+        assert_eq!(worker_completed[0].envs["COYOTE_NODE_TYPE"], "agent");
+        assert_eq!(worker_completed[0].envs["COYOTE_NODE_ROUTE"], "recover");
+
+        let node_failed = hook_captures_named("t037_fb_node_failed");
+        assert!(
+            node_failed
+                .iter()
+                .all(|capture| capture.envs["COYOTE_NODE_ID"] != "worker"),
+            "a node that continues via fallback must not fire graph.node.failed: {node_failed:?}"
+        );
+    }
+
+    /// Two branches running in the same super-step each carry their own
+    /// node metadata, captured task-locally before the branch was spawned;
+    /// the distinct routes prove one branch's metadata never leaks into a
+    /// sibling's events.
+    #[tokio::test]
+    async fn parallel_super_step_branches_fire_per_node_metadata() {
+        if !cmd_available("bash") {
+            eprintln!("skipping: bash not available");
+            return;
+        }
+        let _sink = hooks::test_sink::install();
+        let ws = TestWorkspace::new();
+        for script in [
+            "dispatcher.sh",
+            "worker_a.sh",
+            "worker_b.sh",
+            "sink_a.sh",
+            "sink_b.sh",
+        ] {
+            ws.write_script(script, "#!/bin/bash\necho '{}'\n");
+        }
+        let mut ctx = ctx_with_global_hooks(hooks_config(&[
+            ("graph.node.started", "t037_par_started"),
+            ("graph.node.completed", "t037_par_completed"),
+        ]));
+
+        let yaml = r#"
+name: t
+start: dispatcher
+nodes:
+  dispatcher:
+    type: script
+    script: dispatcher.sh
+    state_updates: {}
+    next: [worker_a, worker_b]
+  worker_a:
+    type: script
+    script: worker_a.sh
+    state_updates: {}
+    next: sink_a
+  worker_b:
+    type: script
+    script: worker_b.sh
+    state_updates: {}
+    next: sink_b
+  sink_a:
+    type: script
+    script: sink_a.sh
+    state_updates: {}
+    next: join
+  sink_b:
+    type: script
+    script: sink_b.sh
+    state_updates: {}
+    next: join
+  join:
+    type: end
+    output: done
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+        let abort = create_abort_signal();
+        let result = GraphExecutor::new(graph, &ws.dir)
+            .execute(&mut ctx, abort)
+            .await
+            .unwrap_or_else(|e| panic!("executor failed: {e:#}"));
+        assert_eq!(result, "done");
+
+        let started = hook_captures_named("t037_par_started");
+        for node_id in [
+            "dispatcher",
+            "worker_a",
+            "worker_b",
+            "sink_a",
+            "sink_b",
+            "join",
+        ] {
+            assert_eq!(
+                started
+                    .iter()
+                    .filter(|capture| capture.envs["COYOTE_NODE_ID"] == node_id)
+                    .count(),
+                1,
+                "exactly one graph.node.started for '{node_id}': {started:?}"
+            );
+        }
+
+        let completed = hook_captures_named("t037_par_completed");
+        let completed_route = |node_id: &str| -> String {
+            let matches: Vec<_> = completed
+                .iter()
+                .filter(|capture| capture.envs["COYOTE_NODE_ID"] == node_id)
+                .collect();
+            assert_eq!(
+                matches.len(),
+                1,
+                "exactly one graph.node.completed for '{node_id}': {completed:?}"
+            );
+            let expected_type = if node_id == "join" { "end" } else { "script" };
+            assert_eq!(matches[0].envs["COYOTE_NODE_TYPE"], expected_type);
+            let duration = &matches[0].envs["COYOTE_NODE_DURATION_MS"];
+            let _: u128 = duration
+                .parse()
+                .unwrap_or_else(|_| panic!("non-numeric duration for '{node_id}': {duration}"));
+            matches[0].envs["COYOTE_NODE_ROUTE"].clone()
+        };
+        assert_eq!(completed_route("dispatcher"), "worker_a, worker_b");
+        assert_eq!(completed_route("worker_a"), "sink_a");
+        assert_eq!(completed_route("worker_b"), "sink_b");
+        assert_eq!(completed_route("sink_a"), "join");
+        assert_eq!(completed_route("sink_b"), "join");
+        assert_eq!(completed_route("join"), "END");
+    }
+
+    /// A graph agent's hooks come from graph.yaml's top level: they resolve
+    /// through the agent scope end-to-end, while a global hook on the same
+    /// event stays gated off because the agent whitelisted nothing.
+    #[tokio::test]
+    async fn graph_agent_hooks_resolve_from_graph_yaml_top_level() {
+        let _sink = hooks::test_sink::install();
+        let mut ctx =
+            ctx_with_global_hooks(hooks_config(&[("graph.node.completed", "t037_gy_global")]));
+
+        let yaml = r#"
+name: hooked_graph
+settings:
+  validate_before_run: false
+start: done
+hooks:
+  graph.node.started:
+    - name: t037_gy_started
+      command: "true"
+  graph.node.completed:
+    - name: t037_gy_completed
+      command: "true"
+nodes:
+  done:
+    type: end
+    output: ok
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+        ctx.agent = Some(Agent::test_new(AgentConfig::from_graph(
+            "hooked_graph",
+            &graph,
+        )));
+
+        let abort = create_abort_signal();
+        let result = GraphExecutor::new(graph, ".")
+            .execute(&mut ctx, abort)
+            .await
+            .unwrap_or_else(|e| panic!("executor failed: {e:#}"));
+        assert_eq!(result, "ok");
+
+        let started = hook_captures_named("t037_gy_started");
+        assert_eq!(started.len(), 1, "{started:?}");
+        assert_eq!(started[0].envs["COYOTE_EVENT"], "graph.node.started");
+        assert_eq!(started[0].envs["COYOTE_NODE_ID"], "done");
+        assert_eq!(started[0].envs["COYOTE_NODE_TYPE"], "end");
+        assert_eq!(started[0].envs["COYOTE_AGENT_NAME"], "hooked_graph");
+
+        let completed = hook_captures_named("t037_gy_completed");
+        assert_eq!(completed.len(), 1, "{completed:?}");
+        assert_eq!(completed[0].envs["COYOTE_NODE_ID"], "done");
+        assert_eq!(completed[0].envs["COYOTE_NODE_ROUTE"], "END");
+        assert_eq!(completed[0].envs["COYOTE_AGENT_NAME"], "hooked_graph");
+
+        assert!(
+            hook_captures_named("t037_gy_global").is_empty(),
+            "an agent context must not run global hooks it did not whitelist"
+        );
+    }
+
+    /// A node that genuinely fails — no fallback to absorb the error — fires
+    /// `graph.node.failed` with the full payload observers rely on: the node's
+    /// id and type, a numeric duration, and the error text, even though the
+    /// failure then propagates out of the executor.
+    #[tokio::test]
+    async fn genuine_node_failure_fires_graph_node_failed_with_payload() {
+        let _sink = hooks::test_sink::install();
+        let mut ctx = ctx_with_global_hooks(hooks_config(&[(
+            "graph.node.failed",
+            "t037_gf_node_failed",
+        )]));
+        // Forces the agent node to fail before it ever loads the (absent)
+        // agent from disk, keeping the test hermetic.
+        ctx.current_depth = crate::config::default_max_agent_depth();
+
+        let yaml = r#"
+name: t
+settings:
+  validate_before_run: false
+start: worker
+nodes:
+  worker:
+    type: agent
+    agent: missing_agent
+    prompt: p
+    next: done
+  done:
+    type: end
+    output: done
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+        let abort = create_abort_signal();
+        let result = GraphExecutor::new(graph, ".")
+            .execute(&mut ctx, abort)
+            .await;
+        let error = result.expect_err("a node failure without a fallback must propagate");
+
+        let failed = hook_captures_named("t037_gf_node_failed");
+        assert_eq!(failed.len(), 1, "{failed:?}");
+        let envs = &failed[0].envs;
+        assert_eq!(envs["COYOTE_EVENT"], "graph.node.failed");
+        assert_eq!(envs["COYOTE_NODE_ID"], "worker");
+        assert_eq!(envs["COYOTE_NODE_TYPE"], "agent");
+        let duration = &envs["COYOTE_NODE_DURATION_MS"];
+        let _: u128 = duration
+            .parse()
+            .unwrap_or_else(|_| panic!("non-numeric duration: {duration}"));
+        assert!(!envs["COYOTE_NODE_ERROR"].is_empty(), "{envs:?}");
+        assert!(
+            format!("{error:#}").contains("Max agent depth exceeded"),
+            "unexpected executor error: {error:#}"
+        );
+    }
+
+    /// A malformed hook definition reaching the executor seam through
+    /// graph.yaml's top level — an entry whose command is blank — degrades
+    /// safely: the node still runs, the malformed hook is skipped with a
+    /// debug log, and a well-formed sibling on the same event still fires.
+    #[tokio::test]
+    async fn malformed_graph_yaml_hook_is_skipped_without_breaking_the_node() {
+        crate::testing::install_warn_collector();
+        let _sink = hooks::test_sink::install();
+        let mut ctx = make_ctx();
+
+        let yaml = r#"
+name: hooked_graph
+settings:
+  validate_before_run: false
+start: done
+hooks:
+  graph.node.completed:
+    - name: t037_mal_empty
+      command: "   "
+    - name: t037_mal_valid
+      command: "true"
+nodes:
+  done:
+    type: end
+    output: ok
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+        ctx.agent = Some(Agent::test_new(AgentConfig::from_graph(
+            "hooked_graph",
+            &graph,
+        )));
+
+        let abort = create_abort_signal();
+        let result = GraphExecutor::new(graph, ".")
+            .execute(&mut ctx, abort)
+            .await
+            .unwrap_or_else(|e| panic!("executor failed: {e:#}"));
+        assert_eq!(result, "ok");
+
+        assert!(
+            hook_captures_named("t037_mal_empty").is_empty(),
+            "a blank-command hook must be skipped, not dispatched"
+        );
+        let valid = hook_captures_named("t037_mal_valid");
+        assert_eq!(valid.len(), 1, "{valid:?}");
+        assert_eq!(valid[0].envs["COYOTE_NODE_ID"], "done");
+
+        let debugs: Vec<String> = crate::testing::debug_messages()
+            .lock()
+            .unwrap_or_else(|poisoned| poisoned.into_inner())
+            .clone();
+        assert!(
+            debugs
+                .iter()
+                .any(|message| message.contains("t037_mal_empty")
+                    && message.contains("empty command")),
+            "expected a debug log for the skipped hook: {debugs:?}"
+        );
+    }
+
     /// Declared variables are seeded into state at run start, so the agent
     /// node's strict prompt interpolation of `{{foo}}` succeeds instead of
     /// bailing with "not found in state". `ctx.agent` is None here, so each

src/graph/map.rs

@@ -497,6 +497,8 @@ mod tests {
             max_concurrent_agents: None,
             max_agent_depth: None,
             global_tools: Vec::new(),
+            hooks: Default::default(),
+            global_hooks: Vec::new(),
             mcp_servers: Vec::new(),
             mcp_tools: None,
             skills_enabled: None,

src/graph/types.rs

@@ -1,4 +1,5 @@
 use crate::config::AgentVariable;
+use crate::hooks::HooksMap;
 use anyhow::Result;
 use indexmap::IndexMap;
 use serde::{Deserialize, Serialize};
@@ -43,6 +44,12 @@ pub struct Graph {
     #[serde(default)]
     pub global_tools: Vec<String>,
 
+    #[serde(default)]
+    pub hooks: HooksMap,
+
+    #[serde(default)]
+    pub global_hooks: Vec<String>,
+
     #[serde(default)]
     pub mcp_servers: Vec<String>,
 
@@ -611,6 +618,52 @@ nodes:
         }
     }
 
+    #[test]
+    fn graph_hooks_and_global_hooks_parse_and_round_trip() {
+        let yaml = r#"
+name: g
+start: e
+hooks:
+  tool.started:
+    - name: notify
+      command: ./hooks/notify.sh
+global_hooks:
+  - tool.started.notify
+nodes:
+  e:
+    id: e
+    type: end
+    output: done
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+
+        assert_eq!(graph.hooks["tool.started"][0].name, "notify");
+        assert_eq!(graph.hooks["tool.started"][0].command, "./hooks/notify.sh");
+        assert_eq!(graph.global_hooks, vec!["tool.started.notify"]);
+
+        let reparsed: Graph =
+            serde_yaml::from_str(&serde_yaml::to_string(&graph).unwrap()).unwrap();
+        assert_eq!(reparsed.hooks, graph.hooks);
+        assert_eq!(reparsed.global_hooks, graph.global_hooks);
+    }
+
+    #[test]
+    fn graph_without_hooks_keys_parses_empty() {
+        let yaml = r#"
+name: g
+start: e
+nodes:
+  e:
+    id: e
+    type: end
+    output: done
+"#;
+        let graph: Graph = serde_yaml::from_str(yaml).unwrap();
+
+        assert!(graph.hooks.is_empty());
+        assert!(graph.global_hooks.is_empty());
+    }
+
     #[test]
     fn agent_node_teammates_parses_and_defaults_false() {
         let yaml = r#"

src/graph/validator.rs

@@ -1459,6 +1459,8 @@ mod tests {
             max_concurrent_agents: None,
             max_agent_depth: None,
             global_tools: Vec::new(),
+            hooks: Default::default(),
+            global_hooks: Vec::new(),
             mcp_servers: Vec::new(),
             mcp_tools: None,
             skills_enabled: None,

src/main.rs

@@ -4,6 +4,7 @@ mod client;
 mod config;
 mod function;
 mod graph;
+mod hooks;
 mod rag;
 mod render;
 mod repl;
@@ -22,7 +23,8 @@ extern crate log;
 
 use crate::cli::Cli;
 use crate::client::{
-    ModelType, call_chat_completions, call_chat_completions_streaming, catalog, list_models, oauth,
+    Client, ModelType, call_chat_completions, call_chat_completions_streaming, catalog,
+    list_models, oauth,
 };
 use crate::config::instructions::WORKSPACE_INSTRUCTIONS_FILE_NAME;
 use crate::config::{
@@ -35,7 +37,7 @@ use crate::config::{memory, paths};
 use crate::function::agents::{GuardrailAction, check_pending_tasks_guardrail};
 use crate::mcp::McpServersConfig;
 use crate::render::{prompt_theme, render_error};
-use crate::repl::Repl;
+use crate::repl::{EXIT_HOOK_DRAIN_TIMEOUT, Repl, TurnBracket};
 use crate::utils::*;
 use crate::vault::{Vault, interpolate_secrets};
 use anyhow::{Context, Result, anyhow, bail};
@@ -386,6 +388,12 @@ async fn run(
         let app = Arc::clone(&ctx.app.config);
         ctx.use_agent(app.as_ref(), agent, session, abort_signal.clone())
             .await?;
+        // The top-level agent bracket does NOT open here: the inspection
+        // flags below (--list-sessions, --info, --macro, --rebuild-rag,
+        // --init-*) return early without running the agent, and an open
+        // bracket on those paths would leak `agent.started` with no
+        // terminal event. It opens at the dispatch sites further down,
+        // where an agent run is actually committed.
     } else {
         let app: Arc<AppConfig> = Arc::clone(&ctx.app.config);
         if let Some(prompt) = &cli.temp_role {
@@ -522,9 +530,17 @@ async fn run(
         return Ok(());
     }
     if cli.execute && !is_repl {
-        let input = create_input(&ctx, text, &cli.file, abort_signal.clone()).await?;
+        // Dispatch committed: open the top-level agent bracket only now,
-        shell_execute(&mut ctx, &SHELL, input, abort_signal.clone()).await?;
+        // past every inspection-flag early return above.
-        return Ok(());
+        ctx.top_level_agent_started();
+        let result = async {
+            let input = create_input(&ctx, text, &cli.file, abort_signal.clone()).await?;
+            shell_execute(&mut ctx, &SHELL, input, abort_signal.clone()).await
+        }
+        .await;
+        ctx.top_level_agent_finished(result.as_ref().err());
+        hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
+        return result;
     }
 
     {
@@ -542,11 +558,23 @@ async fn run(
         return acp::run_acp_server(ctx, abort_signal).await;
     }
 
+    // Dispatch committed (headless directive or REPL): open the top-level
+    // agent bracket only now, past every inspection-flag early return
+    // above. The ACP server stays unbracketed deliberately. The headless
+    // arm closes the bracket below; the REPL closes it at teardown (or on
+    // an interactive agent switch).
+    ctx.top_level_agent_started();
     match is_repl {
         false => {
-            let mut input = create_input(&ctx, text, &cli.file, abort_signal.clone()).await?;
+            let result = async {
-            input.use_embeddings(abort_signal.clone()).await?;
+                let mut input = create_input(&ctx, text, &cli.file, abort_signal.clone()).await?;
-            start_directive(&mut ctx, input, cli.code, abort_signal).await
+                input.use_embeddings(abort_signal.clone()).await?;
+                start_directive(&mut ctx, input, cli.code, abort_signal.clone()).await
+            }
+            .await;
+            ctx.top_level_agent_finished(result.as_ref().err());
+            hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
+            result
         }
         true => {
             if !*IS_STDOUT_TERMINAL {
@@ -563,6 +591,17 @@ async fn start_directive(
     input: Input,
     code_mode: bool,
     abort_signal: AbortSignal,
+) -> Result<()> {
+    let bracket = TurnBracket::enter(ctx);
+    let result = start_directive_inner(ctx, input, code_mode, abort_signal.clone()).await;
+    bracket.finish(ctx, &abort_signal, result)
+}
+
+async fn start_directive_inner(
+    ctx: &mut RequestContext,
+    input: Input,
+    code_mode: bool,
+    abort_signal: AbortSignal,
 ) -> Result<()> {
     let app: Arc<AppConfig> = Arc::clone(&ctx.app.config);
     ctx.session_abort = Some(abort_signal.clone());
@@ -638,22 +677,10 @@ async fn shell_execute(
     abort_signal: AbortSignal,
 ) -> Result<()> {
     let app: Arc<AppConfig> = Arc::clone(&ctx.app.config);
-    let client = input.create_client()?;
+    // Each revision round is its own turn: the recursive 'r' call re-enters.
-    ctx.before_chat_completion(&input)?;
+    let bracket = TurnBracket::enter(ctx);
-    let (eval_str, _) = call_chat_completions(
+    let result = shell_execute_turn(ctx, &input, abort_signal.clone()).await;
-        &input,
+    let (client, eval_str) = bracket.finish(ctx, &abort_signal, result)?;
-        false,
-        true,
-        client.as_ref(),
-        ctx,
-        abort_signal.clone(),
-    )
-    .await?;
-
-    ctx.after_chat_completion(app.as_ref(), &input, &eval_str, &[])?;
-    if eval_str.is_empty() {
-        bail!("No command generated");
-    }
     if app.dry_run {
         app.print_markdown(&eval_str)?;
         return Ok(());
@@ -679,6 +706,8 @@ async fn shell_execute(
                     if code == 0 && app.save_shell_history {
                         let _ = append_to_shell_history(&shell.name, &eval_str, code);
                     }
+                    ctx.top_level_agent_finished(None);
+                    hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
                     process::exit(code);
                 }
                 'r' => {
@@ -726,6 +755,24 @@ async fn shell_execute(
     Ok(())
 }
 
+async fn shell_execute_turn(
+    ctx: &mut RequestContext,
+    input: &Input,
+    abort_signal: AbortSignal,
+) -> Result<(Box<dyn Client>, String)> {
+    let app: Arc<AppConfig> = Arc::clone(&ctx.app.config);
+    let client = input.create_client()?;
+    ctx.before_chat_completion(input)?;
+    let (eval_str, _) =
+        call_chat_completions(input, false, true, client.as_ref(), ctx, abort_signal).await?;
+
+    ctx.after_chat_completion(app.as_ref(), input, &eval_str, &[])?;
+    if eval_str.is_empty() {
+        bail!("No command generated");
+    }
+    Ok((client, eval_str))
+}
+
 async fn create_input(
     ctx: &RequestContext,
     text: Option<String>,

src/repl/mod.rs

@@ -17,6 +17,7 @@ use crate::config::{
 };
 use crate::config::{AssetCategory, paths};
 use crate::function::agents::{GuardrailAction, check_pending_tasks_guardrail};
+use crate::hooks::{self, HookEvent};
 use crate::render::render_error;
 use crate::utils::{
     AbortSignal, SHELL, abortable_run_with_spinner, create_abort_signal, dimmed_text,
@@ -41,11 +42,58 @@ use reedline::{
 use reedline::{MenuBuilder, Signal};
 use std::collections::HashMap;
 use std::sync::LazyLock;
+use std::time::Duration;
 use std::{env, process, sync::Arc};
 use tokio::task;
 
 const MENU_NAME: &str = "completion_menu";
 
+/// Bounded wait applied at process-exit seams (REPL teardown, headless and
+/// shell-execute exits) so already-fired exit hooks — `session.ended`, the
+/// final `turn.*` / `agent.*` events — finish spawning before the process
+/// tears down. Never used mid-session.
+pub(crate) const EXIT_HOOK_DRAIN_TIMEOUT: Duration = Duration::from_secs(2);
+
+/// Brackets one user-visible turn at an outer boundary (`ask`,
+/// `start_directive`, `shell_execute`): `enter` fires `turn.started`, and
+/// `finish` fires exactly one of `turn.completed` / `turn.interrupted` /
+/// `turn.failed`. The interrupted-vs-failed discrimination lives here and
+/// nowhere else: a ctrl-c abort wins over the result, then an error means
+/// failed (carrying `COYOTE_ERROR`), otherwise completed. Tool rounds,
+/// auto-continue, and compression retries run inside one bracket and never
+/// re-fire turn events.
+pub(crate) struct TurnBracket(());
+
+impl TurnBracket {
+    #[must_use]
+    pub(crate) fn enter(ctx: &RequestContext) -> Self {
+        hooks::fire(HookEvent::TurnStarted, ctx, &[], None);
+        Self(())
+    }
+
+    pub(crate) fn finish<T>(
+        self,
+        ctx: &RequestContext,
+        abort_signal: &AbortSignal,
+        result: Result<T>,
+    ) -> Result<T> {
+        if abort_signal.aborted_ctrlc() {
+            hooks::fire(HookEvent::TurnInterrupted, ctx, &[], None);
+        } else {
+            match &result {
+                Ok(_) => hooks::fire(HookEvent::TurnCompleted, ctx, &[], None),
+                Err(err) => hooks::fire(
+                    HookEvent::TurnFailed,
+                    ctx,
+                    &[("COYOTE_ERROR", format!("{err:#}"))],
+                    None,
+                ),
+            }
+        }
+        result
+    }
+}
+
 pub const DEFAULT_CONTINUATION_PROMPT: &str = indoc! {"
     [SYSTEM REMINDER - TODO CONTINUATION]
     You have incomplete tasks. Rules:
@@ -482,8 +530,12 @@ Type ".help" for additional help.
             supervisor.read().cancel_recursive();
         }
 
-        self.ctx.write().exit_session()?;
+        let exit_result = self.ctx.write().exit_session();
-        Ok(())
+        self.ctx
+            .write()
+            .top_level_agent_finished(exit_result.as_ref().err());
+        hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
+        exit_result
     }
 
     fn create_editor(ctx: Arc<RwLock<RequestContext>>, app: &AppConfig) -> Result<Reedline> {
@@ -983,6 +1035,7 @@ pub async fn run_repl_command(
                     let app = Arc::clone(&ctx.app.config);
                     ctx.use_agent(app.as_ref(), agent_name, session_name, abort_signal.clone())
                         .await?;
+                    ctx.top_level_agent_started();
                     if let Some(session) = &ctx.session {
                         let (compressed, active) = replay::snapshot(session);
                         replay::render(app.as_ref(), &compressed, &active)?;
@@ -1090,6 +1143,7 @@ pub async fn run_repl_command(
                         abort_signal.clone(),
                     )
                     .await?;
+                    hooks::fire(HookEvent::SessionCompressed, ctx, &[], None);
                     println!("✓ Successfully compressed the session.");
                 }
                 _ => {
@@ -1433,6 +1487,17 @@ async fn ask(
     abort_signal: AbortSignal,
     input: Input,
     with_embeddings: bool,
+) -> Result<()> {
+    let bracket = TurnBracket::enter(ctx);
+    let result = ask_inner(ctx, abort_signal.clone(), input, with_embeddings).await;
+    bracket.finish(ctx, &abort_signal, result)
+}
+
+async fn ask_inner(
+    ctx: &mut RequestContext,
+    abort_signal: AbortSignal,
+    input: Input,
+    with_embeddings: bool,
 ) -> Result<()> {
     let mut input = input;
     let mut with_embeddings = with_embeddings;
@@ -1579,9 +1644,7 @@ async fn ask(
             };
             eprintln!("\n📢 {}", color.italic().paint("Compressing the session."),);
 
-            if let Err(err) = ctx.compress_session().await {
+            auto_compress_session(ctx).await;
-                warn!("Failed to compress the session: {err}");
-            }
             if let Some(session) = ctx.session.as_mut() {
                 session.set_compressing(false);
             }
@@ -1632,6 +1695,13 @@ fn print_turn_divider() {
     println!();
 }
 
+async fn auto_compress_session(ctx: &mut RequestContext) {
+    match ctx.compress_session().await {
+        Ok(()) => hooks::fire(HookEvent::SessionCompressed, ctx, &[], None),
+        Err(err) => warn!("Failed to compress the session: {err}"),
+    }
+}
+
 fn should_continue(ctx: &RequestContext) -> bool {
     let config = ctx.auto_continue_config();
     ctx.app.config.function_calling_support
@@ -1939,6 +2009,320 @@ pub fn split_args_text(line: &str, is_win: bool) -> (Vec<String>, &str) {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::client::{ClientConfig, Model};
+    use crate::config::{AppState, RoleLike, Session, WorkingMode};
+    use crate::hooks::{HookDef, HooksMap, test_sink};
+    use anyhow::anyhow;
+    use serial_test::serial;
+    use std::future::Future;
+
+    const TURN_EVENTS: [&str; 4] = [
+        "turn.started",
+        "turn.completed",
+        "turn.interrupted",
+        "turn.failed",
+    ];
+
+    fn ctx_with_hooks(events: &[&str], marker: &str) -> RequestContext {
+        let mut hooks_map = HooksMap::default();
+        for event in events {
+            hooks_map.insert(
+                event.to_string(),
+                vec![HookDef {
+                    name: format!("{marker}-{event}"),
+                    command: "true".to_string(),
+                }],
+            );
+        }
+        let mut app = AppState::test_default();
+        app.config = Arc::new(AppConfig {
+            hooks: hooks_map,
+            ..Default::default()
+        });
+        RequestContext::new(Arc::new(app), WorkingMode::Repl)
+    }
+
+    /// Sink captures for `marker`, ordered (started, completed, interrupted, failed).
+    fn turn_counts(marker: &str) -> (usize, usize, usize, usize) {
+        let captures = test_sink::snapshot();
+        let count = |event: &str| {
+            captures
+                .iter()
+                .filter(|capture| capture.hook_name == format!("{marker}-{event}"))
+                .count()
+        };
+        (
+            count("turn.started"),
+            count("turn.completed"),
+            count("turn.interrupted"),
+            count("turn.failed"),
+        )
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn turn_bracket_ok_final_fires_started_and_completed() {
+        let _sink = test_sink::install();
+        let marker = "tb-ok-x7q";
+        let ctx = ctx_with_hooks(&TURN_EVENTS, marker);
+        let abort_signal = create_abort_signal();
+
+        let bracket = TurnBracket::enter(&ctx);
+        let result: Result<()> = async { Ok(()) }.await;
+        bracket.finish(&ctx, &abort_signal, result).unwrap();
+
+        assert_eq!(turn_counts(marker), (1, 1, 0, 0));
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn turn_bracket_tool_rounds_then_final_fire_one_turn() {
+        let _sink = test_sink::install();
+        let marker = "tb-rounds-p2m";
+        let ctx = ctx_with_hooks(&TURN_EVENTS, marker);
+        let abort_signal = create_abort_signal();
+
+        let bracket = TurnBracket::enter(&ctx);
+        let result: Result<()> = async {
+            // Simulates a turn that loops through tool rounds before the
+            // final round; rounds happen inside the bracket and never re-fire.
+            let mut rounds = 0;
+            loop {
+                rounds += 1;
+                if rounds == 3 {
+                    break Ok(());
+                }
+            }
+        }
+        .await;
+        bracket.finish(&ctx, &abort_signal, result).unwrap();
+
+        assert_eq!(turn_counts(marker), (1, 1, 0, 0));
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn turn_bracket_error_fires_failed_with_error_env() {
+        let _sink = test_sink::install();
+        let marker = "tb-err-k4d";
+        let ctx = ctx_with_hooks(&TURN_EVENTS, marker);
+        let abort_signal = create_abort_signal();
+
+        let bracket = TurnBracket::enter(&ctx);
+        let result: Result<()> = async { Err(anyhow!("turn exploded")) }.await;
+        let err = bracket.finish(&ctx, &abort_signal, result).unwrap_err();
+        assert_eq!(err.to_string(), "turn exploded");
+
+        assert_eq!(turn_counts(marker), (1, 0, 0, 1));
+        let captures = test_sink::snapshot();
+        let failed = captures
+            .iter()
+            .find(|capture| capture.hook_name == format!("{marker}-turn.failed"))
+            .expect("turn.failed capture");
+        assert_eq!(
+            failed.envs.get("COYOTE_ERROR").map(String::as_str),
+            Some("turn exploded")
+        );
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn turn_bracket_ctrlc_error_fires_interrupted_not_failed() {
+        let _sink = test_sink::install();
+        let marker = "tb-ctrlc-err-j6w";
+        let ctx = ctx_with_hooks(&TURN_EVENTS, marker);
+        let abort_signal = create_abort_signal();
+        abort_signal.set_ctrlc();
+
+        let bracket = TurnBracket::enter(&ctx);
+        let result: Result<()> = async { Err(anyhow!("Aborted!")) }.await;
+        assert!(bracket.finish(&ctx, &abort_signal, result).is_err());
+
+        assert_eq!(turn_counts(marker), (1, 0, 1, 0));
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn turn_bracket_ctrlc_with_ok_exit_fires_interrupted() {
+        let _sink = test_sink::install();
+        let marker = "tb-ctrlc-ok-r3v";
+        let ctx = ctx_with_hooks(&TURN_EVENTS, marker);
+        let abort_signal = create_abort_signal();
+        abort_signal.set_ctrlc();
+
+        let bracket = TurnBracket::enter(&ctx);
+        let result: Result<()> = async { Ok(()) }.await;
+        bracket.finish(&ctx, &abort_signal, result).unwrap();
+
+        assert_eq!(turn_counts(marker), (1, 0, 1, 0));
+    }
+
+    /// Drives a deep REPL future to completion on a thread with extra stack
+    /// headroom: nested `run_repl_command`/`compress_session` poll frames
+    /// are deep in debug builds and overflow the default test-thread stack
+    /// (Windows exhausts it first).
+    fn run_async<F>(f: F) -> F::Output
+    where
+        F: Future + Send,
+        F::Output: Send,
+    {
+        std::thread::scope(|scope| {
+            std::thread::Builder::new()
+                .stack_size(8 * 1024 * 1024)
+                .spawn_scoped(scope, || {
+                    tokio::runtime::Builder::new_current_thread()
+                        .enable_all()
+                        .build()
+                        .unwrap()
+                        .block_on(f)
+                })
+                .unwrap()
+                .join()
+                .unwrap()
+        })
+    }
+
+    #[test]
+    #[serial]
+    fn compress_command_failure_fires_no_session_compressed() {
+        let _sink = test_sink::install();
+        let marker = "compress-fail-z9t";
+        run_async(async {
+            let mut ctx = ctx_with_hooks(&["session.compressed"], marker);
+            ctx.session = Some(Session::default());
+            let abort_signal = create_abort_signal();
+
+            // Boxed: `run_repl_command`'s state machine is far larger than a
+            // test thread's stack.
+            let result = Box::pin(run_repl_command(
+                &mut ctx,
+                abort_signal,
+                ".compress session",
+            ))
+            .await;
+
+            assert!(result.is_err(), "compressing an empty session must fail");
+        });
+        assert_eq!(
+            test_sink::snapshot()
+                .iter()
+                .filter(|capture| capture.hook_name.starts_with(marker))
+                .count(),
+            0,
+            "a failed compression must fire no session.compressed hook"
+        );
+    }
+
+    /// A ctx whose compression can actually SUCCEED offline: `dry_run`
+    /// makes the summarization call echo instead of hitting the network,
+    /// the default openai client config makes the session model
+    /// resolvable, and the session already holds a user exchange so
+    /// `compress_session` has something to summarize.
+    fn compressible_ctx(marker: &str) -> RequestContext {
+        let mut hooks_map = HooksMap::default();
+        hooks_map.insert(
+            "session.compressed".to_string(),
+            vec![HookDef {
+                name: format!("{marker}-session.compressed"),
+                command: "true".to_string(),
+            }],
+        );
+        let mut app = AppState::test_default();
+        app.config = Arc::new(AppConfig {
+            hooks: hooks_map,
+            dry_run: true,
+            clients: vec![ClientConfig::default()],
+            ..Default::default()
+        });
+        let mut ctx = RequestContext::new(Arc::new(app), WorkingMode::Repl);
+        let mut session = Session::default();
+        session.set_model(Model::new("openai", "test-compress-model"));
+        ctx.session = Some(session);
+        let input = Input::from_str(&ctx, "hello there", None).unwrap();
+        ctx.session
+            .as_mut()
+            .unwrap()
+            .add_message(&input, "hi")
+            .unwrap();
+        ctx
+    }
+
+    fn session_compressed_count(marker: &str) -> usize {
+        test_sink::snapshot()
+            .iter()
+            .filter(|capture| capture.hook_name == format!("{marker}-session.compressed"))
+            .count()
+    }
+
+    #[test]
+    #[serial]
+    fn compress_command_success_fires_session_compressed_once() {
+        let _sink = test_sink::install();
+        let marker = "compress-ok-w2p";
+        run_async(async {
+            let mut ctx = compressible_ctx(marker);
+            let abort_signal = create_abort_signal();
+
+            // Boxed: `run_repl_command`'s state machine is far larger than a
+            // test thread's stack.
+            let result = Box::pin(run_repl_command(
+                &mut ctx,
+                abort_signal,
+                ".compress session",
+            ))
+            .await;
+
+            assert!(
+                result.is_ok(),
+                "dry-run compression must succeed: {result:?}"
+            );
+        });
+        assert_eq!(
+            session_compressed_count(marker),
+            1,
+            "a successful `.compress session` must fire session.compressed exactly once"
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn auto_compress_success_fires_session_compressed_once() {
+        // Covers the ask-loop call site through its extracted seam;
+        // driving `needs_compression` itself requires a full LLM turn and
+        // is exercised end-to-end by integration coverage, not here.
+        let _sink = test_sink::install();
+        let marker = "auto-compress-ok-f8r";
+        run_async(async {
+            let mut ctx = compressible_ctx(marker);
+            auto_compress_session(&mut ctx).await;
+        });
+
+        assert_eq!(
+            session_compressed_count(marker),
+            1,
+            "a successful auto-compression must fire session.compressed exactly once"
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn auto_compress_failure_fires_no_session_compressed_and_swallows_error() {
+        let _sink = test_sink::install();
+        let marker = "auto-compress-fail-d3k";
+        run_async(async {
+            let mut ctx = compressible_ctx(marker);
+            // An empty session makes compress_session fail; the seam must
+            // swallow the error (no panic, no propagation) and fire nothing.
+            ctx.session = Some(Session::default());
+            auto_compress_session(&mut ctx).await;
+        });
+
+        assert_eq!(
+            session_compressed_count(marker),
+            0,
+            "a failed auto-compression must fire no session.compressed hook"
+        );
+    }
 
     #[test]
     fn test_process_command_line() {

src/sandbox/mixins.rs

@@ -200,6 +200,12 @@ pub fn discover() -> Result<Vec<DiscoveredMixin>> {
     for path in collect_mixins(&paths::rags_dir(), &[ScanMode::Flat]) {
         out.push(read_mixin(path)?);
     }
+    for path in collect_mixins(&paths::roles_dir(), &[ScanMode::Flat]) {
+        out.push(read_mixin(path)?);
+    }
+    for path in collect_mixins(&paths::roles_dir().join("hooks"), &[ScanMode::Flat]) {
+        out.push(read_mixin(path)?);
+    }
 
     if let Ok(cwd) = env::current_dir()
         && let Some(path) = paths::find_workspace_sbx_mixin(&cwd)
@@ -940,6 +946,65 @@ network:
         let _ = fs::remove_dir_all(&root);
     }
 
+    #[test]
+    #[serial_test::serial]
+    fn discover_scans_roles_and_role_hooks_mixins() {
+        use crate::utils::get_env_name;
+
+        let root = unique_root("discover-roles");
+        let roles = root.join("roles");
+        fs::create_dir_all(roles.join("hooks")).unwrap();
+        let role_mixin = roles.join("review.sbx-mixin.yaml");
+        let hook_mixin = roles.join("hooks").join("notify.sbx-mixin.yaml");
+        fs::write(&role_mixin, "kind: mixin\n").unwrap();
+        fs::write(&hook_mixin, "kind: mixin\n").unwrap();
+        // The builtin installer's hidden manifest lives in the same dir but
+        // is not a mixin and must never be picked up by the flat scan.
+        let manifest = roles
+            .join("hooks")
+            .join(crate::config::builtin_manifest::BUILTIN_MANIFEST_FILE);
+        fs::write(&manifest, "notify.sh\n").unwrap();
+
+        let config_env = get_env_name("config_dir");
+        let roles_env = get_env_name("roles_dir");
+        let prev_config = env::var_os(&config_env);
+        let prev_roles = env::var_os(&roles_env);
+        unsafe {
+            env::set_var(&config_env, &root);
+            env::set_var(&roles_env, &roles);
+        }
+
+        let discovered = discover();
+
+        unsafe {
+            match prev_config {
+                Some(v) => env::set_var(&config_env, v),
+                None => env::remove_var(&config_env),
+            }
+            match prev_roles {
+                Some(v) => env::set_var(&roles_env, v),
+                None => env::remove_var(&roles_env),
+            }
+        }
+
+        let found: Vec<PathBuf> = discovered
+            .unwrap()
+            .into_iter()
+            .map(|mixin| mixin.path)
+            .collect();
+        assert!(found.contains(&role_mixin), "missing role mixin: {found:?}");
+        assert!(
+            found.contains(&hook_mixin),
+            "missing role hook mixin: {found:?}"
+        );
+        assert!(
+            !found.contains(&manifest),
+            "builtin manifest must not be scanned as a mixin: {found:?}"
+        );
+
+        let _ = fs::remove_dir_all(&root);
+    }
+
     /// `generate_rag_sbx_mixin` writes an agent-scoped RAG sidecar next to the
     /// rag yaml, at `<agents>/<agent>/<rag>.sbx-mixin.yaml`. Before `SubdirFlat`
     /// existed, nothing scanned that shape and attaching a Qdrant RAG from

src/testing.rs

@@ -3,27 +3,64 @@
 use log::{Level, LevelFilter, Log, Metadata, Record};
 use std::sync::{Mutex, Once, OnceLock};
 
-struct WarnCollector;
+struct TestLogCollector;
 
 static WARN_MESSAGES: OnceLock<Mutex<Vec<String>>> = OnceLock::new();
+static DEBUG_MESSAGES: OnceLock<Mutex<Vec<String>>> = OnceLock::new();
 
-/// Every warn-level message captured since the collector was installed. The
+/// Debug capture is restricted to the hooks module so the buffer is not
-/// buffer is process-global and shared by all tests, so assert by filtering
+/// flooded by debug output from the rest of the crate. Matching is
-/// for a marker unique to the test rather than on the whole buffer.
+/// module-boundary-aware: only this exact module or its `::` submodules
+/// qualify, so a sibling like `hooks_registry` would not.
+const DEBUG_TARGET_PREFIX: &str = concat!(env!("CARGO_CRATE_NAME"), "::hooks");
+
+fn captures_warn(metadata: &Metadata) -> bool {
+    metadata.level() <= Level::Warn
+}
+
+fn captures_hooks_debug(metadata: &Metadata) -> bool {
+    if metadata.level() != Level::Debug {
+        return false;
+    }
+    let target = metadata.target();
+    target == DEBUG_TARGET_PREFIX
+        || target
+            .strip_prefix(DEBUG_TARGET_PREFIX)
+            .is_some_and(|rest| rest.starts_with("::"))
+}
+
+/// Every warn- or error-level message captured since the collector was
+/// installed. The buffer is process-global and shared by all tests, so assert
+/// by filtering for a marker unique to the test rather than on the whole
+/// buffer.
 pub(crate) fn warn_messages() -> &'static Mutex<Vec<String>> {
     WARN_MESSAGES.get_or_init(Mutex::default)
 }
 
-impl Log for WarnCollector {
+/// Every debug-level message from the hooks module captured since the
+/// collector was installed. Same marker-filtering discipline as
+/// [`warn_messages`].
+pub(crate) fn debug_messages() -> &'static Mutex<Vec<String>> {
+    DEBUG_MESSAGES.get_or_init(Mutex::default)
+}
+
+impl Log for TestLogCollector {
     fn enabled(&self, metadata: &Metadata) -> bool {
-        metadata.level() <= Level::Warn
+        captures_warn(metadata) || captures_hooks_debug(metadata)
     }
 
+    // A test that panics while holding a buffer poisons its mutex; the logger
+    // recovers via `into_inner` so every later test can still log.
     fn log(&self, record: &Record) {
-        if self.enabled(record.metadata()) {
+        if captures_warn(record.metadata()) {
             warn_messages()
                 .lock()
-                .unwrap()
+                .unwrap_or_else(|poisoned| poisoned.into_inner())
+                .push(record.args().to_string());
+        } else if captures_hooks_debug(record.metadata()) {
+            debug_messages()
+                .lock()
+                .unwrap_or_else(|poisoned| poisoned.into_inner())
                 .push(record.args().to_string());
         }
     }
@@ -31,13 +68,15 @@ impl Log for WarnCollector {
     fn flush(&self) {}
 }
 
-/// Installs the process-wide warn collector. `log::set_logger` accepts one
+/// Installs the process-wide log collector. `log::set_logger` accepts one
-/// logger per process, so every test that captures warns must install through
+/// logger per process, so every test that captures warns or hooks debug
-/// this shared entry point.
+/// output must install through this shared entry point. The max level is
+/// Debug so the hooks debug capture sees its records; warn capture is
+/// unaffected.
 pub(crate) fn install_warn_collector() {
     static INSTALL: Once = Once::new();
     INSTALL.call_once(|| {
-        log::set_logger(&WarnCollector).expect("no other logger should be installed");
+        log::set_logger(&TestLogCollector).expect("no other logger should be installed");
-        log::set_max_level(LevelFilter::Warn);
+        log::set_max_level(LevelFilter::Debug);
     });
 }