docs: Updated the pull request template

PLAN-hooks-v2: hook system follow-ups and v2 features

.gitattributes

@@ -1 +1,7 @@
 assets/config-template.yaml text eol=lf
+assets/hooks/*.sh text eol=lf
+assets/agents/** text eol=lf
+assets/functions/tools/* text eol=lf
+assets/functions/scripts/* text eol=lf
+assets/functions/utils/*.sh text eol=lf
+scripts/*.sh text eol=lf

.github/PULL_REQUEST_TEMPLATE/pull_request_template.md

@@ -1,11 +0,0 @@
-### AI assistance (if any):
-- List tools here and files touched by them
-
-### Authorship & Understanding
-
-- [ ] I wrote or heavily modified this code myself
-- [ ] I understand how it works end-to-end
-- [ ] I can maintain this code in the future
-- [ ] No undisclosed AI-generated code was used
-- [ ] If AI assistance was used, it is documented below
-

.github/pull_request_template.md

@@ -0,0 +1,18 @@
+### Description
+<!-- What problem is this PR solving? -->
+
+### Alternatives Considered (Optional)
+<!-- What alternatives did you consider? Why did you choose this approach? -->
+
+### AI assistance (if any)
+<!-- Required if AI assistance was used to write or modify code in this PR. -->
+<!-- List tools here -->
+
+### Authorship & Understanding
+
+- [ ] I wrote or heavily modified this code myself. If I didn't, I gave proper attribution to AI assistance above.
+- [ ] I understand how it works end-to-end
+- [ ] I can maintain this code in the future
+- [ ] No undisclosed AI-generated code was used
+- [ ] If AI assistance was used, it is documented above
+

CONTRIBUTING.md

@@ -78,8 +78,9 @@ act -W .github/workflows/release.yml --input_type bump=minor
 
  ## Authorship Policy
 
-All code in this repository is written and reviewed by humans. AI-generated code (e.g., Copilot, ChatGPT,
-Claude, etc.) is not permitted unless explicitly disclosed and approved.
+All code in this repository is written and reviewed by humans, or AI-generated where explicitly disclosed.
+AI-generated code (e.g., Copilot, ChatGPT, Claude, etc.) is permitted only when explicitly disclosed and
+approved. For example: disclosing the use of AI-generated code in a PR description.
 
 Submissions must certify that the contributor understands and can maintain the code they submit.
 

Dockerfile

@@ -82,6 +82,8 @@ RUN set -euo pipefail; \
     chown 1000:1000 /home/agent/.cargo/bin/coyote; \
     rm -rf "$TMPDIR"
 
+COPY --chmod=0755 scripts/docker-entrypoint.sh /usr/local/bin/coyote-entrypoint
+
 FROM scratch
 
 ARG COYOTE_VERSION
@@ -107,4 +109,7 @@ WORKDIR /home/agent/workspace
 
 USER 1000
 
-ENTRYPOINT ["coyote"]
+# tini as PID 1 (as in the sandbox-templates base) reaps orphans and forwards
+# signals; coyote-entrypoint runs coyote by default, or the given command
+# (e.g. the Docker Sandboxes keep-alive) when the first arg is sh/bash/a path.
+ENTRYPOINT ["/usr/bin/tini", "--", "/usr/local/bin/coyote-entrypoint"]

README.md

@@ -56,6 +56,7 @@ Coming from [AIChat](https://github.com/sigoden/aichat)? Follow the [migration g
 * [Agents](https://github.com/Dark-Alex-17/coyote/wiki/Agents): Leverage AI agents to perform complex tasks and workflows, including sub-agent spawning, teammate messaging, and user interaction tools.
     * [Graph Agents](https://github.com/Dark-Alex-17/coyote/wiki/Graph-Agents): Define an agent as a declarative, YAML-driven workflow. A directed graph of typed nodes (LLM calls, scripts, approvals, user input, RAG retrieval, sub-agent spawns).
 * [Background Jobs](https://github.com/Dark-Alex-17/coyote/wiki/Background-Jobs): Run long tool calls (builds, test suites, slow MCP calls) in the background with the `job__*` tools while the model keeps working, and completion arrives as a push notification.
+* [Hooks](https://github.com/Dark-Alex-17/coyote/wiki/Hooks): Run your own fire-and-forget commands when lifecycle events fire. Turns, tools, LLM requests, agents, sub-agent escalations, and more (26 events). Perfect for desktop notifications, activity logging, and downstream automation; hooks never block Coyote or change its behavior.
 * [Todo System](https://github.com/Dark-Alex-17/coyote/wiki/TODO-System): Built-in task tracking for improved LLM reliability with smaller models.
 * [Environment Variables](https://github.com/Dark-Alex-17/coyote/wiki/Environment-Variables): Override and customize your Coyote configuration at runtime with environment variables.
 * [Client Configurations](https://github.com/Dark-Alex-17/coyote/wiki/Clients): Configuration instructions for various LLM providers.
@@ -143,6 +144,13 @@ docker run --rm -it \
   darkalex17/coyote
 ```
 
+Arguments are passed to `coyote`. If the first argument is `sh`, `bash`, or an absolute path, that command runs instead,
+e.g. to get a shell inside the image:
+
+```bash
+docker run --rm -it darkalex17/coyote bash
+```
+
 ### Scripts
 #### Linux/MacOS (`bash`)
 You can use the following command to run a bash script that downloads and installs the latest version of `coyote` for your

assets/agents/adversary/graph.yaml

@@ -205,9 +205,26 @@ nodes:
       confirm the change makes the criterion true, confirm the test targets
       BEHAVIOR (not implementation echo), use ast_grep for structural claims.
       Watch for gamed evidence: a test weakened/deleted so it passes, hardcoded
-      values shaped to the criterion's example, TODO/stub presented as done —
+      values shaped to the criterion's example, TODO/stub presented as done, a
+      mock expectation whose count is relaxed (`AnyTimes`, `MinTimes`, ignored
+      request body) AND whose matcher is permissive (`gomock.Any()`,
+      `mock.Anything`) — it proves a call happened, never that it carried the
+      criterion's values, so it is not a proving test —
       those are PARTIAL or DIVERGED with the gaming named in the complaint.
 
+      Retry / redelivery / idempotency demands: before you mark a criterion PARTIAL
+      or UNMET for lacking a retry, re-run, or "second attempt emits nothing" spec,
+      classify the handler. STATEFUL — it carries something across attempts (emits
+      events, calls an external system, performs an unconditional write, keeps an
+      in-memory or ledger record) — a retry spec is a legitimate demand. STATELESS —
+      each attempt is a pure function of the request plus a conditional store
+      predicate (`WHERE status = 'pending'`, `ended_at IS NULL`, `INSERT … ON
+      CONFLICT DO NOTHING`) and nothing is emitted or ledgered outside that
+      predicate — then "retry produces no event" is a tautology of the mechanism,
+      not a missing behavior: demand at most one test of the predicate itself,
+      never a retry spec. Name the classification and its file:line evidence in
+      the complaint either way.
+
       Execution criteria ("tests pass", "lint clean", "build succeeds") are
       judged ONLY against the recorded verification runs in your prompt — you
       have no execution tools BY DESIGN and must never claim to have run
@@ -297,7 +314,10 @@ nodes:
       The checklist (each hit becomes one complaint with kind, file:line
       location, the violation, and the fix):
       - **Absence** — something the PLAN requires that maps to no criterion and
-        never showed up in the diff (the dog that didn't bark).
+        never showed up in the diff (the dog that didn't bark). A missing
+        retry/redelivery spec is an absence ONLY for a handler that carries state
+        or side effects across attempts; a handler that is a pure function of the
+        request plus a conditional store predicate owes none.
       - **Scope drift / out-of-scope** — the diff touches what the plan's scope
         notes say not to touch, or quietly does extra unplanned work.
       - **Interface/approach substitution** — the plan named an interface,

assets/agents/adversary/scripts/run_checks.py

@@ -31,7 +31,9 @@ in-script degradation would never fire. Each command gets
 min(PER_COMMAND_TIMEOUT_SECS, remaining budget); commands the deadline
 leaves no budget for are recorded as {"cmd", "skipped": "deadline"} entries,
 so the in-script handling stays authoritative. The env var
-ADVERSARY_RUN_CHECKS_DEADLINE_SECS overrides the deadline (test seam).
+ADVERSARY_RUN_CHECKS_DEADLINE_SECS overrides the deadline (test seam), and
+ADVERSARY_STACK_LOCK_PATH overrides the review-stack lock file location
+(isolation seam — see acquire_stack_lock).
 
 Process hygiene: commands run through the shell. On POSIX each command gets
 its own session (start_new_session) and a timeout SIGKILLs the whole process
@@ -51,14 +53,20 @@ 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
 
+try:
+    import fcntl
+except ImportError:  # non-POSIX (Windows): advisory flock unavailable
+    fcntl = None
+
 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_PATH = os.environ.get("ADVERSARY_STACK_LOCK_PATH") or os.path.expanduser(
+    "~/.cache/coyote/review-stack.lock"
+)
 STACK_LOCK_WAIT_SECS = float(os.environ.get("ADVERSARY_STACK_LOCK_WAIT_SECS") or 1200)
 
 
@@ -67,7 +75,11 @@ def acquire_stack_lock():
     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)."""
+    on stderr. The fd is held for the process lifetime (released on exit).
+    On non-POSIX platforms (no fcntl) the lock is skipped entirely."""
+    if fcntl is None:
+        sys.stderr.write("WARN: review-stack lock unsupported on this platform; running unlocked\n")
+        return None
     try:
         os.makedirs(os.path.dirname(STACK_LOCK_PATH), exist_ok=True)
         fd = os.open(STACK_LOCK_PATH, os.O_CREAT | os.O_RDWR)

assets/agents/architect/config.yaml

@@ -6,7 +6,7 @@ description: |
   plan-conformance check (plus a black-box usage-pattern probe for consumer-facing surface), and
   finishes with ONE draft PR (CI checks watched to green) plus tracked follow-up tasks. Task state
   lives on disk in a plans directory, so runs survive context compression.
-version: 2.5.0
+version: 2.8.0
 agent_session: temp
 auto_continue: true
 max_auto_continues: 100
@@ -18,6 +18,7 @@ spawnable_agents:
   - oracle
   - explore
   - librarian
+  - deep-research
   - adversary
   - probe
   - review-gauntlet
@@ -180,7 +181,9 @@ instructions: |
   <label>; authoritative sources preferred; return a distilled, deduplicated checklist"), put the
   returned checklist through the same accept/drop round with the user, and write the ACCEPTED
   items into the plan — as measurable acceptance criteria on the relevant tasks where possible,
-  otherwise as a checklist under `## Quality bar → Long-tail criteria`.
+  otherwise as a checklist under `## Quality bar → Long-tail criteria`. Spawn checklist
+  librarians with `--variables {"research_depth": "deep"}` — checklist distillation is
+  broad-topic research and the default standard depth (3 searches / 8 fetches) starves it.
 
   Ground the breakdown in real code: fan out `explore` agents (load `parallel-research`) across
   {{project_dir}} — and `librarian` for unfamiliar external libraries — to confirm the design's
@@ -373,6 +376,12 @@ instructions: |
        `## 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.
+       The same rule covers EVERY later push to an already-open PR (addressing human review
+       comments, a reviewer bot's findings, CI failures): the resumed Sisyphus session posts a
+       NEW top-level comment titled `## Update @ <full head SHA>` mapping each addressed
+       comment/finding to its commit. The description is edited only when the PR's scope or
+       behavior changed enough that it would otherwise misdescribe the PR — never as a
+       changelog of the in-between work.
      - **Spawn `adversary`** with the diff base and the criteria pasted in:
 
        ```
@@ -587,7 +596,8 @@ instructions: |
   |-------|---------|
   | `sisyphus` | Implement ONE task's code in {{project_dir}} (its own explore/coder/verify/review loop). One per task. |
   | `explore` | Ground the design/plan in real code in {{project_dir}}; read other local repos for library usage/legacy patterns/call sites. Fan out in parallel. |
-  | `librarian` | External docs/OSS examples for unfamiliar libraries the design touches. |
+  | `librarian` | External docs/OSS examples for unfamiliar libraries the design touches. Design-time/broad topics: pass `--variables {"research_depth": "deep"}` (~3× budgets); default depth is for narrow lookups. One librarian per question beats one broad librarian — deep is for inherently broad questions. |
+  | `deep-research` | Open-ended/exhaustive research that should churn until its critique loop passes (plans sub-questions, deep librarian per question, credibility vetting). Spawn with `--variables {"autonomy": "autonomous"}` — MANDATORY, the supervised default blocks on a human approval gate; raise `reflexion_budget` (default 2) for longer churn. |
   | `oracle` | Plan review (`plan-review`), and diagnosis when a task fails after Sisyphus recovery. |
   | `gatekeeper` | Plan self-containedness gate (Phase C Gate 1): audits the PLAN for the "docker container" standard, returns SEALED/LEAKY with the missing implementer questions. |
   | `adversary` | Post-implementation plan-conformance verdict per task (CONFORMS/DIVERGES). |
@@ -622,6 +632,10 @@ instructions: |
     an unprobeable consumer-facing change is a plan gap to fix, not a checkbox to skip.
   - Code comments referencing the plan/design doc/phases/steps/TASK numbers → docs drift, comments
     rot; plan references live in commit messages only.
+  - Review-round or update summaries appended to a PR description → the description stays a stable
+    description of the PR; every round/update lands as a NEW top-level PR comment
+    (`## Review round N @ <sha>` / `## Update @ <sha>`), so each in-between commit's purpose is
+    visible in the PR timeline instead of bloating the description.
   - A `.env` file landing in any repo → only `.env.example` with placeholder keys is committable;
     `.env` stays gitignored and real values are a follow-up.
   - Dropping a Sisyphus-reported follow-up (not logged in the task's log.md, not in the PR's

assets/agents/coder/graph.yaml

@@ -39,7 +39,7 @@ settings:
 initial_state:
   project_dir: ''
   fix_attempts: 0
-  max_fix_attempts: 3
+  max_fix_attempts: 5
   fix_instructions: ''
   build_output: ''
   tests_output: ''
@@ -222,7 +222,8 @@ nodes:
       3. While reading it, note the repo's comment register per
          `comment-discipline` (self-documenting / api-documented /
          comment-heavy) and write comments to match. When the signal is
-         weak, write NO comment.
+         weak, write NO comment. Every comment must EARN ITS KEEP — if
+         the code already tells the reader, don't add it.
       4. If the change touches boundaries, error paths, jobs, or state
          transitions, also note the logging register per
          `logging-discipline` (logger, message style, payload vs IDs,
@@ -323,7 +324,8 @@ nodes:
         - Suppressed errors (as any, @ts-ignore, #[allow(...)] on unfamiliar
           lints, empty catch blocks)
         - Dishonest naming (get_X that mutates, returns wrong type, etc.)
-        - Useless comments that restate the code
+        - Useless comments that restate the code, or that otherwise don't earn
+          their keep (the code already tells the reader)
         - AI slop (filler prose, multi-paragraph docstrings, defensive
           handling of impossible cases)
 

assets/agents/deep-research/README.md

@@ -13,6 +13,13 @@ this agent runs a fixed graph: every request goes through the same
 `plan -> parallel research -> vet -> critique -> synthesize -> verify -> approve`
 pipeline.
 
+Two variables tune a run (pass via `--variables`): `reflexion_budget`
+(default 2) caps the automated critique -> re-research passes — raise it
+to let the run churn until the critique passes — and
+`autonomy: autonomous` skips the final human approval gate so other
+agents can spawn this one autonomously. Each sub-question is researched
+by a spawned `librarian` running at deep budgets.
+
 This agent is also the **canonical reference for the Coyote graph
 system**: it exercises every node type (`script`, `llm`, `rag`, `map`,
 `agent`, `input`, `approval`, `end`) and both static fan-out and

assets/agents/deep-research/graph.yaml

@@ -7,7 +7,12 @@ description: |
   delegates the final write-up to a focused sub-agent, checks that the
   cited sources are reachable, and gates the result behind human
   approval. A reviewer's free-form feedback at the approval step feeds
-  back into another research pass.
+  back into another research pass. Each sub-question is researched by a
+  spawned librarian running at deep budgets. Tunable via --variables:
+  reflexion_budget (default 2) caps the automated critique->re-research
+  passes - raise it to let the run churn until the critique passes;
+  autonomy=autonomous skips the human approval gate (REQUIRED when
+  another agent spawns this one).
 
   This is the canonical Coyote graph-agent reference: it exercises every
   node type (script, llm, rag, map, agent, input, approval, end) and
@@ -27,8 +32,16 @@ conversation_starters:
   - 'How does HTTP/3 differ from HTTP/2?'
   - 'Summarize recent advances in solid-state battery chemistry'
 
+variables:
+  - name: reflexion_budget
+    description: "Max automated critique->re-research passes before synthesis proceeds anyway. Default 2; raise it (4-8) for exhaustive runs that should churn until the critique passes."
+    default: '2'
+  - name: autonomy
+    description: "supervised (default): the finished report stops at the human approval gate. autonomous: skip the gate and return the report directly - REQUIRED when another agent spawns this one (a human gate would block the run)."
+    default: 'supervised'
+
 settings:
-  max_loop_iterations: 40
+  max_loop_iterations: 120
   log_state_snapshots: false
   validate_before_run: true
   max_concurrency: 4
@@ -142,23 +155,11 @@ nodes:
 
   research_one_question:
     id: research_one_question
-    type: llm
-    instructions: |
-      You are a web research assistant. Investigate the SINGLE question
-      given to you using your tools: search the web, fetch and read
-      pages, and search arXiv for academic sources.
-
-      Rules:
-        - Every factual claim must be backed by a real source you
-          actually retrieved. Never fabricate URLs, page titles,
-          authors, or DOIs.
-        - Prefer primary and authoritative sources over aggregators.
-        - Where sources disagree, report the disagreement rather than
-          papering over it.
-        - Put the URL (or DOI) inline next to each claim it supports.
-
-      Return organized findings in plain text. Do not include
-      meta-commentary about the process.
+    type: agent
+    agent: librarian
+    # The leaf research primitive: triage -> doc+OSS search -> cited
+    # synthesis. `inputs:` overlays the librarian graph's initial state,
+    # pinning research_depth to deep for every sub-question lane.
     prompt: |
       Research question: {{question}}
 
@@ -166,16 +167,13 @@ nodes:
       {{local_context}}
 
       {{research_feedback}}
-    tools:
-      - web_search_coyote
-      - fetch_url_via_curl
-      - search_arxiv
-      - mcp:ddg-search
-    max_iterations: 10
+    inputs:
+      research_depth: deep
+    timeout: 1900
     max_attempts: 2
     state_updates:
       finding: '{{output}}'
-    # On failure the engine writes "LLM node ...failed: <chain>" into `finding`
+    # On failure the engine writes "Agent node failed: <chain>" into `finding`
     # via the state_updates above BEFORE routing to the fallback. The marker
     # is branch-local: a map branch's fallback must stay inside the branch.
     fallback: question_fault
@@ -312,6 +310,13 @@ nodes:
     id: verify_sources
     type: script
     script: scripts/verify_sources.py
+    next: approval_gate
+
+  approval_gate:
+    id: approval_gate
+    type: script
+    description: Autonomy router - autonomous runs (spawned by another agent) skip the human approval gate and end accepted with the source check + pipeline notes attached; supervised (default) proceeds to the approval node. A crash fails forward via `next` to approve, the safe human-gated direction.
+    script: scripts/approval_gate.py
     next: approve
 
   approve:
@@ -348,6 +353,15 @@ nodes:
     type: end
     output: '{{report}}{{pipeline_notes}}'
 
+  end_autonomous:
+    id: end_autonomous
+    type: end
+    output: |
+      {{report}}
+
+      ----
+      {{source_check}}{{pipeline_notes}}
+
   end_rejected:
     id: end_rejected
     type: end

assets/agents/deep-research/scripts/approval_gate.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+"""Autonomy router for deep-research's approval gate.
+
+Runs after verify_sources. When the `autonomy` variable is
+'autonomous' (the run was spawned by another agent — architect or
+sisyphus research tiers — with no human at the terminal), the report
+skips the human approval node and ends accepted: the reflexion loop
+already served as the quality gate, and end_autonomous carries the
+source check + pipeline notes with the report so the caller sees them.
+Any other value (default 'supervised') proceeds to the human approval
+gate unchanged.
+
+Routing (`_next`):
+  - autonomy == 'autonomous' -> end_autonomous
+  - anything else            -> approve
+
+Fail-safe: a crash here fails FORWARD via the node's `next` to
+`approve` — the safe, human-gated direction.
+"""
+import json
+import os
+
+
+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", "{}"))
+
+
+def main():
+    state = load_state()
+    autonomy = str(state.get("autonomy") or "supervised").strip().lower()
+    target = "end_autonomous" if autonomy == "autonomous" else "approve"
+    print(json.dumps({"_next": target}))
+
+
+main()

assets/agents/deep-research/scripts/question_fault.py

@@ -4,10 +4,11 @@
 Reached ONLY via research_one_question's `fallback:` route inside the
 `research_each_question` map branch (branch-local — a map branch's fallback
 must stay inside the branch subgraph). Grounded in engine behavior: on
-llm-node failure the engine writes "LLM node …failed: <chain>" into
-`finding` via the node's state_updates BEFORE routing to the fallback (on
-success the same key holds the researched findings, which never start with
-the "LLM node" prefix). This node normalizes the failure text into a
+branch failure the engine writes its failure text into `finding` via the
+node's state_updates BEFORE routing to the fallback — "Agent node failed:
+<chain>" now that the branch spawns a librarian agent, "LLM node …failed:
+<chain>" for an llm branch (on success the same key holds the researched
+findings, which never start with either prefix). This node normalizes the failure text into a
 PIPELINE-FAULT finding and the chain ends here — the map collects the fault
 as the lane's `finding`, so one dead research lane never sinks the whole
 map. combine_findings later lifts PIPELINE-FAULT findings into
@@ -53,7 +54,7 @@ def main():
     state = load_state()
     raw = state.get("finding")
     detail = raw.strip().replace("\n", " ") if isinstance(raw, str) else ""
-    if not detail.startswith("LLM node"):
+    if not detail.startswith(("LLM node", "Agent node")):
         detail = "the research lane died without recording a failure detail"
     if len(detail) > MAX_DETAIL_CHARS:
         detail = detail[: MAX_DETAIL_CHARS - 1] + "…"

assets/agents/deep-research/scripts/reflexion_gate.py

@@ -2,7 +2,8 @@
 """Reflexion gate for deep-research.
 
 Runs after `critique` has reviewed the current research findings. If the
-critique's verdict is REVISE and the reflexion budget is not spent,
+critique's verdict is REVISE and the reflexion budget (the graph's
+`reflexion_budget` variable, default 2) is not spent,
 loops back to `research` with the critique attached as
 `research_feedback`, so the retry is informed rather than a blind
 re-run. Otherwise it proceeds to `synthesize`.
@@ -26,9 +27,11 @@ import json
 import os
 import re
 
-# Automated revision passes allowed. `research` runs at most
-# MAX_REFLEXION_REVISIONS + 1 times per user pass. Bump to allow more.
-MAX_REFLEXION_REVISIONS = 2
+# Default automated revision passes when the `reflexion_budget` variable
+# is absent or malformed. `research` runs at most budget + 1 times per
+# user pass. Callers raise it via --variables {"reflexion_budget": "6"}
+# to let the run churn until the critique passes.
+DEFAULT_REFLEXION_REVISIONS = 2
 
 
 def load_state():
@@ -69,8 +72,9 @@ def main():
     critique = state.get("critique") or ""
     verdict = parse_verdict(critique)
     attempts = as_int(state.get("research_attempts"))
+    budget = as_int(state.get("reflexion_budget"), DEFAULT_REFLEXION_REVISIONS)
 
-    if verdict == "REVISE" and attempts < MAX_REFLEXION_REVISIONS:
+    if verdict == "REVISE" and attempts < budget:
         feedback = (
             "A reviewer judged the previous research pass incomplete. "
             "Address every point in the critique below:\n\n" + critique

assets/agents/finding-verifier/graph.yaml

@@ -174,7 +174,7 @@ nodes:
       - fs_read
       - fs_cat
       - fs_grep
-    max_iterations: 14
+    max_iterations: 28
     max_attempts: 2
     state_updates:
       verdict: '{{output}}'

assets/agents/librarian/graph.yaml

@@ -6,13 +6,16 @@ description: |
   preamble. The "external grep" sibling of explore (which handles
   internal/codebase grep). Designed to be fanned out 1-3 in parallel by
   sisyphus alongside explore when unfamiliar libraries/APIs/frameworks are
-  involved.
+  involved. Supports research_depth=deep (via --variables) for broad
+  design-time topics: ~3x the search/OSS/fetch budgets of the standard
+  quick-lookup mode.
 
 version: '1.0'
 
 global_tools:
   - web_search_coyote.sh
   - fetch_url_via_curl.sh
+  - search_arxiv.sh
 
 mcp_servers:
   - ddg-search
@@ -26,11 +29,14 @@ variables:
   - name: project_dir
     description: Project directory for context (unused in MVP but reserved for future iterations).
     default: '.'
+  - name: research_depth
+    description: "standard (default) = quick targeted lookup budgets. deep = design-time research: ~3x search/OSS/fetch budgets for broad topics (best-practice checklists, architecture surveys)."
+    default: 'standard'
 
 settings:
   max_loop_iterations: 12
   log_state_snapshots: true
-  timeout: 600
+  timeout: 1800
 
 initial_state:
   language_ecosystem: 'general'
@@ -117,7 +123,7 @@ nodes:
   search:
     id: search
     type: llm
-    description: Identify 3-5 authoritative documentation sources via ddg-search.
+    description: Identify authoritative documentation sources via ddg-search (3-5 standard depth, 6-12 deep).
     skills_enabled: true
     enabled_skills:
       - ai-slop-remover
@@ -129,7 +135,10 @@ nodes:
       Priority order:
         1. Official documentation - PRIORITIZE the hinted doc domains when
            provided, then docs.X.org / readthedocs.io / MDN / vendor docs
-        2. Specifications (RFCs, W3C, ECMA, IEEE)
+        2. Specifications (RFCs, W3C, ECMA, IEEE) and academic sources -
+           the search_arxiv tool is available; use it when the topic is
+           academic/research-flavored (arXiv/DOI links count as
+           authoritative)
         3. Credible secondary references (PEPs, official blog posts) - only
            if 1-2 are sparse
 
@@ -142,14 +151,19 @@ nodes:
 
       ## Search budget and fail-fast rules
 
-      You have a HARD BUDGET of 3 search calls total. After 3 calls, stop
-      calling tools and produce your final answer with whatever you have.
+      Your budget is set by the `Research depth` line in the prompt:
+        - standard -> HARD BUDGET of 3 search calls total.
+        - deep     -> HARD BUDGET of 10 search calls total; spend the extra
+          calls covering DISTINCT subtopics of the research topic, never
+          re-running near-duplicate queries.
+      After the budget is spent, stop calling tools and produce your final
+      answer with whatever you have.
 
       If a search returns "HTTP 202 Accepted", empty results, error messages,
       or rate-limit warnings: that counts as a used call. Do not retry the
       same query - either rephrase OR give up.
 
-      If after 3 calls you have NO usable URLs, output exactly:
+      If after spending the budget you have NO usable URLs, output exactly:
 
         NO_AUTHORITATIVE_SOURCES_FOUND
         Reason: <one line>
@@ -168,9 +182,11 @@ nodes:
         URL: <full url>
         ...
 
-      Output 3-5 source blocks. No prose intro, no closing summary.
+      Output 3-5 source blocks (standard depth) or 6-12 (deep). No prose
+      intro, no closing summary.
     prompt: |
       Research topic: {{initial_prompt}}
+      Research depth: {{research_depth}}
 
       Triage hints:
         - Language/ecosystem: {{language_ecosystem}}
@@ -183,8 +199,9 @@ nodes:
       pathlib` style queries).
     tools:
       - mcp:ddg-search
+      - search_arxiv
       - web_search_coyote
-    max_iterations: 15
+    max_iterations: 30
     state_updates:
       search_output: '{{output}}'
     fallback: synthesize
@@ -193,7 +210,7 @@ nodes:
   search_oss:
     id: search_oss
     type: llm
-    description: Find 2-3 production OSS examples relevant to the topic via the personal-github MCP.
+    description: Find production OSS examples relevant to the topic via the personal-github MCP (2-3 standard depth, 4-8 deep).
     skills_enabled: true
     enabled_skills:
       - ai-slop-remover
@@ -219,8 +236,12 @@ nodes:
 
       ## Search budget and fail-fast rules
 
-      HARD BUDGET: 8 tool calls total. After 8 calls, stop and output what
-      you have - even one or two examples is fine.
+      Your budget is set by the `Research depth` line in the prompt:
+        - standard -> HARD BUDGET of 8 tool calls total; output 2-3 blocks.
+        - deep     -> HARD BUDGET of 20 tool calls total; output 4-8 blocks
+          across DIFFERENT repos/approaches, not near-duplicates.
+      After the budget is spent, stop and output what you have - even one or
+      two examples is fine.
 
       If you find no production examples, output exactly:
 
@@ -240,10 +261,12 @@ nodes:
 
         REPO: ...
 
-      Output 2-3 blocks. The URL should point to a specific file that
+      Output 2-3 blocks (standard depth) or 4-8 (deep). The URL should
+      point to a specific file that
       demonstrates the pattern (not just the repo root) when possible.
     prompt: |
       Research topic: {{initial_prompt}}
+      Research depth: {{research_depth}}
 
       Triage hints:
         - Language/ecosystem: {{language_ecosystem}}
@@ -254,7 +277,7 @@ nodes:
       Filter to {{language_ecosystem}} repositories when the API allows.
     tools:
       - mcp:personal-github
-    max_iterations: 15
+    max_iterations: 30
     state_updates:
       oss_output: '{{output}}'
     fallback: synthesize
@@ -308,8 +331,10 @@ nodes:
         5. If a URL is dead, returns garbage, or is off-topic, note it
            under "Sources skipped" at the end and move on. Do not retry.
 
-      Budget: max 8 fetches total (across both source lists). Skip
-      aggressively.
+      Fetch budget, set by the `Research depth` line in the prompt:
+        - standard -> max 8 fetches total (across both source lists).
+        - deep     -> max 25 fetches total. Depth buys MORE SOURCES, never
+          re-fetching dead or off-topic URLs - skip aggressively either way.
 
       ## Output format
 
@@ -332,6 +357,7 @@ nodes:
       No flattery, no preamble. Start with `## Findings`.
     prompt: |
       Research topic: {{initial_prompt}}
+      Research depth: {{research_depth}}
 
       Documentation sources (from doc search branch):
       {{search_output}}
@@ -340,7 +366,7 @@ nodes:
       {{oss_output}}
     tools:
       - fetch_url_via_curl
-    max_iterations: 20
+    max_iterations: 45
     state_updates:
       findings: '{{output}}'
     fallback: final_format

assets/agents/probe/config.yaml

@@ -120,7 +120,15 @@ instructions: |
      update — never delete or silence it).
   4. **Clean, local, isolated.** Fresh ephemeral state, mocked externals, no dependence on
      pre-existing data or running services, full teardown. Bounded retries for startup only —
-     never to mask a flaky assertion.
+     never to mask a flaky assertion. Teardown MUST NOT depend on a shell trap firing (a
+     killed or timed-out lane leaks containers — it has happened): pick one unique run
+     prefix up front (e.g. `probe-$$`), give EVERY container you create `--name <prefix>-…`
+     and `--label coyote-probe=<prefix>` (compose: `-p <prefix>`), prefer `docker run --rm`,
+     and make the LAST action before emitting your verdict an explicit sweep:
+     `docker ps -aq --filter label=coyote-probe=<prefix> | xargs -r docker rm -f` (compose:
+     `docker compose -p <prefix> down -v`). The label filter keeps the sweep scoped to YOUR
+     resources — rule 0 still forbids touching anyone else's. A leftover you cannot remove
+     is a finding to REPORT in the verdict, never to silence.
   5. **Classify every failure** as BUG / EXPECTED-CHANGE / ENV per the skill table. The verdict
      depends on the classification being honest.
   6. **Committed tests are the deliverable** alongside the verdict: write them where the repo's

assets/agents/review-gauntlet/README.md

@@ -14,7 +14,7 @@ flowchart TD
     parse -. "fallback" .-> pfault["parse_fault<br/>(script: PIPELINE-FAULT marker)"]
     pfault --> gate
     signals --> select["select_lanes<br/>(llm: ADDITIVE-only judgment)"]
-    select --> build["build_items<br/>(script: rules floor ∪ additions;<br/>forced lanes override exactly)"]
+    select --> build["build_items<br/>(script: rules floor ∪ additions;<br/>forced lanes add)"]
     select -. "fallback" .-> dlanes["default_lanes<br/>(script: deterministic degraded<br/>selection — wider, never narrower)"]
     dlanes --> build
     build --> mcr["map: code-review"] & madv["map: adversary"] & msec["map: security"] & mpb["map: probe"]
@@ -155,7 +155,7 @@ Plan / acceptance criteria:
 Local-run recipe / usage suites:
 <how to boot the service locally + where existing suites live — enables the probe lane>
 
-Forced lanes: (optional — e.g. 'adversary, probe' to run exactly those)" \
+Forced lanes: (optional, ADDITIVE — e.g. 'adversary, probe' run on top of the computed selection; forcing never drops the always-on floor)" \
   --variables {"verification_commands": "[\"cargo test --all\", \"cargo clippy -- -D warnings\"]"}
 ```
 
@@ -210,9 +210,9 @@ verbatim.
   (`'[]'` ⇒ "none declared"); a declaration that is not a JSON array of
   strings executes nothing and records a `PIPELINE-FAULT`, which the
   adversary lane reports as DIVERGES and the gate as BLOCKED.
-- Signals failures degrade gracefully: if git can't compute the diff, lane
-  selection falls back to caller context + forced lanes, and the report notes
-  it. The auth-path regex deliberately over-fires (`auth(?!or)` matches
+- Signals failures degrade WIDER: if git can't compute the diff, the surface
+  is unknown — the security lane is added (and probe, when a local-run recipe
+  exists) on top of caller context + forced lanes, and the report notes it. The auth-path regex deliberately over-fires (`auth(?!or)` matches
   auth/authn/authz/oauth but not "author") — the safe direction, since signals
   only ever ADD the security lane.
 - Requires the `code-reviewer`, `adversary`, `security-reviewer`, and `probe`

assets/agents/review-gauntlet/graph.yaml

@@ -107,10 +107,14 @@ nodes:
       You extract the facts of a review request into structured fields.
       EXTRACTION ONLY — do not decide which review lanes should run.
 
-      - `diff_spec`: the git diff specification the caller named — a ref
-        range ("main...HEAD", "HEAD~3..HEAD"), a single ref, or the literal
-        "worktree" for uncommitted changes against HEAD. When the caller
-        did not name one, use "worktree".
+      - `diff_spec`: the git diff specification the caller named, as a BARE
+        revision token usable verbatim in `git diff <spec>` — a ref range
+        ("main...HEAD", "HEAD~3..HEAD"), a single ref, or the literal
+        "worktree" for uncommitted changes against HEAD. NEVER prose, a
+        command, or a path: from "run get_diff --base origin/main" extract
+        "origin/main...HEAD"; from "diff origin/main...HEAD in ~/code/x"
+        extract "origin/main...HEAD". When the caller did not name one, use
+        "worktree".
       - `project_dir_in`: the repository directory the caller named as holding
         the change (absolute path preferred); empty string when the caller
         named none.
@@ -127,7 +131,8 @@ nodes:
         pointers for black-box probing (how to boot the service, where the
         suites live). Empty string when the caller supplied none.
       - `forced_lanes`: lanes the caller explicitly demanded (verbatim
-        names). Empty array = automatic selection.
+        names). Empty array = automatic selection. Forcing is ADDITIVE
+        downstream: it widens the computed selection, never replaces it.
       - `extra_context`: any remaining caller context reviewers should see,
         condensed.
     prompt: |
@@ -261,7 +266,7 @@ nodes:
   build_items:
     id: build_items
     type: script
-    description: Deterministic lane builder — hard rules are the floor, LLM flags may only add, forced lanes override exactly. Emits one 0-or-1-item list per lane; an empty list skips that lane's map. On a re-run pass (retry_lanes non-empty) it skips selection and emits items only for those lanes, each carrying its attempt number.
+    description: Deterministic lane builder — hard rules are the floor, LLM flags may only add, forced lanes are ADDITIVE (selection only ever widens; unavailable signals widen it too). Emits one 0-or-1-item list per lane; an empty list skips that lane's map. On a re-run pass (retry_lanes non-empty) it skips selection and emits items only for those lanes, each carrying its attempt number.
     script: scripts/build_items.py
     timeout: 30
     next: [map_code_review, map_adversary, map_security, map_probe]

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

@@ -1,14 +1,20 @@
 #!/usr/bin/env python3
 """Deterministic lane builder for the review gauntlet.
 
-Selection = hard rules (the floor) ∪ LLM additions; forced lanes override
-everything exactly. Emits one 0-or-1-item list per lane: an empty list makes
-that lane's map node run zero branches (map-over-nothing), which IS the
-skip mechanism — no dynamic routing anywhere.
+Selection = hard rules (the floor) ∪ LLM additions ∪ caller-forced lanes.
+Forcing is ADDITIVE: it can only widen the computed selection — honoring a
+forced list as the exact set once dropped the always-on code-review lane in
+a live run. Emits one 0-or-1-item list per lane: an empty list makes that
+lane's map node run zero branches (map-over-nothing), which IS the skip
+mechanism — no dynamic routing anywhere.
 
 The LLM's add_* flags can only ADD lanes. A flag that is false never
 removes a lane the hard rules selected.
 
+Unavailable diff signals (malformed spec, git failure) mean the surface is
+UNKNOWN — selection degrades WIDER (security on; probe when a recipe
+exists), never narrower.
+
 A re-run pass (retry_gate emitted `retry_lanes`) skips selection: only the
 named lanes get an item, stamped with their attempt number, and every other
 lane maps over nothing — retry_gate restores their earlier reports.
@@ -101,10 +107,6 @@ def main():
         (forced.append(canon) if canon else unknown.append(str(lane)))
 
     reasons = []
-    if forced:
-        lanes = set(forced)
-        reasons.append(f"forced lanes honored exactly: {sorted(lanes)}")
-    else:
     lanes = {"code-review"}
     reasons.append(
         "code-review: always on — the gauntlet is only spawned for non-trivial work"
@@ -128,6 +130,22 @@ def main():
             "probe: consumer-facing surface changed and a local-run recipe/suite pointer exists"
         )
 
+    # Unavailable signals (malformed diff spec, git failure) = surface UNKNOWN.
+    # Degrade WIDER, never narrower — a run without signals once silently
+    # dropped the security and probe lanes.
+    if text("signals_summary") == "signals unavailable":
+        if "security" not in lanes:
+            lanes.add("security")
+            reasons.append(
+                "security: diff signals unavailable — surface unknown, degrading wider"
+            )
+        if "probe" not in lanes and text("probe_context"):
+            lanes.add("probe")
+            reasons.append(
+                "probe: diff signals unavailable and a local-run recipe/suite pointer "
+                "exists — degrading wider"
+            )
+
     # LLM judgment is additive-only.
     llm_why = text("lane_reasons")[:300]
     for flag, lane in (
@@ -152,6 +170,28 @@ def main():
             lanes.add(lane)
             reasons.append(f"{lane}: added by lane-selection judgment — {llm_why}")
 
+    # Caller-forced lanes are ADDITIVE: they widen the computed selection,
+    # never replace it. (Honoring them as the exact set dropped code-review —
+    # documented as always-on — and adversary in a live run.) Forcing also
+    # bypasses the context guards above: the caller demanded the lane, so it
+    # runs, with the expectation named in the summary.
+    if forced:
+        newly = sorted(set(forced) - lanes)
+        lanes |= set(forced)
+        reasons.append(
+            f"forced lanes (additive): {sorted(set(forced))}"
+            + (f" — newly added: {newly}" if newly else " — all already selected")
+        )
+        if "probe" in forced and not text("probe_context"):
+            reasons.append(
+                "probe: forced without a local-run recipe/suite pointer — expect INCONCLUSIVE"
+            )
+        if "adversary" in forced and not text("plan_context"):
+            reasons.append(
+                "adversary: forced without spec/plan context — it fails closed "
+                "(DIVERGES) without extractable criteria"
+            )
+
     if unknown:
         reasons.append(f"ignored unknown forced lane name(s): {unknown}")
 

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

@@ -8,8 +8,10 @@ AND a local-run recipe exists (build_items gates probe the same way — a
 probe without a recipe is INCONCLUSIVE by construction),
 plus security when the attack-surface signals (auth/deps/exec) or a hardened
 posture demand it, unioned with any lanes the caller forced (canonicalized
-with the same aliases build_items uses) — which build_items honors exactly,
-so selection degrades WIDER, never narrower. The degradation note goes into
+with the same aliases build_items uses) — which build_items honors
+ADDITIVELY, so selection degrades WIDER, never narrower. Unavailable diff
+signals also widen: unknown surface adds security (and probe when a
+local-run recipe exists). The degradation note goes into
 `lanes_degraded`; build_items folds it into lanes_summary so the final
 report names the degradation.
 
@@ -72,6 +74,11 @@ def main():
         or state.get("security_posture") == "hardened"
     ):
         lanes.add("security")
+    # Unavailable signals = surface UNKNOWN → widen (mirrors build_items).
+    if (state.get("signals_summary") or "") == "signals unavailable":
+        lanes.add("security")
+        if isinstance(probe_context, str) and probe_context.strip():
+            lanes.add("probe")
     # Caller-forced lanes survive degradation — union, never overwrite.
     for lane in state.get("forced_lanes") or []:
         if canon := ALIASES.get(str(lane).strip().lower()):

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

@@ -3,9 +3,10 @@
 
 Pure git — no LLM judgment. Every signal is computed from the changed-file
 list and the added lines of the diff. Failures never sink the gauntlet:
-on any error the script reports `signals_error` and leaves the defaults
-(false/empty) in place, which biases lane selection toward the caller's
-context and forced lanes.
+on any error the script reports `signals_error` and marks the signals
+unavailable — downstream (build_items / default_lanes) treats that as
+UNKNOWN surface and degrades WIDER (security on; probe when a recipe
+exists), on top of caller context and forced lanes.
 """
 
 import json
@@ -26,6 +27,19 @@ proj = os.path.expanduser(
     (state.get("project_dir_in") or "").strip() or state.get("project_dir") or "."
 )
 spec = (state.get("diff_spec") or "worktree").strip()
+spec_raw = spec
+# The parse stage should emit a bare revision token, but callers write prose
+# and extraction drifts ("run get_diff --base origin/main" once reached
+# `git diff` verbatim, killing the signals — and with them the security and
+# probe lanes). Deterministically recover a usable spec before giving up.
+_TOKEN = r"[\w./~^@{}-]+"
+if spec not in ("", "worktree") and not re.fullmatch(
+    rf"{_TOKEN}(\.\.\.?{_TOKEN})?", spec
+):
+    if m := re.search(rf"({_TOKEN}\.\.\.?{_TOKEN})", spec):
+        spec = m.group(1)  # a revision range buried in prose
+    elif m := re.search(rf"--base[= ]({_TOKEN})", spec):
+        spec = f"{m.group(1)}...HEAD"  # the get_diff idiom
 
 
 def git(*args):
@@ -112,13 +126,18 @@ try:
             ),
             "docs_only": bool(files)
             and all(re.search(r"\.(md|rst|txt|adoc)$", f, re.I) for f in files),
-            "signals_summary": f"{len(files)} file(s) changed (diff: {spec})",
+            "signals_summary": f"{len(files)} file(s) changed (diff: {spec})"
+            + (f" — spec normalized from {spec_raw!r}" if spec != spec_raw else ""),
         }
     )
 except Exception as e:  # noqa: BLE001 — degraded signals must not sink the gauntlet
+    what = f"diff spec {spec!r}" + (
+        f", normalized from {spec_raw!r}" if spec != spec_raw else ""
+    )
     out["signals_error"] = (
-        f"NOTE: diff signals could not be computed ({e}); "
-        "lane selection falls back to caller context and forced lanes."
+        f"NOTE: diff signals could not be computed ({what}: {e}); surface UNKNOWN — "
+        "lane selection degrades WIDER (security lane added; probe eligible when a "
+        "local-run recipe exists), plus caller context and forced lanes."
     )
     out["signals_summary"] = "signals unavailable"
 

assets/agents/sisyphus/config.yaml

@@ -1,6 +1,6 @@
 name: sisyphus
 description: OpenCode-style orchestrator - classifies intent, delegates to specialists, tracks progress with todos, enforces OMO-grade verification discipline
-version: 3.13.0
+version: 3.17.0
 
 agent_session: temp
 auto_continue: true
@@ -11,6 +11,7 @@ can_spawn_agents: true
 spawnable_agents:
   - explore
   - librarian
+  - deep-research
   - coder
   - oracle
   - code-reviewer
@@ -157,7 +158,8 @@ instructions: |
   | Agent | Use For | Characteristics |
   |-------|---------|-----------------|
   | `explore` | Find patterns in THIS codebase, understand local code | Read-only, returns findings, fan out as many as the task warrants — one per distinct search angle, module, or concern. Large codebases or cross-cutting tasks should spawn 5–15+. |
-  | `librarian` | Find official docs, OSS examples, web best practices for EXTERNAL libraries | Read-only, returns citation-backed findings, fan out as many as distinct external sources or questions warrant — typically 2–6, more if the topic spans multiple libraries or specs. |
+  | `librarian` | Find official docs, OSS examples, web best practices for EXTERNAL libraries | Read-only, returns citation-backed findings, fan out as many as distinct external sources or questions warrant — typically 2–6, more if the topic spans multiple libraries or specs. Default depth = quick-lookup budgets; for a BROAD topic (design research, best-practice surveys, architecture comparisons) pass `--variables {"research_depth": "deep"}` (~3× search/fetch budgets). Still prefer several narrow librarians over one giant one — deep is for questions that are inherently broad, not a substitute for fan-out. |
+  | `deep-research` | Open-ended investigation that must CHURN until solid — plans sub-questions, fans out a deep librarian per question, vets source credibility, runs a critique→re-research loop | Spawn with `--variables {"autonomy": "autonomous"}` — MANDATORY when spawned as a subagent (the supervised default blocks on a human approval gate). Raise `reflexion_budget` (e.g. "6", default 2) to let it churn longer. Expect hours, not minutes; one per investigation — its internal map is the fan-out. |
   | `coder` | Write/edit files, implement features | Graph agent: plan → approval → implement → verify build+tests → self_review → bounded fix-loop |
   | `oracle` | Architecture, complex debugging, review, plan review | Advisory, blocking — never answer the user before collecting Oracle results |
   | `step-runner` | Execute ONE step of a phased plan repo (Phase 8) | Graph agent: orient → staleness check → coder → verify → handoff → user approval gate |
@@ -575,7 +577,7 @@ instructions: |
 
   When you write or modify files yourself (rather than delegating to coder):
 
-  - **Calibrate comments before writing.** Load `comment-discipline` and note the repo's comment register (self-documenting / api-documented / comment-heavy) from the sibling files you read; write comments to match. When the signal is weak, write NO comment.
+  - **Calibrate comments before writing.** Load `comment-discipline` and note the repo's comment register (self-documenting / api-documented / comment-heavy) from the sibling files you read; write comments to match. When the signal is weak, write NO comment. In every register, a comment must EARN ITS KEEP — if the code already tells the reader, don't add it.
   - **Calibrate logging before writing.** When the change touches boundaries, error paths, jobs, or state transitions, load `logging-discipline` and note the repo's logging register (logger, message style, payload vs IDs, level semantics) from the same sibling reads; match it. No discernible convention → its best-judgment defaults. Never leave a new error path silently swallowed, and never delete existing log lines as drive-by cleanup.
   - **For editing an existing file**, prefer `fs_patch`. It's a surgical edit that preserves unchanged content. Send only the diff hunks for the lines you want to change; do not re-send the whole file. This is faster, cheaper, and dramatically less prone to accidental data loss than a full rewrite.
   - **For writing a NEW file or doing a COMPLETE rewrite**, use `fs_write`. Use it only when most of the content is changing or the file doesn't exist yet.
@@ -709,6 +711,13 @@ instructions: |
     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.
+    The same discipline covers EVERY later push to a PR you (or your run) opened — addressing
+    human review comments, a reviewer bot's findings, CI failures, or any other PR event: post
+    a NEW top-level PR comment titled `## Update @ <full head SHA>` mapping each addressed
+    comment/finding to the commit that addresses it (one line each), plus anything
+    deliberately NOT addressed and why. NEVER append update summaries to the description.
+    Edit the description ONLY when the PR's actual scope or behavior changed enough that it
+    would otherwise misdescribe the PR — it stays a description, never a changelog.
 
     **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

assets/config-template.yaml

@@ -186,6 +186,7 @@ save_session: null               # Controls the persistence of the session. If t
 compression_threshold: 4000      # Compress the session when the token count reaches or exceeds this threshold
 compression_keep_last: 0         # Number of most-recent messages to keep visible after compression (0 = compress all messages)
 compression_model: null          # Model to use for session compression (e.g. 'openai:gpt-4o-mini'); defaults to the session's current model
+compression_safety_valve: 0.8    # Force compression when the last real request's prompt size (or the local estimate) reaches this fraction of the model's max_input_tokens, even if compression_threshold would not fire (0 = disabled)
 summarization_prompt: null       # The text prompt used for creating a concise summary of session messages. If null, uses built-in default
 summary_context_prompt: null     # The text prompt used for including the summary of the entire session as context to the model. If null, uses built-in default
 max_tool_result_chars: null      # Cap on tool result characters forwarded to the model per call (null = no cap)
@@ -276,6 +277,7 @@ sync_models_ttl_hours: 24        # Hours before the synced model catalog is cons
 # All clients have the following configuration:
 # - type: xxxx
 #   name: xxxx                                      # Only use it to distinguish clients with the same client type. Optional
+#   extend_models: true                             # Merge the models below on top of the catalog models for this client instead of replacing them. Optional, default false
 #   models:
 #     - name: xxxx                                  # Chat model
 #       max_input_tokens: 100000

assets/hooks/log-events.sh

@@ -4,7 +4,8 @@
 # each one carries.
 #
 # Env vars read:
-#   COYOTE_HOOK_LOG   log file to append to (default: /tmp/coyote-hooks.log)
+#   COYOTE_HOOK_LOG   log file to append to
+#                     (default: ${XDG_STATE_HOME:-$HOME/.local/state}/coyote/hooks.log)
 #   COYOTE_*          everything coyote sets for the event is dumped verbatim
 #
 # Secrets (COYOTE_SECRET_*) are excluded from the snapshot; widening the grep
@@ -26,15 +27,15 @@
 
 set -u
 
-log_file="${COYOTE_HOOK_LOG:-/tmp/coyote-hooks.log}"
+log_file="${COYOTE_HOOK_LOG:-${XDG_STATE_HOME:-$HOME/.local/state}/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.
+# COYOTE_HOOK_LOG may point into a shared directory: refuse to append through
+# a symlink someone else planted there.
 [ -L "$log_file" ] && exit 0
 umask 077
+mkdir -p "$(dirname "$log_file")" 2> /dev/null || true
 {
-  echo "=== $(date '+%Y-%m-%dT%H:%M:%S%z') ${COYOTE_EVENT:-unknown}"
+  echo "=== $(date -u '+%Y-%m-%dT%H:%M:%SZ') ${COYOTE_EVENT:-unknown}"
   env | grep '^COYOTE_' | grep -v '^COYOTE_SECRET_' | sort
   echo
 } >> "$log_file" 2> /dev/null || true

assets/hooks/notify.sh

@@ -38,5 +38,8 @@ elif command -v osascript > /dev/null 2>&1; then
 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"
+  # $body carries model-influenced values: strip control bytes (including
+  # ESC, so ANSI/OSC sequences cannot drive the terminal) before echoing.
+  safe_line="$(printf '%s' "[$title] $body" | tr -d '\000-\010\013\014\016-\037\177')"
+  { echo "$safe_line" > /dev/tty; } 2> /dev/null || echo "$safe_line"
 fi

assets/skills/code-review/SKILL.md

@@ -89,6 +89,15 @@ These are review findings that only surface in a diff context, not in a whole-fi
   finding (dead weight or a forgotten wiring step). Used in SOME applicable in-diff sites but
   not others = a finding naming the sites that didn't adopt it — half-adopted artifacts are how
   two mechanisms for the same job end up coexisting forever.
+- **"Ignored / redundant request field" claims need a wire-validation check first** — before
+  calling a request/message field ignored, redundant, or dead on some code path because the
+  handler never reads it there, `fs_grep` the boundary contract for that field: proto validation
+  rules (`(validate.rules)`, `buf.validate`), OpenAPI/JSON-schema `required`, struct-tag
+  `required`/`binding`/serde attributes, or a hand-written validator/interceptor. A field the
+  validator MANDATES is load-bearing at the boundary even when the handler ignores it — the
+  honest finding (if any) is "validator requires `<field>` on the `<path>` path that never reads
+  it (`path:line`); relax with `ignore_empty`/`oneof` or document why", never "`<field>` is
+  ignored". No validation found ⇒ the ignored-field finding stands, citing the grep you ran.
 - **Version-literal consistency and freshness** — when the diff bumps a version (image tag,
   tool version, dependency pin), `fs_grep` the repo for other occurrences of the OLD version
   string (compose files, workflows, docs, sibling Dockerfiles) — stragglers are findings. For
@@ -143,6 +152,21 @@ Named adequacy anti-patterns — each is a finding even when coverage looks gree
 - **Leaky fixture** — an integration test against a shared/persistent database inserts fixture
   rows directly with no paired cleanup (deferred delete/teardown/transaction rollback). The
   test passes today and leaves a primary-key landmine for the next run.
+- **Struct-typed args against an inferred schema** — when a struct drives an inferred wire schema
+  (MCP go-sdk, OpenAPI/JSON-schema generators, serde-derived schemas), every field without
+  `omitempty`/pointer/`Option` becomes schema-REQUIRED. Cross-check the optionality the doc
+  strings promise ("X as an alternative to Y") against the tags — a documented-optional field
+  without the omission marker is a live validation bug, not a style nit. And tests that build the
+  request from the typed struct serialize EVERY field (zero values included), so they can never
+  exercise the required-ness check: demand raw-JSON / map-typed tests that OMIT each
+  documented-optional field.
+- **Relaxed call count with a permissive matcher** — a mock expectation whose COUNT is relaxed
+  (`AnyTimes()`, `MinTimes(1)`, `Maybe()`, "called at least once") leaves the ARGUMENT matcher as
+  the only thing asserted; pair it with `gomock.Any()` / `mock.Anything` / `mock.ANY` /
+  `expect.anything()` / an ignored request body and the expectation proves nothing — a call with
+  the wrong ID, wrong quantity, or wrong principal satisfies it. Flag every relaxed-count
+  expectation whose matcher is permissive; the fix pins the load-bearing fields in the matcher
+  (or exact count + captured args).
 
 ## 3. Clarity
 

assets/skills/comment-discipline/SKILL.md

@@ -1,7 +1,7 @@
 ---
 description: Calibrate comment density and style to the repository's existing conventions before writing code. Detects the repo's comment register (self-documenting / api-documented / comment-heavy) from the sibling files you already read for pattern matching, or from a declared policy in workspace instructions, then dictates when a comment is warranted. Default when signal is weak - write NO comment. Complements ai-slop-remover (which bans comments that restate code in every register).
 ---
-You are about to write or modify code. LLMs systematically over-comment — narrating every block, restating signatures, banner-ing sections — and that default is wrong in most repositories. Before writing, determine the repo's **comment register** and match it, exactly the way you already match imports, naming, and error handling.
+You are about to write or modify code. LLMs systematically over-comment — narrating every block, restating signatures, banner-ing sections — and that default is wrong in most repositories. Before writing, determine the repo's **comment register** and match it, exactly the way you already match imports, naming, and error handling. Across every register, one test governs each comment you write: it must **earn its keep**. If the code already tells the reader, the comment doesn't get written — don't add comments you don't need; make the code tell them instead.
 
 ## Step 0: Check for a declared policy first
 

assets/skills/security-review/SKILL.md

@@ -56,6 +56,16 @@ If no posture is given, assume `standard` and say so in the report.
 8. **Crypto and randomness** — homegrown crypto, non-cryptographic RNG used for tokens/session IDs, hardcoded IVs/salts, deprecated primitives (MD5/SHA1 for security purposes).
 9. **Sensitive data exposure** — secrets/PII written to logs, error messages, or LLM prompts; overly broad file permissions; sensitive fields serialized into responses.
 10. **Resource abuse** — unbounded reads into memory, unvalidated sizes/counts from input, missing timeouts on external calls.
+11. **Error-text passthrough on a NEW surface** — a new mount, gateway, adapter, or endpoint that
+    writes an upstream/middleware error's text (`err.Error()`, connect/gRPC `Message()`, a wrapped
+    library message) into its own response body. `fs_grep` the new surface's response writers for
+    interpolated error strings. Default expectation: fixed strings per error class; passthrough
+    needs POSITIVE justification (the upstream text is a documented, stable, caller-facing
+    contract). "The same principal already sees this text on another surface" is NOT a clearance
+    — upstream strings are not a stable contract, grow internal detail over time (verifier
+    internals, allow-list names, hostnames), and the new surface may acquire callers with
+    different trust. Medium by default; High when the passed-through source is an authorizer,
+    token verifier, or anything that names internal identifiers.
 
 ## Ground-truth verification (verify, don't pattern-match)
 

scripts/docker-entrypoint.sh

@@ -0,0 +1,12 @@
+#!/bin/sh
+# Entrypoint for the coyote Docker image. Runs under tini:
+#   ENTRYPOINT ["/usr/bin/tini", "--", "/usr/local/bin/coyote-entrypoint"]
+#
+# tini (PID 1) reaps orphaned processes and forwards signals; coyote is not an
+# init and does neither.
+
+case "$1" in
+  sh | bash | /*) exec "$@" ;;
+esac
+
+exec coyote "$@"

scripts/usage-probe-hooks.sh

@@ -1,232 +0,0 @@
-#!/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/completer.rs

@@ -1,7 +1,9 @@
 use crate::client::{ModelType, list_models};
 use crate::config::paths;
-use crate::config::{AppConfig, Config, list_agents_with_descriptions, list_sessions};
-use crate::utils::list_file_names;
+use crate::config::{
+    AppConfig, Config, labeled_session_names, list_agents_with_descriptions, sanitize_display_text,
+    session_scope_dirs,
+};
 use crate::vault::Vault;
 use clap_complete::{CompletionCandidate, Shell, generate};
 use clap_complete_nushell::Nushell;
@@ -51,12 +53,12 @@ pub(super) fn model_completer(current: &OsStr) -> Vec<CompletionCandidate> {
 fn load_app_config_for_completion() -> anyhow::Result<AppConfig> {
     let h = tokio::runtime::Handle::try_current().ok();
     let cfg = match h {
-        Some(handle) => {
-            tokio::task::block_in_place(|| handle.block_on(Config::load_with_interpolation(true)))?
-        }
+        Some(handle) => tokio::task::block_in_place(|| {
+            handle.block_on(Config::load_with_interpolation(true, true))
+        })?,
         None => {
             let rt = tokio::runtime::Runtime::new()?;
-            rt.block_on(Config::load_with_interpolation(true))?
+            rt.block_on(Config::load_with_interpolation(true, true))?
         }
     };
     AppConfig::from_config(cfg)
@@ -115,7 +117,11 @@ pub(super) fn bundle_completer(current: &OsStr) -> Vec<CompletionCandidate> {
 }
 
 fn extract_agent_from_args() -> Option<String> {
-    let args: Vec<String> = env::args().collect();
+    extract_agent_from_args_in(env::args())
+}
+
+fn extract_agent_from_args_in<I: IntoIterator<Item = String>>(args: I) -> Option<String> {
+    let args: Vec<String> = args.into_iter().collect();
     let mut i = 0;
     while i < args.len() {
         let arg = &args[i];
@@ -134,19 +140,21 @@ fn extract_agent_from_args() -> Option<String> {
 }
 
 pub(super) fn session_completer(current: &OsStr) -> Vec<CompletionCandidate> {
-    let cur = current.to_string_lossy();
+    session_candidates(
+        &current.to_string_lossy(),
+        extract_agent_from_args().as_deref(),
+    )
+}
 
-    let sessions = if let Some(agent_name) = extract_agent_from_args() {
-        let sessions_dir = paths::agent_data_dir(&agent_name).join("sessions");
-        list_file_names(sessions_dir, ".yaml")
-    } else {
-        list_sessions()
-    };
-
-    sessions
+fn session_candidates(cur: &str, agent: Option<&str>) -> Vec<CompletionCandidate> {
+    let (workspace_dir, global_dir) = session_scope_dirs(agent);
+    labeled_session_names(&workspace_dir, &global_dir)
         .into_iter()
-        .filter(|s| s.starts_with(&*cur))
-        .map(CompletionCandidate::new)
+        .filter(|(name, _)| name.starts_with(cur))
+        .map(|(name, scope)| {
+            CompletionCandidate::new(sanitize_display_text(&name))
+                .help(Some(scope.to_string().into()))
+        })
         .collect()
 }
 
@@ -194,3 +202,112 @@ pub(super) fn secrets_completer(current: &OsStr) -> Vec<CompletionCandidate> {
         Err(_) => vec![],
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::config::default_sessions_dir;
+    use crate::testing::{EnvVarGuard, TestConfigDirGuard};
+    use serial_test::serial;
+    use std::path::Path;
+
+    fn seed(dir: &Path, name: &str) {
+        fs::create_dir_all(dir).unwrap();
+        fs::write(dir.join(format!("{name}.yaml")), "model: x\n").unwrap();
+    }
+
+    fn labeled(candidates: Vec<CompletionCandidate>) -> Vec<(String, Option<String>)> {
+        candidates
+            .into_iter()
+            .map(|c| {
+                (
+                    c.get_value().to_string_lossy().into_owned(),
+                    c.get_help().map(|h| h.to_string()),
+                )
+            })
+            .collect()
+    }
+
+    #[test]
+    #[serial]
+    fn session_completer_labels_scope_and_prefers_workspace() {
+        let _guard = TestConfigDirGuard::new("cli-session-completer");
+        seed(&paths::workspace_sessions_dir(), "both");
+        seed(&default_sessions_dir(), "both");
+        seed(&default_sessions_dir(), "only-global");
+        seed(&paths::workspace_sessions_dir(), "only-ws");
+
+        assert_eq!(
+            labeled(session_completer(OsStr::new(""))),
+            vec![
+                ("both".to_string(), Some("workspace".to_string())),
+                ("only-ws".to_string(), Some("workspace".to_string())),
+                ("only-global".to_string(), Some("global".to_string())),
+            ]
+        );
+        assert_eq!(
+            labeled(session_completer(OsStr::new("on"))),
+            vec![
+                ("only-ws".to_string(), Some("workspace".to_string())),
+                ("only-global".to_string(), Some("global".to_string())),
+            ]
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn session_candidates_use_the_agent_scope_dirs() {
+        let _guard = TestConfigDirGuard::new("cli-agent-session-completer");
+        let _agent_data_dir = EnvVarGuard::unset("A_DATA_DIR");
+        seed(&paths::workspace_agent_sessions_dir("a"), "both");
+        seed(&paths::agent_sessions_dir("a"), "both");
+        seed(&paths::agent_sessions_dir("a"), "agent-global");
+        seed(&default_sessions_dir(), "plain-global");
+
+        assert_eq!(
+            labeled(session_candidates("", Some("a"))),
+            vec![
+                ("both".to_string(), Some("workspace".to_string())),
+                ("agent-global".to_string(), Some("global".to_string())),
+            ]
+        );
+        assert_eq!(
+            labeled(session_candidates("", None)),
+            vec![("plain-global".to_string(), Some("global".to_string()))]
+        );
+    }
+
+    #[test]
+    fn extract_agent_from_args_in_reads_both_flag_forms() {
+        fn args(s: &str) -> Vec<String> {
+            s.split_whitespace().map(str::to_string).collect()
+        }
+        assert_eq!(
+            extract_agent_from_args_in(args("coyote --agent a --session x")),
+            Some("a".to_string())
+        );
+        assert_eq!(
+            extract_agent_from_args_in(args("coyote -a b")),
+            Some("b".to_string())
+        );
+        assert_eq!(
+            extract_agent_from_args_in(args("coyote --agent=c")),
+            Some("c".to_string())
+        );
+        assert_eq!(extract_agent_from_args_in(args("coyote --agent")), None);
+        assert_eq!(extract_agent_from_args_in(args("coyote --session x")), None);
+    }
+
+    #[test]
+    #[serial]
+    fn config_dir_guard_clears_and_restores_the_sessions_dir_override() {
+        let key = crate::utils::get_env_name("sessions_dir");
+        let junk = std::path::PathBuf::from("/nonexistent/junk-sessions");
+        let _outer = EnvVarGuard::set(&key, &junk);
+        {
+            let guard = TestConfigDirGuard::new("cli-sessions-dir-guard");
+            assert!(default_sessions_dir().starts_with(&guard.path));
+        }
+        assert_eq!(default_sessions_dir(), junk);
+    }
+}

src/client/azure_openai.rs

@@ -4,13 +4,15 @@ use super::*;
 use anyhow::Result;
 use serde::Deserialize;
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct AzureOpenAIConfig {
     pub name: Option<String>,
     pub api_base: Option<String>,
     pub api_key: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }

src/client/bedrock.rs

@@ -16,7 +16,7 @@ use reqwest::{Client as ReqwestClient, Method, RequestBuilder};
 use serde::Deserialize;
 use serde_json::{Value, json};
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct BedrockConfig {
     pub name: Option<String>,
     pub access_key_id: Option<String>,
@@ -25,6 +25,8 @@ pub struct BedrockConfig {
     pub session_token: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub prompt_cache: Option<bool>,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
@@ -423,6 +425,7 @@ fn build_chat_completions_body(
                     tool_results,
                     text,
                     sequence,
+                    round_starts,
                 }) => {
                     if !sequence {
                         let mut assistant_parts = vec![];
@@ -472,11 +475,15 @@ fn build_chat_completions_body(
                         }
                     } else {
                         // One pair per round: Claude can reuse tool_use IDs across API calls.
-                        // A round boundary is detected by the presence of round text, but
-                        // rounds where the model emitted only tool calls (no narration)
-                        // carry no text marker. As a backstop, also split whenever a
-                        // toolUseId would repeat within the current assistant message.
-                        // Converse rejects duplicate toolUseIds in a single message.
+                        // Round boundaries are recorded in `round_starts` at merge time.
+                        // Splitting per round also keeps the serialized history append-only
+                        // across tool-loop iterations, so prompt caching keeps hitting on
+                        // earlier rounds instead of rewriting them every request.
+                        // Sessions recorded before round tracking carry no `round_starts`;
+                        // for those, fall back to the presence of round text, plus an ID
+                        // backstop: split whenever a toolUseId would repeat within the
+                        // current assistant message. Converse rejects duplicate toolUseIds
+                        // in a single message.
                         let mut messages = vec![];
                         let mut assistant_parts: Vec<Value> = vec![];
                         let mut user_parts: Vec<Value> = vec![];
@@ -487,7 +494,11 @@ fn build_chat_completions_body(
                                 .id
                                 .as_deref()
                                 .is_some_and(|id| chunk_ids.contains(id));
-                            if index > 0 && (tool_result.text.is_some() || id_collision) {
+                            if index > 0
+                                && (round_starts.contains(&index)
+                                    || tool_result.text.is_some()
+                                    || id_collision)
+                            {
                                 messages.push(
                                     json!({ "role": "assistant", "content": assistant_parts }),
                                 );
@@ -896,6 +907,7 @@ mod tests {
                         tool_results,
                         text: text.to_string(),
                         sequence,
+                        round_starts: vec![],
                     }),
                 ),
             ],
@@ -912,6 +924,29 @@ mod tests {
         build_body_with(tool_results, "", true)
     }
 
+    fn build_body_rounds(tool_results: Vec<ToolResult>, round_starts: Vec<usize>) -> Value {
+        let data = ChatCompletionsData {
+            messages: vec![
+                Message::new(MessageRole::User, MessageContent::Text("hello".to_string())),
+                Message::new(
+                    MessageRole::Assistant,
+                    MessageContent::ToolCalls(MessageContentToolCalls {
+                        tool_results,
+                        text: String::new(),
+                        sequence: true,
+                        round_starts,
+                    }),
+                ),
+            ],
+            temperature: None,
+            top_p: None,
+            reasoning_effort: None,
+            functions: None,
+            stream: false,
+        };
+        build_chat_completions_body(data, &Model::new("bedrock", "test"), false).unwrap()
+    }
+
     fn tool_result_content_block(output: Value) -> Value {
         let body = build_body(vec![tool_result(output)]);
         body["messages"][2]["content"][0]["toolResult"]["content"][0].clone()
@@ -1067,6 +1102,9 @@ mod tests {
         assert_unique_tool_use_ids_per_message(&body);
     }
 
+    /// Legacy sessions recorded before round tracking carry no
+    /// `round_starts`; without a text marker or an ID collision their
+    /// textless rounds still serialize merged (the pre-round-tracking shape).
     #[test]
     fn sequence_keeps_textless_rounds_merged_when_ids_are_unique() {
         let body = build_body(vec![
@@ -1081,6 +1119,64 @@ mod tests {
         assert_unique_tool_use_ids_per_message(&body);
     }
 
+    /// Regression: textless tool-loop rounds must split into one
+    /// assistant/user pair per recorded round so the serialized history stays
+    /// append-only across iterations and prompt caching keeps hitting on
+    /// earlier rounds (mirrors the claude client's round_starts handling).
+    #[test]
+    fn sequence_splits_on_round_starts_without_text() {
+        let body = build_body_rounds(
+            vec![
+                sequence_tool_result("toolu_A", None),
+                sequence_tool_result("toolu_B", None),
+                sequence_tool_result("toolu_C", None),
+            ],
+            vec![1, 2],
+        );
+
+        let messages = body["messages"].as_array().unwrap();
+
+        // user + 3 × (assistant, user) — one pair per round.
+        assert_eq!(messages.len(), 7, "body: {body}");
+        for pair in messages[1..].chunks(2) {
+            assert_eq!(pair[0]["role"], "assistant", "body: {body}");
+            assert_eq!(pair[0]["content"].as_array().unwrap().len(), 1);
+            assert_eq!(pair[1]["role"], "user", "body: {body}");
+        }
+        assert_unique_tool_use_ids_per_message(&body);
+    }
+
+    /// The serialized history must be append-only across tool-loop
+    /// iterations: request N+1's messages must start with exactly request N's
+    /// messages, so the prompt-cache prefix keeps matching.
+    #[test]
+    fn round_history_is_append_only_across_iterations() {
+        let two = build_body_rounds(
+            vec![
+                sequence_tool_result("toolu_A", None),
+                sequence_tool_result("toolu_B", None),
+            ],
+            vec![1],
+        );
+        let three = build_body_rounds(
+            vec![
+                sequence_tool_result("toolu_A", None),
+                sequence_tool_result("toolu_B", None),
+                sequence_tool_result("toolu_C", None),
+            ],
+            vec![1, 2],
+        );
+
+        let two_messages = two["messages"].as_array().unwrap();
+        let three_messages = three["messages"].as_array().unwrap();
+
+        assert_eq!(
+            &three_messages[..two_messages.len()],
+            &two_messages[..],
+            "two: {two}, three: {three}"
+        );
+    }
+
     #[test]
     fn non_sequence_emits_assistant_user_pair() {
         let body = build_body_with(

src/client/catalog.rs

@@ -572,7 +572,7 @@ pub(crate) fn name_overlap(old: &[String], new: &[String]) -> f64 {
     kept as f64 / old.len() as f64
 }
 
-fn overlay_hand_owned(hand: ModelData, api: ModelData) -> ModelData {
+pub(crate) fn overlay_hand_owned(hand: ModelData, api: ModelData) -> ModelData {
     ModelData {
         name: hand.name,
         model_type: hand.model_type,
@@ -604,6 +604,23 @@ fn overlay_hand_owned(hand: ModelData, api: ModelData) -> ModelData {
     }
 }
 
+pub(crate) fn extend_catalog_models(
+    catalog: &[ModelData],
+    overrides: &[ModelData],
+) -> Vec<ModelData> {
+    let mut models = catalog.to_vec();
+    for override_model in overrides {
+        match models.iter_mut().find(|model| {
+            model.name == override_model.name && model.model_type == override_model.model_type
+        }) {
+            Some(model) => *model = overlay_hand_owned(override_model.clone(), model.clone()),
+            None => models.push(override_model.clone()),
+        }
+    }
+
+    models
+}
+
 #[derive(Debug, Clone, Serialize, Deserialize)]
 #[serde(deny_unknown_fields)]
 pub struct ProviderQuirks {
@@ -1724,4 +1741,47 @@ rules:
             );
         }
     }
+
+    fn typed_model(name: &str, model_type: &str) -> ModelData {
+        ModelData {
+            name: name.to_string(),
+            model_type: model_type.to_string(),
+            ..Default::default()
+        }
+    }
+
+    #[test]
+    fn extend_catalog_models_merges_collisions_field_wise() {
+        let mut catalog_model = ModelData::new("m");
+        catalog_model.max_input_tokens = Some(100_000);
+        catalog_model.input_price = Some(1.0);
+        catalog_model.supports_vision = true;
+        let mut override_model = ModelData::new("m");
+        override_model.input_price = Some(9.0);
+
+        let merged = extend_catalog_models(&[catalog_model], &[override_model]);
+        assert_eq!(merged.len(), 1);
+        assert_eq!(merged[0].input_price, Some(9.0));
+        assert_eq!(merged[0].max_input_tokens, Some(100_000));
+        assert!(merged[0].supports_vision);
+    }
+
+    #[test]
+    fn extend_catalog_models_appends_net_new_after_catalog() {
+        let catalog = [ModelData::new("a"), ModelData::new("b")];
+        let merged = extend_catalog_models(&catalog, &[ModelData::new("c")]);
+        let names: Vec<&str> = merged.iter().map(|model| model.name.as_str()).collect();
+        assert_eq!(names, ["a", "b", "c"]);
+    }
+
+    #[test]
+    fn extend_catalog_models_collides_on_name_and_type() {
+        let mut catalog_model = typed_model("m", "embedding");
+        catalog_model.default_chunk_size = Some(1500);
+        let merged = extend_catalog_models(&[catalog_model], &[typed_model("m", "reranker")]);
+        assert_eq!(merged.len(), 2);
+        assert_eq!(merged[0].model_type, "embedding");
+        assert_eq!(merged[0].default_chunk_size, Some(1500));
+        assert_eq!(merged[1].model_type, "reranker");
+    }
 }

src/client/claude.rs

@@ -15,7 +15,7 @@ use serde_json::{Value, json};
 const API_BASE: &str = "https://api.anthropic.com/v1";
 const CLAUDE_CODE_PREFIX: &str = "You are Claude Code, Anthropic's official CLI for Claude.";
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct ClaudeConfig {
     pub name: Option<String>,
     pub api_key: Option<String>,
@@ -24,6 +24,8 @@ pub struct ClaudeConfig {
     pub oauth: Option<Box<OAuthConfig>>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub prompt_cache: Option<bool>,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
@@ -401,6 +403,7 @@ pub fn claude_build_chat_completions_body(
                     tool_results,
                     text,
                     sequence,
+                    round_starts,
                 }) => {
                     if !sequence {
                         let mut assistant_parts = vec![];
@@ -456,14 +459,18 @@ pub fn claude_build_chat_completions_body(
                         }
                     } else {
                         // One pair per round: Claude can reuse tool_use IDs across API calls.
-                        // A round boundary is detected by the presence of round text, but
-                        // rounds where the model emitted only tool calls (no narration)
-                        // carry no text marker. As a backstop, also split whenever a
-                        // tool_use ID would repeat within the current assistant message —
-                        // the API rejects duplicate tool_use IDs in a single message.
+                        // Round boundaries are recorded in `round_starts` at merge time.
+                        // Splitting per round also keeps the serialized history append-only
+                        // across tool-loop iterations, so prefix-based prompt caching keeps
+                        // hitting on earlier rounds instead of rewriting them every request.
+                        // Sessions recorded before round tracking carry no `round_starts`;
+                        // for those, fall back to the presence of round text, plus an ID
+                        // backstop: split whenever a tool_use ID would repeat within the
+                        // current assistant message — the API rejects duplicate tool_use
+                        // IDs in a single message.
                         let mut messages = vec![];
-                        let mut assistant_parts: Vec<serde_json::Value> = vec![];
-                        let mut user_parts: Vec<serde_json::Value> = vec![];
+                        let mut assistant_parts: Vec<Value> = vec![];
+                        let mut user_parts: Vec<Value> = vec![];
                         let mut chunk_ids: HashSet<&str> = HashSet::new();
                         for (index, tool_result) in tool_results.iter().enumerate() {
                             let id_collision = tool_result
@@ -471,7 +478,11 @@ pub fn claude_build_chat_completions_body(
                                 .id
                                 .as_deref()
                                 .is_some_and(|id| chunk_ids.contains(id));
-                            if index > 0 && (tool_result.text.is_some() || id_collision) {
+                            if index > 0
+                                && (round_starts.contains(&index)
+                                    || tool_result.text.is_some()
+                                    || id_collision)
+                            {
                                 messages.push(
                                     json!({ "role": "assistant", "content": assistant_parts }),
                                 );
@@ -735,6 +746,7 @@ mod tests {
                         tool_results,
                         text: text.to_string(),
                         sequence,
+                        round_starts: vec![],
                     }),
                 ),
             ],
@@ -752,6 +764,30 @@ mod tests {
         build_body_with(tool_results, "", true, prompt_cache)
     }
 
+    fn build_body_rounds(tool_results: Vec<ToolResult>, round_starts: Vec<usize>) -> Value {
+        let data = ChatCompletionsData {
+            messages: vec![
+                Message::new(MessageRole::User, MessageContent::Text("hello".to_string())),
+                Message::new(
+                    MessageRole::Assistant,
+                    MessageContent::ToolCalls(MessageContentToolCalls {
+                        tool_results,
+                        text: String::new(),
+                        sequence: true,
+                        round_starts,
+                    }),
+                ),
+            ],
+            temperature: None,
+            top_p: None,
+            reasoning_effort: None,
+            functions: None,
+            stream: false,
+        };
+        claude_build_chat_completions_body(data, &Model::new("claude", "claude-test"), false)
+            .unwrap()
+    }
+
     fn multi_turn_data(functions: Option<Vec<FunctionDeclaration>>) -> ChatCompletionsData {
         ChatCompletionsData {
             messages: vec![
@@ -823,6 +859,63 @@ mod tests {
         assert_unique_tool_use_ids_per_message(&body);
     }
 
+    /// Regression: tool-loop rounds where the model emitted no narration text
+    /// (the norm with thinking models) must still serialize as one
+    /// assistant/user pair per round. Collapsing them into one growing pair
+    /// rewrites the whole accumulated history on every request, which defeats
+    /// prefix-based prompt caching (cache reads stall at the system prompt).
+    #[test]
+    fn sequence_splits_on_round_starts_without_text() {
+        let body = build_body_rounds(
+            vec![
+                tool_result("toolu_A", None),
+                tool_result("toolu_B", None),
+                tool_result("toolu_C", None),
+            ],
+            vec![1, 2],
+        );
+
+        let messages = body["messages"].as_array().unwrap();
+
+        // user + 3 × (assistant, user) — one pair per round.
+        assert_eq!(messages.len(), 7, "body: {body}");
+        for pair in messages[1..].chunks(2) {
+            assert_eq!(pair[0]["role"], "assistant", "body: {body}");
+            assert_eq!(pair[0]["content"].as_array().unwrap().len(), 1);
+            assert_eq!(pair[1]["role"], "user", "body: {body}");
+        }
+        assert_unique_tool_use_ids_per_message(&body);
+    }
+
+    /// The serialized history must be append-only across tool-loop
+    /// iterations: request N+1's messages must start with exactly request N's
+    /// messages, so the prompt-cache prefix keeps matching and the cache read
+    /// grows monotonically instead of re-writing every round each request.
+    #[test]
+    fn round_history_is_append_only_across_iterations() {
+        let two = build_body_rounds(
+            vec![tool_result("toolu_A", None), tool_result("toolu_B", None)],
+            vec![1],
+        );
+        let three = build_body_rounds(
+            vec![
+                tool_result("toolu_A", None),
+                tool_result("toolu_B", None),
+                tool_result("toolu_C", None),
+            ],
+            vec![1, 2],
+        );
+
+        let two_messages = two["messages"].as_array().unwrap();
+        let three_messages = three["messages"].as_array().unwrap();
+
+        assert_eq!(
+            &three_messages[..two_messages.len()],
+            &two_messages[..],
+            "two: {two}, three: {three}"
+        );
+    }
+
     #[test]
     fn sequence_splits_on_reused_id_in_textless_round() {
         let body = build_body(
@@ -840,6 +933,9 @@ mod tests {
         assert_unique_tool_use_ids_per_message(&body);
     }
 
+    /// Legacy sessions recorded before round tracking carry no
+    /// `round_starts`; without a text marker or an ID collision their
+    /// textless rounds still serialize merged (the pre-round-tracking shape).
     #[test]
     fn sequence_keeps_textless_rounds_merged_when_ids_are_unique() {
         let body = build_body(
@@ -1028,16 +1124,12 @@ mod tests {
     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,
+            ..Default::default()
         }
     }
 

src/client/cohere.rs

@@ -16,6 +16,8 @@ pub struct CohereConfig {
     pub api_base: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }

src/client/common.rs

@@ -420,6 +420,15 @@ impl TokenUsage {
             && self.cache_read_input_tokens.is_none()
     }
 
+    /// Prompt-side tokens the API reported for one request: fresh input plus
+    /// cache writes and cache reads. The buckets are disjoint (see
+    /// [`Self::cost_usd`]), so the terms sum without adjustment.
+    pub fn total_prompt_tokens(&self) -> u64 {
+        self.input_tokens.unwrap_or(0)
+            + self.cache_creation_input_tokens.unwrap_or(0)
+            + self.cache_read_input_tokens.unwrap_or(0)
+    }
+
     pub fn accumulate(&mut self, other: &TokenUsage) {
         fn add(acc: &mut Option<u64>, value: Option<u64>) {
             if let Some(value) = value {
@@ -613,9 +622,9 @@ fn llm_failed_extras(
     }
     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:#}"))
+        // The immediate error only, matching COYOTE_TOOL_ERROR; the context
+        // chain below it stays out of the env.
+        err.map(|err| err.to_string())
             .unwrap_or_else(|| "Aborted.".to_string()),
     ));
 
@@ -1896,12 +1905,10 @@ mod tests {
             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_eq!(
+            failed.envs.get("COYOTE_LLM_ERROR").map(String::as_str),
+            Some("Failed to call chat-completions api"),
+            "the env must carry the immediate error only, not the context chain"
         );
         assert!(!failed.envs.contains_key("COYOTE_LLM_DURATION_MS"));
     }

src/client/gemini.rs

@@ -20,6 +20,8 @@ pub struct GeminiConfig {
     pub oauth: Option<Box<OAuthConfig>>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }

src/client/macros.rs

@@ -51,15 +51,24 @@ macro_rules! register_client {
 
                 pub fn list_models(local_config: &$config) -> Vec<Model> {
                     let client_name = Self::name(local_config);
-                    if local_config.models.is_empty() {
-                        if let Some(v) = $crate::client::ALL_PROVIDER_MODELS.iter().find(|v| {
+                    let find_catalog = || $crate::client::ALL_PROVIDER_MODELS.iter().find(|v| {
                         v.provider == $name ||
                             ($name == OpenAICompatibleClient::NAME
                                 && local_config.name.as_ref().map(|name| name.starts_with(&v.provider)).unwrap_or_default())
-                        }) {
-                            return Model::from_config(client_name, &v.models);
+                    });
+                    if local_config.models.is_empty() {
+                        match find_catalog() {
+                            Some(v) => Model::from_config(client_name, &v.models),
+                            None => vec![],
+                        }
+                    } else if local_config.extend_models {
+                        match find_catalog() {
+                            Some(v) => Model::from_config(
+                                client_name,
+                                &$crate::client::catalog::extend_catalog_models(&v.models, &local_config.models),
+                            ),
+                            None => Model::from_config(client_name, &local_config.models),
                         }
-                        vec![]
                     } else {
                         Model::from_config(client_name, &local_config.models)
                     }

src/client/message.rs

@@ -216,6 +216,16 @@ pub struct MessageContentToolCalls {
     pub tool_results: Vec<ToolResult>,
     pub text: String,
     pub sequence: bool,
+    /// Indices into `tool_results` where a new tool-call round begins (the
+    /// first round implicitly starts at index 0). Recorded by `merge()` on
+    /// every merge, so serializers can emit one assistant/user pair per
+    /// round even when the model produced no narration text for a round.
+    /// Keeping each round in its own message pair makes the request history
+    /// append-only across tool-loop iterations, which prefix-based prompt
+    /// caches require to produce growing cache reads instead of rewriting
+    /// the whole accumulated history on every request.
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
+    pub round_starts: Vec<usize>,
 }
 
 impl MessageContentToolCalls {
@@ -224,6 +234,7 @@ impl MessageContentToolCalls {
             tool_results,
             text,
             sequence: false,
+            round_starts: vec![],
         }
     }
 
@@ -233,6 +244,9 @@ impl MessageContentToolCalls {
         {
             first.text = Some(text);
         }
+        if !self.tool_results.is_empty() && !tool_results.is_empty() {
+            self.round_starts.push(self.tool_results.len());
+        }
         self.tool_results.extend(tool_results);
         self.sequence = true;
     }
@@ -358,4 +372,56 @@ mod tests {
         let restored: Vec<ThinkingBlock> = serde_yaml::from_str(&yaml).unwrap();
         assert_eq!(serde_json::to_value(&restored).unwrap(), json);
     }
+
+    /// Session files recorded before round tracking carry no `round_starts`
+    /// key — they must deserialize to an empty default, and an empty
+    /// `round_starts` must be skipped on serialize so new files keep the old
+    /// shape until a merge actually records a round boundary.
+    #[test]
+    fn tool_calls_round_starts_defaults_and_skips_when_empty() {
+        let json = json!({
+            "tool_results": [],
+            "text": "t",
+            "sequence": true,
+        });
+
+        let parsed: MessageContentToolCalls = serde_json::from_value(json).unwrap();
+        assert!(parsed.round_starts.is_empty());
+
+        let serialized = serde_json::to_value(&parsed).unwrap();
+        assert!(
+            serialized.get("round_starts").is_none(),
+            "serialized: {serialized}"
+        );
+    }
+
+    #[test]
+    fn tool_calls_round_starts_round_trip_through_yaml() {
+        let mut tool_calls = MessageContentToolCalls::new(vec![], "t".to_string());
+        tool_calls.round_starts = vec![1, 3];
+
+        let yaml = serde_yaml::to_string(&tool_calls).unwrap();
+        let restored: MessageContentToolCalls = serde_yaml::from_str(&yaml).unwrap();
+
+        assert_eq!(restored.round_starts, vec![1, 3]);
+    }
+
+    /// Each `merge()` call is one tool-loop round: the boundary index must be
+    /// recorded even when the model produced no narration text for the round.
+    #[test]
+    fn merge_records_round_start_per_call() {
+        let tool_result = |id: &str| {
+            crate::function::ToolResult::new(
+                crate::function::ToolCall::new("t".into(), json!({}), Some(id.to_string())),
+                json!("ok"),
+            )
+        };
+        let mut tool_calls = MessageContentToolCalls::new(vec![tool_result("a")], String::new());
+
+        tool_calls.merge(vec![tool_result("b"), tool_result("c")], String::new());
+        tool_calls.merge(vec![tool_result("d")], String::new());
+
+        assert!(tool_calls.sequence);
+        assert_eq!(tool_calls.round_starts, vec![1, 3]);
+    }
 }

src/client/model.rs

@@ -557,4 +557,96 @@ reasoning_levels: [none, low, medium, high]
             "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"
         );
     }
+
+    #[test]
+    fn config_models_replace_catalog_by_default() {
+        let ClientConfig::ClaudeConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: claude\nmodels:\n  - name: test-replace-model\n",
+        )
+        .unwrap() else {
+            panic!("expected a claude config");
+        };
+        assert!(!config.extend_models);
+
+        let models = crate::client::ClaudeClient::list_models(&config);
+        assert_eq!(models.len(), 1);
+        assert_eq!(models[0].name(), "test-replace-model");
+    }
+
+    #[test]
+    fn config_models_extend_catalog_when_flag_set() {
+        let ClientConfig::ClaudeConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: claude\nextend_models: true\nmodels:\n  - name: test-extra-model\n",
+        )
+        .unwrap() else {
+            panic!("expected a claude config");
+        };
+
+        let catalog_len = crate::client::ALL_PROVIDER_MODELS
+            .iter()
+            .find(|v| v.provider == "claude")
+            .map(|v| v.models.len())
+            .unwrap();
+        let models = crate::client::ClaudeClient::list_models(&config);
+        assert_eq!(models.len(), catalog_len + 1);
+        assert_eq!(models.last().unwrap().name(), "test-extra-model");
+    }
+
+    #[test]
+    fn extend_models_with_empty_models_returns_catalog_exactly() {
+        let ClientConfig::ClaudeConfig(config) =
+            serde_yaml::from_str::<ClientConfig>("type: claude\nextend_models: true\n").unwrap()
+        else {
+            panic!("expected a claude config");
+        };
+
+        let catalog = crate::client::ALL_PROVIDER_MODELS
+            .iter()
+            .find(|v| v.provider == "claude")
+            .unwrap();
+        let models = crate::client::ClaudeClient::list_models(&config);
+        assert_eq!(models.len(), catalog.models.len());
+        for (model, catalog_model) in models.iter().zip(catalog.models.iter()) {
+            assert_eq!(model.name(), catalog_model.name);
+        }
+    }
+
+    #[test]
+    fn extend_models_without_catalog_match_returns_config_models_only() {
+        let ClientConfig::OpenAICompatibleConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: openai-compatible\nname: no-such-provider-xyz\nextend_models: true\nmodels:\n  - name: test-only-model\n",
+        )
+        .unwrap() else {
+            panic!("expected an openai-compatible config");
+        };
+
+        assert!(
+            !crate::client::ALL_PROVIDER_MODELS
+                .iter()
+                .any(|v| "no-such-provider-xyz".starts_with(v.provider.as_str())),
+            "test premise: the client name must not prefix-match any catalog provider"
+        );
+        let models = crate::client::OpenAICompatibleClient::list_models(&config);
+        assert_eq!(models.len(), 1);
+        assert_eq!(models[0].name(), "test-only-model");
+    }
+
+    #[test]
+    fn extend_models_extends_catalog_via_provider_name_prefix_match() {
+        let ClientConfig::OpenAICompatibleConfig(config) = serde_yaml::from_str::<ClientConfig>(
+            "type: openai-compatible\nname: openrouter-custom\nextend_models: true\nmodels:\n  - name: test-net-new-model\n",
+        )
+        .unwrap() else {
+            panic!("expected an openai-compatible config");
+        };
+
+        let catalog_len = crate::client::ALL_PROVIDER_MODELS
+            .iter()
+            .find(|v| v.provider == "openrouter")
+            .map(|v| v.models.len())
+            .unwrap();
+        let models = crate::client::OpenAICompatibleClient::list_models(&config);
+        assert_eq!(models.len(), catalog_len + 1);
+        assert_eq!(models.last().unwrap().name(), "test-net-new-model");
+    }
 }

src/client/oauth.rs

@@ -1457,13 +1457,9 @@ echo_pkce_in_token_exchange: true
         ClientConfig::OpenAICompatibleConfig(OpenAICompatibleConfig {
             name: Some(name.into()),
             api_base: Some("https://api.example/v1".into()),
-            api_key: None,
             auth: auth.map(str::to_string),
             oauth: oauth.map(Box::new),
-            wire_api: None,
-            models: vec![],
-            patch: None,
-            extra: None,
+            ..Default::default()
         })
     }
 
@@ -1474,14 +1470,9 @@ echo_pkce_in_token_exchange: true
     ) -> 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,
+            ..Default::default()
         })
     }
 
@@ -1492,15 +1483,9 @@ echo_pkce_in_token_exchange: true
     ) -> 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,
+            ..Default::default()
         })
     }
 
@@ -1511,13 +1496,9 @@ echo_pkce_in_token_exchange: true
     ) -> 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,
+            ..Default::default()
         })
     }
 

src/client/openai.rs

@@ -24,6 +24,8 @@ pub struct OpenAIConfig {
     pub wire_api: Option<WireApi>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }
@@ -481,6 +483,7 @@ pub fn openai_build_chat_completions_body(data: ChatCompletionsData, model: &Mod
                         tool_results,
                         text,
                         sequence,
+                        ..
                     }) => {
                         // Empty tool_results (reachable via deserialized sessions) must not emit empty tool_calls.
                         if tool_results.is_empty() {
@@ -681,7 +684,7 @@ pub fn openai_build_responses_body(data: ChatCompletionsData, model: &Model) ->
                 MessageContent::ToolCalls(MessageContentToolCalls {
                     tool_results,
                     text,
-                    sequence: _,
+                    ..
                 }) => tool_results
                     .into_iter()
                     .enumerate()
@@ -868,17 +871,22 @@ fn reasoning_thinking_block(item: &Value) -> Option<ThinkingBlock> {
 }
 
 /// OpenAI reports cached input under `input_tokens_details` and has no
-/// cache-creation concept, so that field stays `None`.
+/// cache-creation concept, so that field stays `None`. The reported
+/// `input_tokens` total already includes cached reads, so cached tokens are
+/// subtracted here to keep the buckets disjoint like other providers.
 fn openai_parse_responses_usage(usage: &Value) -> Option<TokenUsage> {
     if !usage.is_object() {
         return None;
     }
 
+    let cached_tokens = usage["input_tokens_details"]["cached_tokens"].as_u64();
     Some(TokenUsage {
-        input_tokens: usage["input_tokens"].as_u64(),
+        input_tokens: usage["input_tokens"]
+            .as_u64()
+            .map(|v| v.saturating_sub(cached_tokens.unwrap_or(0))),
         output_tokens: usage["output_tokens"].as_u64(),
         cache_creation_input_tokens: None,
-        cache_read_input_tokens: usage["input_tokens_details"]["cached_tokens"].as_u64(),
+        cache_read_input_tokens: cached_tokens,
     })
 }
 
@@ -993,6 +1001,7 @@ mod tests {
                         tool_results: vec![],
                         text: "leftover text".to_string(),
                         sequence,
+                        round_starts: vec![],
                     }),
                 ),
             ],
@@ -1057,6 +1066,7 @@ mod tests {
                         tool_results,
                         text: "first round".to_string(),
                         sequence: false,
+                        round_starts: vec![],
                     }),
                 ),
             ],
@@ -1264,12 +1274,31 @@ mod tests {
         let output = openai_extract_responses(&data).unwrap();
 
         let usage = output.usage.unwrap();
-        assert_eq!(usage.input_tokens, Some(100));
+        assert_eq!(usage.input_tokens, Some(40));
         assert_eq!(usage.output_tokens, Some(20));
         assert_eq!(usage.cache_creation_input_tokens, None);
         assert_eq!(usage.cache_read_input_tokens, Some(60));
     }
 
+    #[test]
+    fn extract_responses_usage_without_cached_details_keeps_input_intact() {
+        let data = json!({
+            "output": [
+                { "type": "message", "content": [{ "type": "output_text", "text": "answer" }] },
+            ],
+            "usage": {
+                "input_tokens": 100,
+                "output_tokens": 20,
+            }
+        });
+
+        let output = openai_extract_responses(&data).unwrap();
+
+        let usage = output.usage.unwrap();
+        assert_eq!(usage.input_tokens, Some(100));
+        assert_eq!(usage.cache_read_input_tokens, None);
+    }
+
     #[test]
     fn extract_responses_without_usage_leaves_it_none() {
         let data = json!({
@@ -1354,7 +1383,7 @@ mod tests {
         assert!(done);
         let (_, _, _, usage) = handler.take();
         let usage = usage.unwrap();
-        assert_eq!(usage.input_tokens, Some(100));
+        assert_eq!(usage.input_tokens, Some(40));
         assert_eq!(usage.output_tokens, Some(20));
         assert_eq!(usage.cache_creation_input_tokens, None);
         assert_eq!(usage.cache_read_input_tokens, Some(60));
@@ -1464,7 +1493,7 @@ mod tests {
         let (text, _, _, usage) = handler.take();
         assert_eq!(text, "partial answer");
         let usage = usage.expect("usage should be recorded for truncated turns");
-        assert_eq!(usage.input_tokens, Some(50));
+        assert_eq!(usage.input_tokens, Some(25));
         assert_eq!(usage.output_tokens, Some(10));
         assert_eq!(usage.cache_read_input_tokens, Some(25));
     }

src/client/openai_compatible.rs

@@ -9,7 +9,7 @@ use serde::Deserialize;
 use serde_json::{Value, json};
 use oauth::OAuthConfig;
 
-#[derive(Debug, Clone, Deserialize)]
+#[derive(Debug, Clone, Deserialize, Default)]
 pub struct OpenAICompatibleConfig {
     pub name: Option<String>,
     pub api_base: Option<String>,
@@ -19,6 +19,8 @@ pub struct OpenAICompatibleConfig {
     pub wire_api: Option<WireApi>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
 }
@@ -274,12 +276,8 @@ mod tests {
             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,
+            ..Default::default()
         }
     }
 

src/client/vertexai.rs

@@ -18,6 +18,8 @@ pub struct VertexAIConfig {
     pub adc_file: Option<String>,
     #[serde(default)]
     pub models: Vec<ModelData>,
+    #[serde(default)]
+    pub extend_models: bool,
     pub prompt_cache: Option<bool>,
     pub patch: Option<RequestPatch>,
     pub extra: Option<ExtraConfig>,
@@ -600,6 +602,7 @@ mod tests {
                         tool_results: vec![],
                         text: "leftover text".to_string(),
                         sequence: false,
+                        round_starts: vec![],
                     }),
                 ),
             ],

src/config/agent.rs

@@ -1,6 +1,6 @@
 use super::*;
 
-use crate::hooks::HooksMap;
+use crate::hooks::{HooksMap, RagSyncHooks};
 use crate::{
     client::Model,
     config::memory,
@@ -14,11 +14,13 @@ use crate::{
 
 use super::rag_cache::RagKey;
 use crate::config::builtin_manifest;
+use crate::config::conflict::{self, InstallMode, StickyMode};
 use crate::config::paths;
 use crate::config::prompts::{
     DEFAULT_JOB_INSTRUCTIONS, DEFAULT_SPAWN_INSTRUCTIONS, DEFAULT_TEAMMATE_INSTRUCTIONS,
     DEFAULT_TODO_INSTRUCTIONS, DEFAULT_USER_INTERACTION_INSTRUCTIONS,
 };
+use crate::function::write_file_atomic;
 use crate::graph::types::RagNode;
 use crate::graph::{Graph, GraphParser, NodeType};
 use crate::mcp::McpServerFeatures;
@@ -29,8 +31,8 @@ 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};
+use std::collections::{BTreeMap, BTreeSet};
+use std::{env, path::Path};
 
 const DEFAULT_AGENT_NAME: &str = "rag";
 
@@ -63,6 +65,101 @@ fn direct_hook_name(rest: &str) -> Option<&str> {
     (!name.is_empty() && !name.contains('/')).then_some(name)
 }
 
+/// Installs one bundled agent's hook scripts under `<agent>/hooks/` and
+/// reconciles that directory through its builtin manifest, mirroring the
+/// role-side hook installer.
+pub(crate) fn install_and_reconcile_agent_hooks(
+    agent: &str,
+    shipped: &[(String, String)],
+    mode: InstallMode,
+    sticky: &mut StickyMode,
+) -> Result<()> {
+    let dir = paths::agents_data_dir().join(agent).join("hooks");
+    let mut written = BTreeSet::new();
+    for (name, content) in shipped {
+        let path = dir.join(name);
+        if path.exists()
+            && !conflict::should_replace_existing(&path, content, "agents", mode, sticky)?
+        {
+            debug!(
+                "Agent hook file already exists, skipping: {}",
+                path.display()
+            );
+            continue;
+        }
+        ensure_parent_exists(&path)?;
+        info!("Creating agent hook file: {}", path.display());
+        write_file_atomic(&path, content, None)?;
+        set_executable_bit_if_script(&path)?;
+        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 the install, matching the role-side policy.
+    if let Err(err) = builtin_manifest::reconcile_builtin_dir(&dir, &names, &written) {
+        warn!("Failed to reconcile builtin hooks for agent '{agent}': {err}");
+    }
+    Ok(())
+}
+
+/// An agent the embed stopped bundling is never visited by the per-agent
+/// reconcile loop, so its installed hooks and manifest would orphan forever.
+/// Any agent directory that carries a builtin hooks manifest but is absent
+/// from the current embed gets its manifest-owned hooks removed, each
+/// deletion logged individually by the reconcile. Only the installer writes
+/// manifests, but a manual copy of a builtin agent directory carries the
+/// hidden manifest along: files it lists are treated as installer-owned and
+/// swept, while files absent from the manifest always survive.
+/// Best-effort: a failure here must not abort the install.
+fn sweep_removed_agent_hooks(bundled_files: &HashMap<String, HashSet<String>>) {
+    let entries = match read_dir(paths::agents_data_dir()) {
+        Ok(entries) => entries,
+        Err(err) => {
+            warn!("Failed to scan agents dir for removed-agent hooks: {err}");
+            return;
+        }
+    };
+    for entry in entries.flatten() {
+        let name = entry.file_name();
+        let Some(name) = name.to_str() else {
+            continue;
+        };
+        if bundled_files.contains_key(name) {
+            continue;
+        }
+        // A symlinked agent dir is user-arranged: never follow it into a
+        // hooks tree that lives somewhere else.
+        if !entry
+            .path()
+            .symlink_metadata()
+            .is_ok_and(|metadata| metadata.is_dir())
+        {
+            continue;
+        }
+        let hooks_dir = entry.path().join("hooks");
+        if !hooks_dir
+            .join(builtin_manifest::BUILTIN_MANIFEST_FILE)
+            .is_file()
+        {
+            continue;
+        }
+        info!(
+            "Removing hooks shipped by removed built-in agent '{name}' in {}",
+            hooks_dir.display()
+        );
+        if let Err(err) =
+            builtin_manifest::reconcile_builtin_dir(&hooks_dir, &BTreeSet::new(), &BTreeSet::new())
+        {
+            warn!("Failed to reconcile builtin hooks for removed agent '{name}': {err}");
+            continue;
+        }
+        // remove_dir only succeeds on an empty directory, so a user file
+        // left behind keeps the directory in place.
+        let _ = fs::remove_dir(&hooks_dir);
+    }
+}
+
 #[derive(Debug, Clone)]
 pub struct Agent {
     name: String,
@@ -81,28 +178,32 @@ pub struct Agent {
 }
 
 impl Agent {
-    pub fn install_builtin_agents(force: bool) -> Result<()> {
+    pub fn install_builtin_agents(mode: InstallMode) -> Result<()> {
         info!(
             "Installing built-in agents in {}",
             paths::agents_data_dir().display()
         );
 
+        let mut sticky = StickyMode::None;
         let mut written_hooks: HashMap<String, BTreeSet<String>> = HashMap::new();
         for file in AgentAssets::iter() {
             debug!("Processing agent file: {}", file.as_ref());
 
             let embedded_file = AgentAssets::get(&file)
                 .ok_or_else(|| anyhow!("Failed to load embedded agent file: {}", file.as_ref()))?;
-            let content = unsafe { std::str::from_utf8_unchecked(&embedded_file.data) };
+            let content = std::str::from_utf8(&embedded_file.data)
+                .expect("bundled agent asset is not valid UTF-8");
             let file_path = paths::agents_data_dir().join(file.as_ref());
-            let file_extension = file_path
-                .extension()
-                .and_then(OsStr::to_str)
-                .map(|s| s.to_lowercase());
-            #[cfg_attr(not(unix), expect(unused))]
-            let is_script = matches!(file_extension.as_deref(), Some("sh") | Some("py"));
 
-            if file_path.exists() && !force {
+            if file_path.exists()
+                && !conflict::should_replace_existing(
+                    &file_path,
+                    content,
+                    "agents",
+                    mode,
+                    &mut sticky,
+                )?
+            {
                 debug!(
                     "Agent file already exists, skipping: {}",
                     file_path.display()
@@ -114,18 +215,13 @@ impl Agent {
             info!("Creating agent file: {}", file_path.display());
             let mut agent_file = File::create(&file_path)?;
             agent_file.write_all(content.as_bytes())?;
+            set_executable_bit_if_script(&file_path)?;
             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 {
-                use std::{fs, os::unix::fs::PermissionsExt};
-                fs::set_permissions(&file_path, fs::Permissions::from_mode(0o755))?;
-            }
         }
 
         let mut bundled_files: HashMap<String, HashSet<String>> = HashMap::new();
@@ -179,6 +275,32 @@ impl Agent {
             }
         }
 
+        sweep_removed_agent_hooks(&bundled_files);
+
+        Ok(())
+    }
+
+    pub fn install_builtin_agent_hooks(mode: InstallMode, sticky: &mut StickyMode) -> Result<()> {
+        let mut shipped: BTreeMap<String, Vec<(String, String)>> = BTreeMap::new();
+        for file in AgentAssets::iter() {
+            let Some((agent, rest)) = file.as_ref().split_once('/') else {
+                continue;
+            };
+            let hooks = shipped.entry(agent.to_string()).or_default();
+            let Some(hook) = direct_hook_name(rest) else {
+                continue;
+            };
+            let embedded = AgentAssets::get(&file)
+                .ok_or_else(|| anyhow!("Failed to load embedded agent file: {}", file.as_ref()))?;
+            let content = std::str::from_utf8(&embedded.data)
+                .expect("bundled agent hook asset is not valid UTF-8");
+            hooks.push((hook.to_string(), content.to_string()));
+        }
+
+        for (agent, files) in &shipped {
+            install_and_reconcile_agent_hooks(agent, files, mode, sticky)?;
+        }
+
         Ok(())
     }
 
@@ -234,6 +356,13 @@ impl Agent {
             }
         };
 
+        let rag_sync_hooks = RagSyncHooks::resolve_for_agent(
+            &app.hooks,
+            &agent_config.global_hooks,
+            &agent_config.hooks,
+            name,
+        );
+
         let rag = if rag_path.exists() {
             let key = RagKey::Agent(name.to_string());
             let app_clone = app.clone();
@@ -266,6 +395,7 @@ impl Agent {
                 let app_clone = app.clone();
                 let rag_path_clone = rag_path.clone();
                 let abort = abort_signal.clone();
+                let sync_hooks = rag_sync_hooks.clone();
                 let rag = app_state
                     .rag_cache
                     .load_with(key, || async move {
@@ -276,6 +406,7 @@ impl Agent {
                             &document_paths,
                             abort,
                             true,
+                            sync_hooks,
                         )
                         .await
                     })
@@ -299,6 +430,7 @@ impl Agent {
                     &loaders,
                     info_flag,
                     abort_signal.clone(),
+                    &rag_sync_hooks,
                 )
                 .await?
             }
@@ -1019,10 +1151,13 @@ impl AgentConfig {
         if let Some(v) = read_env_value::<String>(&with_prefix("reasoning_effort")) {
             self.reasoning_effort = v;
         }
-        if let Ok(v) = env::var(with_prefix("global_tools"))
-            && let Ok(v) = serde_json::from_str(&v)
-        {
-            self.global_tools = v;
+        if let Ok(v) = env::var(with_prefix("global_tools")) {
+            match serde_json::from_str(&v) {
+                Ok(v) => self.global_tools = v,
+                Err(err) => {
+                    debug!("Ignoring malformed global_tools env override for agent '{name}': {err}")
+                }
+            }
         }
         if let Ok(v) = env::var(with_prefix("global_hooks")) {
             match serde_json::from_str(&v) {
@@ -1178,6 +1313,7 @@ async fn init_graph_rags(
     loaders: &HashMap<String, String>,
     info_flag: bool,
     abort_signal: AbortSignal,
+    sync_hooks: &RagSyncHooks,
 ) -> Result<HashMap<String, Arc<Rag>>> {
     let mut rags = HashMap::new();
     if info_flag {
@@ -1254,6 +1390,7 @@ async fn init_graph_rags(
             let path_clone = rag_path.clone();
             let name_clone = node_id.clone();
             let abort = abort_signal.clone();
+            let sync_hooks = sync_hooks.clone();
             app_state
                 .rag_cache
                 .load_with(key, || async move {
@@ -1264,6 +1401,7 @@ async fn init_graph_rags(
                         &document_paths,
                         &config,
                         abort,
+                        sync_hooks,
                     )
                     .await
                 })
@@ -1361,6 +1499,7 @@ pub fn complete_agent_variables(agent_name: &str) -> Vec<(String, Option<String>
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::testing;
 
     #[test]
     fn parse_direct_hook_path_accepts_only_direct_hook_children() {
@@ -1472,6 +1611,33 @@ global_hooks:
         }
     }
 
+    #[test]
+    #[serial_test::serial]
+    fn load_envs_ignores_malformed_global_tools_and_logs_debug() {
+        testing::install_log_collector();
+        let name = "gt-malformed-envtest";
+        let yaml = format!("name: {name}\ninstructions: hi\nglobal_tools:\n  - keep_tool.sh\n");
+        let mut config: AgentConfig = serde_yaml::from_str(&yaml).unwrap();
+        let env_name = normalize_env_name(&format!("{name}_global_tools"));
+        let _guard = testing::EnvVarGuard::set(&env_name, "{not-json");
+
+        config.load_envs(&AppConfig::default());
+
+        assert_eq!(
+            config.global_tools,
+            vec!["keep_tool.sh"],
+            "a malformed override must leave the existing value untouched"
+        );
+        let debugs = testing::debug_snapshot();
+        assert!(
+            debugs.iter().any(|message| {
+                message.contains("Ignoring malformed global_tools env override")
+                    && message.contains(name)
+            }),
+            "expected a debug log for the malformed override: {debugs:?}"
+        );
+    }
+
     #[test]
     fn from_graph_carries_hooks_and_global_hooks() {
         let yaml = "\
@@ -1896,4 +2062,164 @@ nodes: {}
         );
         assert_eq!(output, expected);
     }
+
+    use crate::testing::TestConfigDirGuard;
+
+    fn fixture(entries: &[(&str, &str)]) -> Vec<(String, String)> {
+        entries
+            .iter()
+            .map(|(name, content)| (name.to_string(), content.to_string()))
+            .collect()
+    }
+
+    #[test]
+    #[serial_test::serial]
+    fn agent_hooks_prompt_mode_asks_per_conflict_and_honors_sticky() {
+        use crate::config::conflict::prompt_script;
+
+        let _guard = TestConfigDirGuard::new("agent-hooks-prompt");
+        let shipped = fixture(&[("a.sh", "new content\n"), ("b.sh", "new content\n")]);
+        let dir = paths::agents_data_dir().join("probe").join("hooks");
+        create_dir_all(&dir).unwrap();
+        fs::write(dir.join("a.sh"), "local a").unwrap();
+        fs::write(dir.join("b.sh"), "local b").unwrap();
+
+        // First conflict answered per-file, second by the sticky replace-all.
+        let script = prompt_script::install(&["replace-all"]);
+        let mut sticky = StickyMode::None;
+        install_and_reconcile_agent_hooks("probe", &shipped, InstallMode::Prompt, &mut sticky)
+            .unwrap();
+        assert_eq!(prompt_script::prompts_asked(), 1);
+        assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "new content\n");
+        assert_eq!(read_to_string(dir.join("b.sh")).unwrap(), "new content\n");
+        assert_eq!(sticky, StickyMode::ReplaceAll);
+        assert_eq!(
+            read_to_string(dir.join(builtin_manifest::BUILTIN_MANIFEST_FILE)).unwrap(),
+            "a.sh\nb.sh\n"
+        );
+        drop(script);
+
+        // A sticky mode carried in from an earlier location suppresses all
+        // prompting: `--install-builtins hooks` shares one sticky scope
+        // across the global, role, and agent hook locations.
+        fs::write(dir.join("a.sh"), "local again").unwrap();
+        let script = prompt_script::install(&[]);
+        let mut sticky = StickyMode::KeepAll;
+        install_and_reconcile_agent_hooks("probe", &shipped, InstallMode::Prompt, &mut sticky)
+            .unwrap();
+        assert_eq!(prompt_script::prompts_asked(), 0);
+        assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "local again");
+        drop(script);
+    }
+
+    #[test]
+    #[serial_test::serial]
+    fn agent_hooks_reconcile_adds_updates_and_drops_within_a_shipped_agent() {
+        let _guard = TestConfigDirGuard::new("agent-hooks-reconcile");
+        let dir = paths::agents_data_dir().join("probe").join("hooks");
+
+        install_and_reconcile_agent_hooks(
+            "probe",
+            &fixture(&[("keep.sh", "v1\n"), ("drop.sh", "#!/bin/sh\n")]),
+            InstallMode::Skip,
+            &mut StickyMode::None,
+        )
+        .unwrap();
+        fs::write(dir.join("user.sh"), "user-owned").unwrap();
+
+        install_and_reconcile_agent_hooks(
+            "probe",
+            &fixture(&[("keep.sh", "v2\n"), ("added.sh", "#!/bin/sh\n")]),
+            InstallMode::Force,
+            &mut StickyMode::None,
+        )
+        .unwrap();
+
+        assert_eq!(
+            read_to_string(dir.join("keep.sh")).unwrap(),
+            "v2\n",
+            "a still-shipped hook updates under Force"
+        );
+        assert_eq!(
+            read_to_string(dir.join("added.sh")).unwrap(),
+            "#!/bin/sh\n",
+            "a newly shipped hook is added"
+        );
+        assert!(
+            !dir.join("drop.sh").exists(),
+            "a dropped hook reconciles away"
+        );
+        assert_eq!(
+            read_to_string(dir.join("user.sh")).unwrap(),
+            "user-owned",
+            "user files in the same dir survive"
+        );
+        assert_eq!(
+            read_to_string(dir.join(builtin_manifest::BUILTIN_MANIFEST_FILE)).unwrap(),
+            "added.sh\nkeep.sh\n"
+        );
+    }
+
+    #[test]
+    #[serial_test::serial]
+    fn install_builtin_agent_hooks_reconciles_hookless_bundled_agents() {
+        let _guard = TestConfigDirGuard::new("agent-hooks-hookless");
+        let agent = AgentAssets::iter()
+            .filter_map(|file| {
+                file.as_ref()
+                    .split_once('/')
+                    .map(|(agent, _)| agent.to_string())
+            })
+            .find(|agent| {
+                !AgentAssets::iter().any(|file| {
+                    parse_direct_hook_path(file.as_ref())
+                        .is_some_and(|(hook_agent, _)| hook_agent == agent)
+                })
+            })
+            .expect("at least one bundled agent ships no hooks");
+        let dir = paths::agents_data_dir().join(&agent).join("hooks");
+        // A manifest-owned hook left over from a release that shipped it.
+        install_and_reconcile_agent_hooks(
+            &agent,
+            &fixture(&[("stale.sh", "#!/bin/sh\n")]),
+            InstallMode::Skip,
+            &mut StickyMode::None,
+        )
+        .unwrap();
+        fs::write(dir.join("user.sh"), "user-owned").unwrap();
+
+        Agent::install_builtin_agent_hooks(InstallMode::Skip, &mut StickyMode::None).unwrap();
+
+        assert!(
+            !dir.join("stale.sh").exists(),
+            "a still-bundled agent with no hook assets must reconcile its hooks dir"
+        );
+        assert_eq!(read_to_string(dir.join("user.sh")).unwrap(), "user-owned");
+    }
+
+    #[cfg(unix)]
+    #[test]
+    #[serial_test::serial]
+    fn sweep_removed_agent_hooks_never_follows_symlinked_agent_dirs() {
+        let guard = TestConfigDirGuard::new("agent-sweep-symlink");
+        let real = guard.path.join("agent-elsewhere");
+        let hooks = real.join("hooks");
+        create_dir_all(&hooks).unwrap();
+        fs::write(
+            hooks.join(builtin_manifest::BUILTIN_MANIFEST_FILE),
+            "shipped.sh\n",
+        )
+        .unwrap();
+        fs::write(hooks.join("shipped.sh"), "stale").unwrap();
+        create_dir_all(paths::agents_data_dir()).unwrap();
+        std::os::unix::fs::symlink(&real, paths::agents_data_dir().join("linked")).unwrap();
+
+        sweep_removed_agent_hooks(&HashMap::new());
+
+        assert!(
+            hooks.join("shipped.sh").exists(),
+            "the sweep must never follow a symlinked agent dir"
+        );
+        assert!(hooks.join(builtin_manifest::BUILTIN_MANIFEST_FILE).exists());
+    }
 }

src/config/app_config.rs

@@ -71,6 +71,7 @@ pub struct AppConfig {
     pub compression_threshold: usize,
     pub compression_keep_last: usize,
     pub compression_model: Option<String>,
+    pub compression_safety_valve: f32,
     pub summarization_prompt: Option<String>,
     pub summary_context_prompt: Option<String>,
     pub max_tool_result_chars: Option<usize>,
@@ -164,6 +165,7 @@ impl Default for AppConfig {
             compression_threshold: 4000,
             compression_keep_last: 0,
             compression_model: None,
+            compression_safety_valve: 0.8,
             summarization_prompt: None,
             summary_context_prompt: None,
             max_tool_result_chars: None,
@@ -210,6 +212,18 @@ impl Default for AppConfig {
 
 impl AppConfig {
     pub fn from_config(config: super::Config) -> Result<Self> {
+        Self::from_config_impl(config, true)
+    }
+
+    /// Like [`Self::from_config`], but tolerates a config with no resolvable
+    /// model: `model_id` stays empty instead of failing with "No available
+    /// model". For inspection readouts (--info, --list-*, --mcp-list,
+    /// --list-secrets), which render model fields as absent/default.
+    pub fn from_config_lenient(config: super::Config) -> Result<Self> {
+        Self::from_config_impl(config, false)
+    }
+
+    fn from_config_impl(config: super::Config, require_model: bool) -> Result<Self> {
         let mut app_config = Self {
             model_id: config.model_id,
             temperature: config.temperature,
@@ -258,6 +272,7 @@ impl AppConfig {
             compression_threshold: config.compression_threshold,
             compression_keep_last: config.compression_keep_last,
             compression_model: config.compression_model,
+            compression_safety_valve: config.compression_safety_valve,
             summarization_prompt: config.summarization_prompt,
             summary_context_prompt: config.summary_context_prompt,
             max_tool_result_chars: config.max_tool_result_chars,
@@ -306,7 +321,13 @@ impl AppConfig {
         }
         app_config.setup_document_loaders();
         app_config.setup_user_agent();
+        if require_model {
             app_config.resolve_model()?;
+        } else {
+            // Model-less is fine here: model_id stays empty and inspection
+            // callers substitute Model::default().
+            let _ = app_config.resolve_model();
+        }
         app_config.validate_reasoning_effort()?;
         Ok(app_config)
     }
@@ -1269,6 +1290,18 @@ mod tests {
         assert!(result.is_err());
     }
 
+    #[test]
+    fn from_config_errors_when_no_model_available() {
+        let result = AppConfig::from_config(Config::default());
+        assert!(result.is_err());
+    }
+
+    #[test]
+    fn from_config_lenient_tolerates_missing_model() {
+        let app = AppConfig::from_config_lenient(Config::default()).unwrap();
+        assert!(app.model_id.is_empty());
+    }
+
     #[test]
     fn resolve_model_keeps_explicit_model_id() {
         let mut app = AppConfig {

src/config/app_state.rs

@@ -43,6 +43,7 @@ impl AppState {
         log_path: Option<PathBuf>,
         start_mcp_servers: bool,
         lenient_vault: bool,
+        inspection: bool,
         abort_signal: AbortSignal,
     ) -> Result<Self> {
         let vault = if lenient_vault {
@@ -74,7 +75,11 @@ impl AppState {
             }
         }
 
-        let mut functions = Functions::init(config.visible_tools.as_deref())?;
+        let mut functions = if inspection {
+            Functions::default()
+        } else {
+            Functions::init(config.visible_tools.as_deref())?
+        };
         if !mcp_registry.is_empty() && config.mcp_server_support {
             functions.append_mcp_meta_functions(mcp_registry.server_features());
         }

src/config/builtin_manifest.rs

@@ -23,6 +23,22 @@ pub(crate) fn is_builtin_manifest_name(name: &str) -> bool {
         .eq_ignore_ascii_case(BUILTIN_MANIFEST_FILE)
 }
 
+/// NTFS 8.3 short names (`BUILTI~1`, `builti~1.sh`) can alias any long
+/// filename on the same volume, including the manifest itself, so an entry
+/// shaped like one is never accepted: it could direct a deletion at a file
+/// the manifest never named.
+fn is_ntfs_short_name_alias(name: &str) -> bool {
+    let stem = name.split('.').next().unwrap_or(name);
+    let Some((base, digits)) = stem.rsplit_once('~') else {
+        return false;
+    };
+    !base.is_empty()
+        && base.len() <= 8
+        && base.chars().all(|c| c.is_ascii_alphanumeric() || c == '~')
+        && !digits.is_empty()
+        && digits.chars().all(|c| c.is_ascii_digit())
+}
+
 /// 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
@@ -83,7 +99,7 @@ fn read_manifest(dir: &Path) -> BTreeSet<String> {
             if line.is_empty() || is_builtin_manifest_name(line) {
                 return false;
             }
-            if !is_plain_file_name(line) {
+            if !is_plain_file_name(line) || is_ntfs_short_name_alias(line) {
                 debug!(
                     "Ignoring suspicious builtin manifest entry in {}: {line:?}",
                     path.display()
@@ -290,4 +306,93 @@ mod tests {
         assert!(!is_builtin_manifest_name(".builtin-manifesto"));
         assert!(!is_builtin_manifest_name("notify.sh"));
     }
+
+    #[test]
+    fn ntfs_short_name_aliases_are_detected() {
+        assert!(is_ntfs_short_name_alias("BUILTI~1"));
+        assert!(is_ntfs_short_name_alias("builti~1.sh"));
+        assert!(is_ntfs_short_name_alias("NOTIFY~12"));
+        assert!(is_ntfs_short_name_alias("A~1"));
+        assert!(!is_ntfs_short_name_alias("notify.sh"));
+        assert!(!is_ntfs_short_name_alias("my~hook.sh"));
+        assert!(!is_ntfs_short_name_alias("~1"));
+        assert!(!is_ntfs_short_name_alias("way-too-long~1"));
+        assert!(!is_ntfs_short_name_alias(".builtin-manifest"));
+    }
+
+    /// This fixture is unrealizable on NTFS: `.builtin-manifest` gets an
+    /// auto-generated 8.3 short name of exactly this shape (`BUILTI~1`), so
+    /// writing `dir/BUILTI~1` opens the manifest through its alias and
+    /// clobbers it instead of creating a distinct file — the precise
+    /// collision [`is_ntfs_short_name_alias`] defends against. Only
+    /// filesystems without 8.3 aliasing can host alias-shaped names as real,
+    /// distinct files; Windows coverage lives in
+    /// `ntfs_short_name_entries_never_accepted_on_windows` below.
+    #[cfg(unix)]
+    #[test]
+    fn ntfs_short_name_entries_never_direct_deletions() {
+        let dir = fresh_dir("builtin-manifest-shortname-");
+        fs::write(dir.join(BUILTIN_MANIFEST_FILE), "BUILTI~1\nbuilti~1.sh\n").unwrap();
+        fs::write(dir.join("BUILTI~1"), "keep").unwrap();
+        fs::write(dir.join("builti~1.sh"), "keep").unwrap();
+
+        reconcile_builtin_dir(&dir, &BTreeSet::new(), &BTreeSet::new()).unwrap();
+
+        assert!(
+            dir.join("BUILTI~1").exists() && dir.join("builti~1.sh").exists(),
+            "8.3-alias-shaped manifest entries must never be removal candidates"
+        );
+        let _ = fs::remove_dir_all(&dir);
+    }
+
+    /// Windows counterpart of `ntfs_short_name_entries_never_direct_deletions`:
+    /// alias-shaped files cannot exist as distinct fixtures here, so the guard
+    /// invariant is proven through the manifest filter instead. Only entries
+    /// accepted into the previous-manifest set can become removal candidates
+    /// (`previous.difference(shipped)`) or be claimed as owned
+    /// (`shipped ∩ previous`); listing the alias names in `shipped` makes the
+    /// second path observable in the rewritten manifest — a broken guard
+    /// would claim them. Where the volume generates 8.3 short names, the
+    /// self-collision that makes the unix fixture unrealizable is also
+    /// asserted directly; where generation is disabled, the alias simply
+    /// never materializes and the invariant assertions stand on their own.
+    #[cfg(windows)]
+    #[test]
+    fn ntfs_short_name_entries_never_accepted_on_windows() {
+        let dir = fresh_dir("builtin-manifest-shortname-win-");
+        fs::write(
+            dir.join(BUILTIN_MANIFEST_FILE),
+            "BUILTI~1\nbuilti~1.sh\nkept.sh\n",
+        )
+        .unwrap();
+        fs::write(dir.join("kept.sh"), "current").unwrap();
+
+        let alias = dir.join("BUILTI~1");
+        if alias.exists() {
+            assert_eq!(
+                fs::read_to_string(&alias).unwrap(),
+                fs::read_to_string(dir.join(BUILTIN_MANIFEST_FILE)).unwrap(),
+                "the 8.3 alias opens the manifest itself, not a distinct file"
+            );
+        }
+
+        reconcile_builtin_dir(
+            &dir,
+            &shipped(&["BUILTI~1", "builti~1.sh", "kept.sh"]),
+            &shipped(&[]),
+        )
+        .unwrap();
+
+        assert!(dir.join("kept.sh").exists(), "real shipped file untouched");
+        assert!(
+            dir.join(BUILTIN_MANIFEST_FILE).exists(),
+            "manifest survives reconciliation"
+        );
+        assert_eq!(
+            fs::read_to_string(dir.join(BUILTIN_MANIFEST_FILE)).unwrap(),
+            "kept.sh\n",
+            "alias-shaped entries are never accepted: neither removal candidates nor claimed"
+        );
+        let _ = fs::remove_dir_all(&dir);
+    }
 }

src/config/conflict.rs

@@ -0,0 +1,364 @@
+//! Shared keep/replace conflict resolution for installers that must not
+//! silently clobber locally modified files. The bundle installer and the
+//! builtin hook installers all funnel per-file conflicts through
+//! [`resolve_conflict`], so the prompt wording and the sticky
+//! keep-all/replace-all semantics are identical everywhere, including when
+//! one sticky scope spans several install locations in a single run.
+
+use crate::utils::IS_STDOUT_TERMINAL;
+
+use anyhow::{Context, Result, bail};
+use inquire::Select;
+use std::fs;
+use std::path::Path;
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) enum InstallMode {
+    Skip,
+    Force,
+    Prompt,
+}
+
+/// A `keep-all`/`replace-all` answer outlives the file it was given for:
+/// the caller threads one value through every subsequent conflict in the
+/// same run.
+#[derive(Debug, Clone, Copy, PartialEq)]
+pub(crate) enum StickyMode {
+    None,
+    KeepAll,
+    ReplaceAll,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) enum ConflictAction {
+    Keep,
+    Replace,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub(crate) enum NonInteractive {
+    Bail,
+    Keep,
+}
+
+pub(crate) fn should_replace_existing(
+    dst: &Path,
+    content: &str,
+    category: &str,
+    mode: InstallMode,
+    sticky: &mut StickyMode,
+) -> Result<bool> {
+    match mode {
+        InstallMode::Skip => Ok(false),
+        InstallMode::Force => Ok(true),
+        InstallMode::Prompt => {
+            if fs::read(dst).is_ok_and(|local| local == content.as_bytes()) {
+                return Ok(false);
+            }
+            match resolve_conflict(dst, category, sticky, NonInteractive::Keep)? {
+                ConflictAction::Keep => Ok(false),
+                ConflictAction::Replace => Ok(true),
+            }
+        }
+    }
+}
+
+pub(crate) fn resolve_conflict(
+    dst: &Path,
+    category: &str,
+    sticky: &mut StickyMode,
+    non_interactive: NonInteractive,
+) -> Result<ConflictAction> {
+    match *sticky {
+        StickyMode::KeepAll => return Ok(ConflictAction::Keep),
+        StickyMode::ReplaceAll => return Ok(ConflictAction::Replace),
+        StickyMode::None => {}
+    }
+
+    if !is_interactive() {
+        match non_interactive {
+            NonInteractive::Keep => return Ok(ConflictAction::Keep),
+            NonInteractive::Bail => bail!(
+                "Refusing to overwrite local file {} non-interactively. \
+                 Re-run in a terminal, with --install-force (installs), \
+                 or with --yes (updates).",
+                dst.display()
+            ),
+        }
+    }
+
+    let prompt = format!("Conflict at {} (category: {category})", dst.display());
+    let choice = select_choice(&prompt)?;
+
+    match choice.as_str() {
+        "keep" => Ok(ConflictAction::Keep),
+        "replace" => Ok(ConflictAction::Replace),
+        "keep-all" => {
+            *sticky = StickyMode::KeepAll;
+            Ok(ConflictAction::Keep)
+        }
+        "replace-all" => {
+            *sticky = StickyMode::ReplaceAll;
+            Ok(ConflictAction::Replace)
+        }
+        "abort" => bail!("Install aborted by user at conflict resolution."),
+        _ => unreachable!("inquire::Select returned an unexpected option"),
+    }
+}
+
+fn is_interactive() -> bool {
+    #[cfg(test)]
+    if let Some(forced) = prompt_script::forced_tty() {
+        return forced;
+    }
+    *IS_STDOUT_TERMINAL
+}
+
+fn select_choice(prompt: &str) -> Result<String> {
+    #[cfg(test)]
+    if prompt_script::active() {
+        return Ok(prompt_script::next_answer(prompt));
+    }
+    Select::new(
+        prompt,
+        vec!["keep", "replace", "keep-all", "replace-all", "abort"],
+    )
+    .prompt()
+    .map(str::to_string)
+    .with_context(|| "failed to read conflict choice")
+}
+
+#[cfg(test)]
+pub(crate) mod prompt_script {
+    //! Scripted stand-in for the interactive conflict prompt.
+    //! `inquire::Select` cannot run under the test harness, so while a guard
+    //! is installed the resolver takes its terminal answer from the guard and
+    //! serves each prompt from a queue of scripted answers, counting every
+    //! prompt asked. A forced-terminal guard with an empty queue pins the
+    //! "never prompts" invariant: any prompt panics and the counter stays 0.
+
+    use std::sync::Mutex;
+    use std::sync::atomic::{AtomicUsize, Ordering};
+
+    const INACTIVE: usize = 0;
+    const TTY: usize = 1;
+    const NON_TTY: usize = 2;
+
+    static STATE: AtomicUsize = AtomicUsize::new(INACTIVE);
+    static ASKED: AtomicUsize = AtomicUsize::new(0);
+    // A test that panics while holding the queue poisons its mutex; every
+    // lock site recovers via `into_inner` so later tests keep working.
+    static ANSWERS: Mutex<Vec<String>> = Mutex::new(Vec::new());
+
+    /// Installs the script with a forced terminal until the guard drops.
+    /// The script is process-global, so tests using it must serialize
+    /// (`#[serial]`). Answers are consumed front to back; a prompt beyond
+    /// the scripted answers panics.
+    #[must_use]
+    pub fn install(answers: &[&str]) -> ScriptGuard {
+        install_with_state(TTY, answers)
+    }
+
+    /// Installs the script with the terminal forced absent, for pinning the
+    /// non-interactive behavior regardless of where the tests actually run.
+    #[must_use]
+    pub fn install_non_interactive() -> ScriptGuard {
+        install_with_state(NON_TTY, &[])
+    }
+
+    fn install_with_state(state: usize, answers: &[&str]) -> ScriptGuard {
+        *ANSWERS
+            .lock()
+            .unwrap_or_else(|poisoned| poisoned.into_inner()) =
+            answers.iter().map(|answer| answer.to_string()).collect();
+        ASKED.store(0, Ordering::SeqCst);
+        STATE.store(state, Ordering::SeqCst);
+        ScriptGuard
+    }
+
+    pub struct ScriptGuard;
+
+    impl Drop for ScriptGuard {
+        fn drop(&mut self) {
+            STATE.store(INACTIVE, Ordering::SeqCst);
+            ANSWERS
+                .lock()
+                .unwrap_or_else(|poisoned| poisoned.into_inner())
+                .clear();
+        }
+    }
+
+    /// Number of prompts asked since the script was installed.
+    pub fn prompts_asked() -> usize {
+        ASKED.load(Ordering::SeqCst)
+    }
+
+    pub(super) fn active() -> bool {
+        STATE.load(Ordering::SeqCst) != INACTIVE
+    }
+
+    pub(super) fn forced_tty() -> Option<bool> {
+        match STATE.load(Ordering::SeqCst) {
+            TTY => Some(true),
+            NON_TTY => Some(false),
+            _ => None,
+        }
+    }
+
+    pub(super) fn next_answer(prompt: &str) -> String {
+        ASKED.fetch_add(1, Ordering::SeqCst);
+        let mut answers = ANSWERS
+            .lock()
+            .unwrap_or_else(|poisoned| poisoned.into_inner());
+        assert!(
+            !answers.is_empty(),
+            "conflict prompt asked with no scripted answer left: {prompt}"
+        );
+        answers.remove(0)
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use serial_test::serial;
+    use std::path::PathBuf;
+
+    fn dst() -> PathBuf {
+        PathBuf::from("/tmp/coyote-conflict-tests/example.yaml")
+    }
+
+    #[test]
+    fn sticky_modes_short_circuit_without_prompting() {
+        let mut sticky = StickyMode::KeepAll;
+        assert!(matches!(
+            resolve_conflict(&dst(), "macros", &mut sticky, NonInteractive::Bail).unwrap(),
+            ConflictAction::Keep
+        ));
+
+        let mut sticky = StickyMode::ReplaceAll;
+        assert!(matches!(
+            resolve_conflict(&dst(), "macros", &mut sticky, NonInteractive::Bail).unwrap(),
+            ConflictAction::Replace
+        ));
+    }
+
+    #[test]
+    #[serial]
+    fn non_interactive_bail_keeps_the_bundle_error_shape() {
+        let _script = prompt_script::install_non_interactive();
+        let mut sticky = StickyMode::None;
+
+        let err =
+            resolve_conflict(&dst(), "macros", &mut sticky, NonInteractive::Bail).unwrap_err();
+
+        assert!(
+            err.to_string().contains("Refusing to overwrite local file"),
+            "got: {err}"
+        );
+        assert!(err.to_string().contains("example.yaml"), "got: {err}");
+        assert_eq!(prompt_script::prompts_asked(), 0);
+    }
+
+    #[test]
+    #[serial]
+    fn non_interactive_keep_resolves_without_error_or_prompt() {
+        let _script = prompt_script::install_non_interactive();
+        let mut sticky = StickyMode::None;
+
+        let action = resolve_conflict(&dst(), "hooks", &mut sticky, NonInteractive::Keep).unwrap();
+
+        assert!(matches!(action, ConflictAction::Keep));
+        assert_eq!(sticky, StickyMode::None);
+        assert_eq!(prompt_script::prompts_asked(), 0);
+    }
+
+    #[test]
+    #[serial]
+    fn scripted_answers_drive_actions_and_sticky_transitions() {
+        let _script = prompt_script::install(&["keep", "replace", "replace-all"]);
+        let mut sticky = StickyMode::None;
+
+        assert!(matches!(
+            resolve_conflict(&dst(), "hooks", &mut sticky, NonInteractive::Keep).unwrap(),
+            ConflictAction::Keep
+        ));
+        assert_eq!(sticky, StickyMode::None);
+        assert!(matches!(
+            resolve_conflict(&dst(), "hooks", &mut sticky, NonInteractive::Keep).unwrap(),
+            ConflictAction::Replace
+        ));
+        assert_eq!(sticky, StickyMode::None);
+        assert!(matches!(
+            resolve_conflict(&dst(), "hooks", &mut sticky, NonInteractive::Keep).unwrap(),
+            ConflictAction::Replace
+        ));
+        assert_eq!(sticky, StickyMode::ReplaceAll);
+        // The sticky answer now short-circuits: no further prompt is asked.
+        assert!(matches!(
+            resolve_conflict(&dst(), "hooks", &mut sticky, NonInteractive::Keep).unwrap(),
+            ConflictAction::Replace
+        ));
+        assert_eq!(prompt_script::prompts_asked(), 3);
+    }
+
+    #[test]
+    #[serial]
+    fn abort_answer_bails_with_the_bundle_abort_message() {
+        let _script = prompt_script::install(&["abort"]);
+        let mut sticky = StickyMode::None;
+
+        let err = resolve_conflict(&dst(), "hooks", &mut sticky, NonInteractive::Keep).unwrap_err();
+
+        assert!(
+            err.to_string()
+                .contains("Install aborted by user at conflict resolution."),
+            "got: {err}"
+        );
+    }
+
+    #[test]
+    #[serial]
+    fn should_replace_existing_skips_identical_content_without_prompting() {
+        let _script = prompt_script::install(&[]);
+        let dir = crate::utils::temp_file("conflict-identical-", "");
+        fs::create_dir_all(&dir).unwrap();
+        let path = dir.join("hook.sh");
+        fs::write(&path, "same content").unwrap();
+
+        let mut sticky = StickyMode::None;
+        let replace = should_replace_existing(
+            &path,
+            "same content",
+            "hooks",
+            InstallMode::Prompt,
+            &mut sticky,
+        )
+        .unwrap();
+
+        let _ = fs::remove_dir_all(&dir);
+        assert!(!replace);
+        assert_eq!(prompt_script::prompts_asked(), 0);
+    }
+
+    #[test]
+    #[serial]
+    fn should_replace_existing_never_prompts_in_skip_or_force_mode() {
+        let _script = prompt_script::install(&[]);
+        let dir = crate::utils::temp_file("conflict-modes-", "");
+        fs::create_dir_all(&dir).unwrap();
+        let path = dir.join("hook.sh");
+        fs::write(&path, "local edit").unwrap();
+
+        let mut sticky = StickyMode::None;
+        let skip =
+            should_replace_existing(&path, "shipped", "hooks", InstallMode::Skip, &mut sticky);
+        let force =
+            should_replace_existing(&path, "shipped", "hooks", InstallMode::Force, &mut sticky);
+
+        let _ = fs::remove_dir_all(&dir);
+        assert!(!skip.unwrap());
+        assert!(force.unwrap());
+        assert_eq!(prompt_script::prompts_asked(), 0);
+    }
+}

src/config/input.rs

@@ -68,6 +68,34 @@ impl Input {
         })
     }
 
+    /// An input carrying only `text`: no session history, no RAG, and no
+    /// function declarations. For auxiliary LLM calls (such as session
+    /// summarization) whose requests must not grow with the session.
+    pub fn detached_text(ctx: &RequestContext, text: &str) -> Self {
+        let mut role = Role::new("", "");
+        role.set_model(ctx.current_model().clone());
+        Self {
+            app_config: Arc::clone(&ctx.app.config),
+            stream_enabled: ctx.app.config.stream,
+            session: None,
+            rag: None,
+            functions: None,
+            text: text.to_string(),
+            raw: (text.to_string(), vec![]),
+            patched_text: None,
+            last_reply: None,
+            continue_output: None,
+            regenerate: false,
+            medias: Default::default(),
+            data_urls: Default::default(),
+            tool_calls: None,
+            role,
+            rag_name: None,
+            with_session: false,
+            with_agent: false,
+        }
+    }
+
     pub async fn from_files(
         ctx: &RequestContext,
         raw_text: &str,
@@ -329,6 +357,14 @@ impl Input {
         }
     }
 
+    /// Re-captures `ctx.session` in place of the snapshot taken at
+    /// construction. Session compression mutates the ctx's session, not the
+    /// snapshot, so an input that outlives a compression must refresh before
+    /// building its next request or it re-sends the pre-compression history.
+    pub fn refresh_session(&mut self, ctx: &RequestContext) {
+        self.session = ctx.session.clone();
+    }
+
     pub fn session_mut<'a>(&self, session: &'a mut Option<Session>) -> Option<&'a mut Session> {
         if self.with_session {
             session.as_mut()
@@ -660,6 +696,60 @@ mod tests {
         assert!(!with_session);
     }
 
+    #[test]
+    fn detached_text_input_carries_no_session_history_or_functions() {
+        let mut ctx = create_test_ctx();
+        ctx.session = Some(Session::default());
+        let earlier = Input::from_str(&ctx, "earlier question", None).unwrap();
+        ctx.session
+            .as_mut()
+            .unwrap()
+            .add_message(&earlier, "earlier answer")
+            .unwrap();
+
+        let detached = Input::detached_text(&ctx, "summarize the above");
+        let messages = detached.build_messages().unwrap();
+        assert_eq!(messages.len(), 1, "must contain only the detached text");
+        assert!(messages[0].role.is_user());
+        assert_eq!(messages[0].content.to_text(), "summarize the above");
+        assert!(detached.declared_function_names().is_empty());
+        assert!(!detached.with_session());
+        assert!(!detached.with_agent());
+    }
+
+    #[test]
+    fn refresh_session_rebuilds_from_compressed_session() {
+        let mut ctx = create_test_ctx();
+        ctx.session = Some(Session::default());
+        for i in 0..4 {
+            let question =
+                Input::from_str(&ctx, &format!("question {i}: {}", "x".repeat(500)), None).unwrap();
+            ctx.session
+                .as_mut()
+                .unwrap()
+                .add_message(&question, &"y".repeat(500))
+                .unwrap();
+        }
+
+        let mut input = Input::from_str(&ctx, "retry me", None).unwrap();
+        let stale = serde_json::to_string(&input.build_messages().unwrap()).unwrap();
+
+        ctx.session.as_mut().unwrap().compress("recap".into(), 1);
+
+        assert_eq!(
+            serde_json::to_string(&input.build_messages().unwrap()).unwrap(),
+            stale,
+            "the snapshot captured at construction must be untouched by compression"
+        );
+
+        input.refresh_session(&ctx);
+        let refreshed = serde_json::to_string(&input.build_messages().unwrap()).unwrap();
+        assert!(
+            refreshed.len() < stale.len(),
+            "a refreshed input must build a strictly smaller request after compression"
+        );
+    }
+
     #[test]
     fn resolve_paths_detects_last_reply_syntax() {
         let loaders = HashMap::new();
@@ -1023,6 +1113,7 @@ mod tests {
         assert!(!tool_calls.sequence);
         assert_eq!(tool_calls.tool_results.len(), 1);
         assert!(tool_calls.tool_results[0].text.is_none());
+        assert!(tool_calls.round_starts.is_empty());
     }
 
     #[test]
@@ -1044,6 +1135,29 @@ mod tests {
             tool_calls.tool_results[1].text,
             Some("second text".to_string())
         );
+        assert_eq!(tool_calls.round_starts, vec![1]);
+    }
+
+    /// Regression: rounds where the model emitted only tool calls (no
+    /// narration text) carry no text marker, so `round_starts` is the only
+    /// record of the round boundary — it must be set on every merge.
+    #[test]
+    fn merge_tool_results_records_round_starts_for_textless_rounds() {
+        let ctx = create_test_ctx();
+        let input = Input::from_str(&ctx, "test", None)
+            .unwrap()
+            .merge_tool_results(String::new(), vec![tool_result("id-1", "ok")])
+            .merge_tool_results(
+                String::new(),
+                vec![tool_result("id-2", "ok2"), tool_result("id-3", "ok3")],
+            )
+            .merge_tool_results(String::new(), vec![tool_result("id-4", "ok4")]);
+
+        let tool_calls = input.tool_calls().as_ref().unwrap();
+        assert!(tool_calls.sequence);
+        assert_eq!(tool_calls.tool_results.len(), 4);
+        assert!(tool_calls.tool_results.iter().all(|t| t.text.is_none()));
+        assert_eq!(tool_calls.round_starts, vec![1, 3]);
     }
 
     #[test]

src/config/install_remote.rs

@@ -3,9 +3,10 @@ use super::bundles::{
     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;
+use crate::config::conflict::{ConflictAction, NonInteractive, StickyMode, resolve_conflict};
+use crate::config::{
+    AssetCategory, BUNDLE_MANIFEST_FILE, InstallFilter, paths, set_executable_bit_if_script,
+};
 use crate::mcp::{McpServer, McpServersConfig};
 use crate::utils;
 use crate::utils::IS_STDOUT_TERMINAL;
@@ -1857,18 +1858,12 @@ fn print_plan_summary(plan: &InstallPlan) {
 }
 
 /// 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.
+/// config, so every planned file landing in a hook location 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"))
-        })
+        .filter(|planned| is_hook_location(planned))
         .map(|planned| {
             let rel = planned.rel.to_string_lossy().replace('\\', "/");
             format!(
@@ -1879,6 +1874,16 @@ fn hook_script_lines(plan: &InstallPlan) -> Vec<String> {
         .collect()
 }
 
+fn is_hook_location(planned: &PlannedFile) -> bool {
+    let components: Vec<_> = planned.rel.components().collect();
+    match planned.top_category {
+        TopCategory::Hooks => true,
+        TopCategory::Agents => components.len() == 3 && components[1].as_os_str() == "hooks",
+        TopCategory::Roles => components.len() == 2 && components[0].as_os_str() == "hooks",
+        _ => false,
+    }
+}
+
 fn count_kind(plan: &InstallPlan, cat: TopCategory, kind: PlannedKind) -> usize {
     plan.files
         .iter()
@@ -1886,18 +1891,6 @@ fn count_kind(plan: &InstallPlan, cat: TopCategory, kind: PlannedKind) -> usize
         .count()
 }
 
-#[derive(Debug, Clone, Copy, PartialEq)]
-enum StickyMode {
-    None,
-    KeepAll,
-    ReplaceAll,
-}
-
-enum ConflictAction {
-    Keep,
-    Replace,
-}
-
 #[derive(Debug)]
 struct ApplyReport {
     new_count: usize,
@@ -1937,7 +1930,12 @@ fn apply_plan(
                 record_written_file(store, bundle, planned, FileAction::Replaced)?;
                 report.refreshed_count += 1;
             }
-            PlannedKind::Conflict => match resolve_conflict(planned, &mut sticky)? {
+            PlannedKind::Conflict => match resolve_conflict(
+                &planned.dst,
+                planned.top_category.label(),
+                &mut sticky,
+                NonInteractive::Bail,
+            )? {
                 ConflictAction::Keep => report.kept_count += 1,
                 ConflictAction::Replace => {
                     write_file(&planned.src, &planned.dst)?;
@@ -2037,50 +2035,6 @@ fn record_mcp_merge(store: &mut BundleStore, bundle: &str, report: &McpMergeRepo
     store.record_mcp_servers(bundle, entries)
 }
 
-fn resolve_conflict(planned: &PlannedFile, sticky: &mut StickyMode) -> Result<ConflictAction> {
-    match *sticky {
-        StickyMode::KeepAll => return Ok(ConflictAction::Keep),
-        StickyMode::ReplaceAll => return Ok(ConflictAction::Replace),
-        StickyMode::None => {}
-    }
-
-    if !*IS_STDOUT_TERMINAL {
-        bail!(
-            "Refusing to overwrite local file {} non-interactively. \
-             Re-run in a terminal, with --install-force (installs), \
-             or with --yes (updates).",
-            planned.dst.display()
-        );
-    }
-
-    let prompt = format!(
-        "Conflict at {} (category: {})",
-        planned.dst.display(),
-        planned.top_category.label()
-    );
-    let choice = Select::new(
-        &prompt,
-        vec!["keep", "replace", "keep-all", "replace-all", "abort"],
-    )
-    .prompt()
-    .with_context(|| "failed to read conflict choice")?;
-
-    match choice {
-        "keep" => Ok(ConflictAction::Keep),
-        "replace" => Ok(ConflictAction::Replace),
-        "keep-all" => {
-            *sticky = StickyMode::KeepAll;
-            Ok(ConflictAction::Keep)
-        }
-        "replace-all" => {
-            *sticky = StickyMode::ReplaceAll;
-            Ok(ConflictAction::Replace)
-        }
-        "abort" => bail!("Install aborted by user at conflict resolution."),
-        _ => unreachable!("inquire::Select returned an unexpected option"),
-    }
-}
-
 fn write_file(src: &Path, dst: &Path) -> Result<()> {
     if let Some(parent) = dst.parent() {
         fs::create_dir_all(parent)
@@ -2092,26 +2046,6 @@ fn write_file(src: &Path, dst: &Path) -> Result<()> {
     Ok(())
 }
 
-#[cfg(unix)]
-fn set_executable_bit_if_script(path: &Path) -> Result<()> {
-    use std::os::unix::fs::PermissionsExt;
-
-    let Some(ext) = path.extension().and_then(OsStr::to_str) else {
-        return Ok(());
-    };
-    if Language::from_extension(ext) == Language::Unsupported {
-        return Ok(());
-    }
-    fs::set_permissions(path, fs::Permissions::from_mode(0o755))
-        .with_context(|| format!("chmod {}", path.display()))?;
-    Ok(())
-}
-
-#[cfg(not(unix))]
-fn set_executable_bit_if_script(_path: &Path) -> Result<()> {
-    Ok(())
-}
-
 #[derive(Debug)]
 struct McpMergeReport {
     added: Vec<String>,
@@ -2924,6 +2858,11 @@ mod tests {
                 file("x/config.yaml", TopCategory::Agents),
                 file("reviewer.md", TopCategory::Roles),
                 file("hello.yaml", TopCategory::Macros),
+                file("x/hooks/nested/deep.sh", TopCategory::Agents),
+                file("x/sub/hooks/pre.sh", TopCategory::Agents),
+                file("sub/hooks/extra.sh", TopCategory::Roles),
+                file("my-skill/hooks/tool.sh", TopCategory::Skills),
+                file("my-macro/hooks/tool.sh", TopCategory::Macros),
             ],
             mcp_json: None,
         };

src/config/macros.rs

@@ -83,6 +83,7 @@ pub async fn macro_execute(
         .bootstrap_tools(app.as_ref(), true, abort_signal.clone())
         .await?;
 
+    let result = async {
         for step in &macro_value.steps {
             let command = Macro::interpolate_command(step, &variables);
             println!(">> {}", multiline_text(&command));
@@ -90,6 +91,10 @@ pub async fn macro_execute(
         }
         Ok(())
     }
+    .await;
+    macro_ctx.top_level_agent_finished(result.as_ref().err(), Some(&abort_signal));
+    result
+}
 
 struct MacroModeGuard<'a> {
     ctx: &'a mut RequestContext,
@@ -167,7 +172,8 @@ impl Macro {
             debug!("Processing macro file: {}", file.as_ref());
             let embedded_file = MacroAssets::get(&file)
                 .ok_or_else(|| anyhow!("Failed to load embedded macro file: {}", file.as_ref()))?;
-            let content = unsafe { std::str::from_utf8_unchecked(&embedded_file.data) };
+            let content = std::str::from_utf8(&embedded_file.data)
+                .expect("bundled macro asset is not valid UTF-8");
             let file_path = paths::macros_dir().join(file.as_ref());
 
             if file_path.exists() && !force {
@@ -350,56 +356,14 @@ fn default_true() -> bool {
 mod tests {
     use super::*;
     use crate::config::{AppState, Session, WorkingMode};
+    use crate::testing::TestConfigDirGuard;
     use crate::utils::{create_abort_signal, get_env_name};
     use serial_test::serial;
     use std::fs::{create_dir_all, remove_dir_all, write};
     use std::future::Future;
-    use std::path::PathBuf;
     use std::time::{SystemTime, UNIX_EPOCH};
     use std::{env, str};
 
-    struct TestConfigDirGuard {
-        key: String,
-        previous: Option<std::ffi::OsString>,
-        path: PathBuf,
-    }
-
-    impl TestConfigDirGuard {
-        fn new() -> Self {
-            let key = get_env_name("config_dir");
-            let previous = env::var_os(&key);
-            let unique = SystemTime::now()
-                .duration_since(UNIX_EPOCH)
-                .unwrap()
-                .as_nanos();
-            let path = env::temp_dir().join(format!("coyote-macros-tests-{unique}"));
-            create_dir_all(&path).unwrap();
-            unsafe {
-                env::set_var(&key, &path);
-            }
-            Self {
-                key,
-                previous,
-                path,
-            }
-        }
-    }
-
-    impl Drop for TestConfigDirGuard {
-        fn drop(&mut self) {
-            if let Some(previous) = &self.previous {
-                unsafe {
-                    env::set_var(&self.key, previous);
-                }
-            } else {
-                unsafe {
-                    env::remove_var(&self.key);
-                }
-            }
-            let _ = remove_dir_all(&self.path);
-        }
-    }
-
     fn test_ctx() -> RequestContext {
         RequestContext::new(Arc::new(AppState::test_default()), WorkingMode::Cmd)
     }
@@ -974,7 +938,7 @@ variables:
     #[test]
     #[serial]
     fn non_isolated_steps_run_on_live_ctx_and_mutations_persist() {
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("macros-tests");
         write_macro_file(
             "live-macro",
             "isolated: false\nsteps:\n  - \".set temperature 0.42\"\n",
@@ -1006,7 +970,7 @@ variables:
     #[test]
     #[serial]
     fn non_isolated_step_failure_aborts_and_restores_flag_and_mode() {
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("macros-tests");
         write_macro_file(
             "fail-macro",
             "isolated: false\nsteps:\n  - \".set temperature 0.9\"\n  - \".update\"\n  - \".set temperature 0.1\"\n",
@@ -1057,7 +1021,7 @@ variables:
     #[test]
     #[serial]
     fn non_isolated_macro_step_invoking_macro_is_rejected() {
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("macros-tests");
         write_macro_file(
             "outer-macro",
             "isolated: false\nsteps:\n  - \".inner-macro\"\n",
@@ -1093,7 +1057,7 @@ variables:
     #[test]
     #[serial]
     fn isolated_macro_step_runs_non_isolated_macro_inline_on_fork() {
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("macros-tests");
         write_macro_file("iso-outer-macro", "steps:\n  - \".inner-macro\"\n");
         write_macro_file(
             "inner-macro",
@@ -1122,7 +1086,7 @@ variables:
     #[test]
     #[serial]
     fn isolated_macro_still_forks_and_leaves_live_ctx_untouched() {
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("macros-tests");
         write_macro_file("iso-macro", "steps:\n  - \".set temperature 0.77\"\n");
         let mut ctx = test_ctx();
         ctx.session = Some(Session::default());
@@ -1152,7 +1116,7 @@ variables:
     #[test]
     #[serial]
     fn guard_restores_prior_flag_values_after_inline_run() {
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("macros-tests");
         write_macro_file(
             "inner-macro",
             "isolated: false\nsteps:\n  - \".set temperature 0.11\"\n",

src/config/mcp_factory.rs

@@ -1,5 +1,6 @@
+use crate::hooks::McpServerHooks;
 use crate::mcp::{
-    ConnectedServer, JsonField, McpAuthRequired, McpServer, McpTransportType,
+    ConnectedServer, HttpAuth, JsonField, McpAuthRequired, McpServer, McpTransportType,
     is_auth_required_error, resolve_http_auth, spawn_mcp_server,
 };
 
@@ -80,11 +81,6 @@ pub struct McpFactory {
 }
 
 impl McpFactory {
-    pub fn try_get_active(&self, key: &McpServerKey) -> Option<Arc<ConnectedServer>> {
-        let map = self.active.lock();
-        map.get(key).and_then(|weak| weak.upgrade())
-    }
-
     pub fn insert_active(&self, key: McpServerKey, handle: &Arc<ConnectedServer>) {
         let mut map = self.active.lock();
         map.insert(key, Arc::downgrade(handle));
@@ -95,15 +91,47 @@ impl McpFactory {
         name: &str,
         spec: &McpServer,
         log_path: Option<&Path>,
+        hooks: &McpServerHooks,
     ) -> Result<Arc<ConnectedServer>> {
         let key = McpServerKey::from_spec(name, spec);
 
-        if let Some(existing) = self.try_get_active(&key) {
+        let reconnect = {
+            let map = self.active.lock();
+            if let Some(existing) = map.get(&key).and_then(|weak| weak.upgrade()) {
                 return Ok(existing);
             }
+            map.contains_key(&key)
+        };
 
+        let transport = transport_label(&spec.transport_type);
+        let handle = match spawn_server(name, spec, log_path).await {
+            Ok(handle) => handle,
+            Err(e) => {
+                hooks.fire_failed(name, transport, &e, is_auth_required_error(&e));
+                return Err(e);
+            }
+        };
+        self.insert_active(key, &handle);
+        hooks.fire_connected(name, transport, reconnect);
+        Ok(handle)
+    }
+}
+
+fn transport_label(transport: &McpTransportType) -> &'static str {
+    match transport {
+        McpTransportType::Stdio => "stdio",
+        McpTransportType::Http => "http",
+        McpTransportType::Sse => "sse",
+    }
+}
+
+async fn spawn_server(
+    name: &str,
+    spec: &McpServer,
+    log_path: Option<&Path>,
+) -> Result<Arc<ConnectedServer>> {
     let (auth, auth_reason) = resolve_http_auth(name, spec).await;
-        let handle = spawn_mcp_server(spec, log_path, auth).await.map_err(|e| {
+    spawn_transport(spec, log_path, auth).await.map_err(|e| {
         if is_auth_required_error(&e) {
             e.context(McpAuthRequired {
                 server: name.to_string(),
@@ -112,17 +140,39 @@ impl McpFactory {
         } else {
             e
         }
-        })?;
-        self.insert_active(key, &handle);
-        Ok(handle)
+    })
 }
+
+async fn spawn_transport(
+    spec: &McpServer,
+    log_path: Option<&Path>,
+    auth: HttpAuth,
+) -> Result<Arc<ConnectedServer>> {
+    #[cfg(test)]
+    if let Some(result) = STUB_SPAWNS.lock().pop() {
+        return result;
     }
+    spawn_mcp_server(spec, log_path, auth).await
+}
+
+/// Injected spawn outcomes, popped instead of spawning a real transport:
+/// nothing in a test environment speaks MCP over stdio or HTTP, so the
+/// connect path is exercised with fixture handles. Empty means spawn for
+/// real.
+#[cfg(test)]
+static STUB_SPAWNS: Mutex<Vec<Result<Arc<ConnectedServer>>>> = Mutex::new(Vec::new());
 
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::config::test_fixtures::FixtureServer;
+    use crate::config::{AppConfig, AppState, RequestContext, WorkingMode};
+    use crate::hooks::{HookDef, HooksMap, test_sink};
     use crate::mcp::{JsonField, McpServer, McpTransportType};
+    use anyhow::anyhow;
     use indexmap::IndexMap;
+    use rmcp::ServiceExt;
+    use serial_test::serial;
     use std::collections::HashMap;
 
     fn stdio_spec(
@@ -299,26 +349,195 @@ mod tests {
         }
     }
 
-    #[test]
-    fn factory_try_get_active_returns_none_when_empty() {
-        let factory = McpFactory::default();
-        let spec = stdio_spec("cmd", None, None);
-        let key = McpServerKey::from_spec("s", &spec);
-        assert!(factory.try_get_active(&key).is_none());
-    }
-
-    #[test]
-    fn factory_try_get_active_returns_none_for_unknown_key() {
-        let factory = McpFactory::default();
-        let spec = stdio_spec("cmd", None, None);
-        let key = McpServerKey::from_spec("s", &spec);
-        assert!(factory.try_get_active(&key).is_none());
-    }
-
     #[test]
     fn factory_default_has_empty_active_map() {
         let factory = McpFactory::default();
         let map = factory.active.lock();
         assert!(map.is_empty());
     }
+
+    /// Clears injected spawn outcomes on drop so a panicking test cannot
+    /// leak stubs into later tests.
+    struct StubSpawnsGuard;
+
+    impl StubSpawnsGuard {
+        fn push(result: Result<Arc<ConnectedServer>>) -> Self {
+            STUB_SPAWNS.lock().push(result);
+            StubSpawnsGuard
+        }
+    }
+
+    impl Drop for StubSpawnsGuard {
+        fn drop(&mut self) {
+            STUB_SPAWNS.lock().clear();
+        }
+    }
+
+    /// An in-process client/server pair; the returned server half must stay
+    /// alive for the client handle to keep working.
+    async fn fixture_handle() -> (Arc<ConnectedServer>, impl Sized) {
+        let (client_io, server_io) = tokio::io::duplex(4096);
+        let (server, client) = tokio::join!(
+            FixtureServer::default().serve(server_io),
+            ().serve(client_io)
+        );
+        (Arc::new(client.unwrap()), server.unwrap())
+    }
+
+    fn ctx_with_mcp_hooks(marker: &str) -> RequestContext {
+        let mut hooks_map = HooksMap::default();
+        for event in ["mcp.server.connected", "mcp.server.failed"] {
+            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::Cmd)
+    }
+
+    fn mcp_captures(marker: &str) -> Vec<test_sink::Capture> {
+        test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name.starts_with(marker))
+            .collect()
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn acquire_fires_connected_only_on_real_spawns_and_marks_reconnects() {
+        let _sink = test_sink::install();
+        let marker = "mcp-spawn-k7d";
+        let ctx = ctx_with_mcp_hooks(marker);
+        let hooks = McpServerHooks::resolve(&ctx);
+        let factory = McpFactory::default();
+        let spec = stdio_spec("fixture-server-cmd", None, None);
+
+        let (first, _first_server) = fixture_handle().await;
+        let stub = StubSpawnsGuard::push(Ok(first.clone()));
+        let connected = factory.acquire("srv", &spec, None, &hooks).await.unwrap();
+        drop(stub);
+        assert!(Arc::ptr_eq(&connected, &first));
+        let captures = mcp_captures(marker);
+        assert_eq!(captures.len(), 1, "{captures:?}");
+        let capture = &captures[0];
+        assert_eq!(capture.hook_name, format!("{marker}-mcp.server.connected"));
+        assert_eq!(
+            capture.envs.get("COYOTE_MCP_SERVER").map(String::as_str),
+            Some("srv")
+        );
+        assert_eq!(
+            capture.envs.get("COYOTE_MCP_TRANSPORT").map(String::as_str),
+            Some("stdio")
+        );
+        assert!(
+            !capture.envs.contains_key("COYOTE_MCP_RECONNECT"),
+            "a first connect must not be marked as a reconnect"
+        );
+
+        let reused = factory.acquire("srv", &spec, None, &hooks).await.unwrap();
+        assert!(Arc::ptr_eq(&reused, &first));
+        assert_eq!(
+            mcp_captures(marker).len(),
+            1,
+            "reusing a live server must fire nothing"
+        );
+
+        // Every holder dropped: the weak in the factory dies, and the next
+        // acquire is a real spawn again — now marked as a reconnect.
+        drop(connected);
+        drop(reused);
+        drop(first);
+        let (second, _second_server) = fixture_handle().await;
+        let _stub = StubSpawnsGuard::push(Ok(second.clone()));
+        let respawned = factory.acquire("srv", &spec, None, &hooks).await.unwrap();
+        assert!(Arc::ptr_eq(&respawned, &second));
+        let captures = mcp_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(
+            captures[1]
+                .envs
+                .get("COYOTE_MCP_RECONNECT")
+                .map(String::as_str),
+            Some("true")
+        );
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn acquire_spawn_failure_fires_failed_with_the_error() {
+        let _sink = test_sink::install();
+        let marker = "mcp-fail-v2q";
+        let ctx = ctx_with_mcp_hooks(marker);
+        let hooks = McpServerHooks::resolve(&ctx);
+        let factory = McpFactory::default();
+        // No stub: the nonexistent binary drives the real spawn-error path.
+        let spec = stdio_spec("coyote-nonexistent-mcp-binary-v2q", None, None);
+
+        let result = factory.acquire("bad-srv", &spec, None, &hooks).await;
+
+        assert!(result.is_err());
+        let captures = mcp_captures(marker);
+        assert_eq!(captures.len(), 1, "{captures:?}");
+        let capture = &captures[0];
+        assert_eq!(capture.hook_name, format!("{marker}-mcp.server.failed"));
+        assert_eq!(
+            capture.envs.get("COYOTE_MCP_SERVER").map(String::as_str),
+            Some("bad-srv")
+        );
+        assert_eq!(
+            capture.envs.get("COYOTE_MCP_TRANSPORT").map(String::as_str),
+            Some("stdio")
+        );
+        assert!(
+            capture
+                .envs
+                .get("COYOTE_ERROR")
+                .is_some_and(|error| !error.is_empty())
+        );
+        assert!(
+            !capture.envs.contains_key("COYOTE_MCP_AUTH_REQUIRED"),
+            "a plain spawn failure must not be flagged as auth-required"
+        );
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn acquire_auth_failure_sets_the_auth_required_flag() {
+        let _sink = test_sink::install();
+        let marker = "mcp-auth-h4n";
+        let ctx = ctx_with_mcp_hooks(marker);
+        let hooks = McpServerHooks::resolve(&ctx);
+        let factory = McpFactory::default();
+        let spec = stdio_spec("oauth-cmd", None, None);
+        let _stub = StubSpawnsGuard::push(Err(anyhow!("Auth required: no stored token")));
+
+        let err = factory
+            .acquire("oauth-srv", &spec, None, &hooks)
+            .await
+            .unwrap_err();
+
+        assert!(
+            err.downcast_ref::<McpAuthRequired>().is_some(),
+            "the auth error must be wrapped in McpAuthRequired context"
+        );
+        let captures = mcp_captures(marker);
+        assert_eq!(captures.len(), 1, "{captures:?}");
+        let capture = &captures[0];
+        assert_eq!(capture.hook_name, format!("{marker}-mcp.server.failed"));
+        assert_eq!(
+            capture
+                .envs
+                .get("COYOTE_MCP_AUTH_REQUIRED")
+                .map(String::as_str),
+            Some("true")
+        );
+    }
 }

src/config/mod.rs

@@ -3,6 +3,7 @@ mod app_config;
 mod app_state;
 pub(crate) mod builtin_manifest;
 mod bundles;
+pub(crate) mod conflict;
 mod input;
 mod install_remote;
 pub(crate) mod instructions;
@@ -37,6 +38,7 @@ pub use self::app_config::AppConfig;
 pub use self::app_state::AppState;
 pub(crate) use self::bundles::installed_bundle_names;
 pub use self::bundles::list_installed_bundles;
+use self::conflict::{InstallMode, StickyMode};
 pub use self::input::Input;
 pub use self::install_remote::{
     DEFAULT_GIT_HOST, install_or_update, install_or_update_from_repl_args, uninstall_bundle,
@@ -56,7 +58,7 @@ pub use self::request_context::{
 pub use self::role::{
     CODE_ROLE, CREATE_TITLE_ROLE, EXPLAIN_SHELL_ROLE, Role, RoleLike, SHELL_ROLE,
 };
-pub use self::session::Session;
+pub use self::session::{Session, SessionScope, labeled_session_names, session_scope_dirs};
 #[allow(unused_imports)]
 pub use self::skill::Skill;
 #[allow(unused_imports)]
@@ -181,7 +183,7 @@ const MCP_FILE_NAME: &str = "mcp.json";
 const HIDDEN_MCP_FILE_NAME: &str = ".mcp.json";
 const MEMORY_DIR_NAME: &str = "memory";
 const MEMORY_INDEX_FILE_NAME: &str = "MEMORY.md";
-const WORKSPACE_COYOTE_DIR_NAME: &str = ".coyote";
+pub(crate) const WORKSPACE_COYOTE_DIR_NAME: &str = ".coyote";
 const SBX_KIT_DIR_NAME: &str = "sbx-kit";
 const SBX_KIT_HASH_FILE: &str = "kit.sha256";
 const SBX_MIXIN_FILE_NAME: &str = "sbx-mixin.yaml";
@@ -284,6 +286,7 @@ pub struct Config {
     pub compression_threshold: usize,
     pub compression_keep_last: usize,
     pub compression_model: Option<String>,
+    pub compression_safety_valve: f32,
     pub summarization_prompt: Option<String>,
     pub summary_context_prompt: Option<String>,
     pub max_tool_result_chars: Option<usize>,
@@ -374,6 +377,7 @@ impl Default for Config {
             compression_threshold: 4000,
             compression_keep_last: 0,
             compression_model: None,
+            compression_safety_valve: 0.8,
             summarization_prompt: None,
             summary_context_prompt: None,
             max_tool_result_chars: None,
@@ -417,12 +421,13 @@ impl Default for Config {
 }
 
 pub fn install_builtins() -> Result<()> {
+    hooks::sweep_stale_payload_files();
     Functions::install_builtin_global_tools(false)?;
-    Agent::install_builtin_agents(false)?;
+    Agent::install_builtin_agents(InstallMode::Skip)?;
     Macro::install_macros(false)?;
     Skill::install_builtin_skills(false)?;
-    hooks::install_builtin_hooks(false)?;
-    Role::install_builtin_role_hooks(false)?;
+    hooks::install_builtin_hooks(InstallMode::Skip, &mut StickyMode::None)?;
+    Role::install_builtin_role_hooks(InstallMode::Skip, &mut StickyMode::None)?;
     Ok(())
 }
 
@@ -519,11 +524,16 @@ pub fn install_assets(category: AssetCategory) -> Result<()> {
     }
 
     match category {
-        AssetCategory::Agents => Agent::install_builtin_agents(true)?,
+        AssetCategory::Agents => Agent::install_builtin_agents(InstallMode::Force)?,
         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::Hooks => {
+            let mut sticky = StickyMode::None;
+            hooks::install_builtin_hooks(InstallMode::Prompt, &mut sticky)?;
+            Role::install_builtin_role_hooks(InstallMode::Prompt, &mut sticky)?;
+            Agent::install_builtin_agent_hooks(InstallMode::Prompt, &mut sticky)?;
+        }
         AssetCategory::McpConfig => Functions::install_mcp_config()?,
     }
 
@@ -544,6 +554,14 @@ fn confirm_asset_overwrite(category: AssetCategory, label: &str, target: &Path)
              references) are left untouched.",
             target.display()
         ),
+        AssetCategory::Hooks => format!(
+            "Refreshing bundled hooks installs any missing bundled hook \
+             scripts in {}, the roles hooks directory, and each bundled \
+             agent's hooks directory. Where a local copy differs from the \
+             bundled version you are asked per file whether to keep or \
+             replace it; non-interactive runs keep local files.",
+            target.display()
+        ),
         _ => format!(
             "Reinstalling bundled {label} overwrites every bundled {label} in \
              {} with this build's packaged versions. Local changes to bundled \
@@ -565,10 +583,6 @@ pub fn default_sessions_dir() -> PathBuf {
     }
 }
 
-pub fn list_sessions() -> Vec<String> {
-    list_file_names(default_sessions_dir(), ".yaml")
-}
-
 /// Refreshes the models override. With a URL, mirrors a full models.yaml from
 /// it; without one, rebuilds the catalog from the live models.dev + OpenRouter
 /// APIs merged with the embedded quirks.
@@ -729,11 +743,17 @@ pub fn maybe_spawn_models_refresh(app: &AppConfig) {
 }
 
 impl Config {
-    pub async fn load_with_interpolation(info_flag: bool) -> Result<Self> {
+    pub async fn load_with_interpolation(
+        skip_interpolation: bool,
+        inspection: bool,
+    ) -> Result<Self> {
         let config_path = paths::config_file();
 
         if env::var_os(SANDBOX_ENV_FLAG).is_some() {
             if !config_path.exists() {
+                if inspection {
+                    return Ok(Self::default());
+                }
                 create_config_file(&config_path).await?;
             }
 
@@ -748,6 +768,9 @@ impl Config {
             {
                 Some(v) => (Self::load_dynamic(&v)?, String::new()),
                 None => {
+                    if inspection {
+                        return Ok(Self::default());
+                    }
                     if *IS_STDOUT_TERMINAL {
                         create_config_file(&config_path).await?;
                     }
@@ -758,7 +781,7 @@ impl Config {
             Self::load_from_file(&config_path)?
         };
 
-        if info_flag {
+        if skip_interpolation {
             return Ok(config);
         }
 
@@ -1120,6 +1143,32 @@ pub(crate) fn ensure_parent_exists(path: &Path) -> Result<()> {
     Ok(())
 }
 
+/// The one exec-bit policy for every hook/agent installer: a file is
+/// executable iff `Language::from_extension` recognizes its extension.
+/// Users may keep non-executable support files in hooks directories, so
+/// installers must write plain and then apply this predicate — never
+/// blanket-0755.
+#[cfg(unix)]
+pub(crate) fn set_executable_bit_if_script(path: &Path) -> Result<()> {
+    use crate::function::Language;
+    use std::os::unix::fs::PermissionsExt;
+
+    let Some(ext) = path.extension().and_then(std::ffi::OsStr::to_str) else {
+        return Ok(());
+    };
+    if Language::from_extension(ext) == Language::Unsupported {
+        return Ok(());
+    }
+    fs::set_permissions(path, fs::Permissions::from_mode(0o755))
+        .with_context(|| format!("chmod {}", path.display()))?;
+    Ok(())
+}
+
+#[cfg(not(unix))]
+pub(crate) fn set_executable_bit_if_script(_path: &Path) -> Result<()> {
+    Ok(())
+}
+
 fn read_env_value<T>(key: &str) -> Option<Option<T>>
 where
     T: std::str::FromStr,
@@ -1328,6 +1377,7 @@ clients:
         assert!(cfg.mcp_server_support);
         assert_eq!(cfg.compression_threshold, 4000);
         assert!(cfg.compression_model.is_none());
+        assert_eq!(cfg.compression_safety_valve, 0.8);
         assert_eq!(cfg.rag_top_k, 5);
         assert!(cfg.save_shell_history);
         assert_eq!(cfg.keybindings, "emacs");
@@ -1368,6 +1418,7 @@ clients:
         assert!(cfg.mapping_tools.is_empty());
         assert!(cfg.document_loaders.is_empty());
         assert_eq!(cfg.compression_threshold, 4000);
+        assert_eq!(cfg.compression_safety_valve, 0.8);
         assert!(cfg.theme.is_none());
         assert_eq!(cfg.clients.len(), 1);
     }
@@ -1593,12 +1644,12 @@ hooks:
         use std::fs;
         use std::time;
 
-        let unique = time::SystemTime::now()
+        let unique = SystemTime::now()
             .duration_since(time::UNIX_EPOCH)
             .unwrap()
             .as_nanos();
-        let tmp_dir = std::env::temp_dir().join(format!("coyote-sandbox-cfg-{unique}"));
-        fs::create_dir_all(&tmp_dir).unwrap();
+        let tmp_dir = env::temp_dir().join(format!("coyote-sandbox-cfg-{unique}"));
+        create_dir_all(&tmp_dir).unwrap();
         let config_path = tmp_dir.join("config.yaml");
 
         fs::write(
@@ -1608,25 +1659,25 @@ hooks:
         .unwrap();
 
         let config_env = get_env_name("config_file");
-        let prev_config = std::env::var_os(&config_env);
-        let prev_sandbox = std::env::var_os(crate::sandbox::SANDBOX_ENV_FLAG);
+        let prev_config = env::var_os(&config_env);
+        let prev_sandbox = env::var_os(SANDBOX_ENV_FLAG);
 
         unsafe {
-            std::env::set_var(&config_env, &config_path);
-            std::env::set_var(crate::sandbox::SANDBOX_ENV_FLAG, "1");
+            env::set_var(&config_env, &config_path);
+            env::set_var(SANDBOX_ENV_FLAG, "1");
         }
 
-        let result = Config::load_with_interpolation(false).await;
+        let result = Config::load_with_interpolation(false, false).await;
         let (_, raw) = Config::load_from_file(&config_path).unwrap();
 
         unsafe {
             match prev_config {
-                Some(v) => std::env::set_var(&config_env, v),
-                None => std::env::remove_var(&config_env),
+                Some(v) => env::set_var(&config_env, v),
+                None => env::remove_var(&config_env),
             }
             match prev_sandbox {
-                Some(v) => std::env::set_var(crate::sandbox::SANDBOX_ENV_FLAG, v),
-                None => std::env::remove_var(crate::sandbox::SANDBOX_ENV_FLAG),
+                Some(v) => env::set_var(SANDBOX_ENV_FLAG, v),
+                None => env::remove_var(SANDBOX_ENV_FLAG),
             }
         }
         let _ = fs::remove_dir_all(&tmp_dir);
@@ -1640,6 +1691,60 @@ hooks:
         );
     }
 
+    #[tokio::test]
+    #[serial_test::serial]
+    async fn info_flag_with_missing_config_skips_wizard_and_writes_nothing() {
+        let unique = SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap()
+            .as_nanos();
+        let tmp_dir = env::temp_dir().join(format!("coyote-info-bypass-{unique}"));
+        create_dir_all(&tmp_dir).unwrap();
+        let _config_dir = crate::testing::EnvVarGuard::set(get_env_name("config_dir"), &tmp_dir);
+        let _config_file = crate::testing::EnvVarGuard::unset(get_env_name("config_file"));
+        let _sandbox = crate::testing::EnvVarGuard::unset(SANDBOX_ENV_FLAG);
+        let _provider = crate::testing::EnvVarGuard::unset(get_env_name("provider"));
+        let _platform = crate::testing::EnvVarGuard::unset(get_env_name("platform"));
+
+        let result = Config::load_with_interpolation(true, true).await;
+
+        let leftover: Vec<_> = read_dir(&tmp_dir)
+            .unwrap()
+            .map(|entry| entry.unwrap().file_name())
+            .collect();
+        let _ = fs::remove_dir_all(&tmp_dir);
+        result.expect("inspection flags must load a default config without a config file");
+        assert!(
+            leftover.is_empty(),
+            "inspection flags must not write anything: {leftover:?}"
+        );
+    }
+
+    #[tokio::test]
+    #[serial_test::serial]
+    async fn sandbox_info_flag_with_missing_config_writes_nothing() {
+        let unique = SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap()
+            .as_nanos();
+        let tmp_dir = env::temp_dir().join(format!("coyote-sandbox-info-bypass-{unique}"));
+        create_dir_all(&tmp_dir).unwrap();
+        let config_path = tmp_dir.join("config.yaml");
+        let _config_file =
+            crate::testing::EnvVarGuard::set(get_env_name("config_file"), &config_path);
+        let _sandbox = crate::testing::EnvVarGuard::set(SANDBOX_ENV_FLAG, "1");
+
+        let result = Config::load_with_interpolation(true, true).await;
+
+        let created = config_path.exists();
+        let _ = fs::remove_dir_all(&tmp_dir);
+        result.expect("inspection flags must load a default config in sandbox mode too");
+        assert!(
+            !created,
+            "inspection flags must not create the sandbox config file"
+        );
+    }
+
     #[test]
     fn unloadable_override_is_stale() {
         assert!(models_override_is_stale(false, Some(SystemTime::now()), 24));
@@ -1719,7 +1824,7 @@ hooks:
             let written = write_models_override(vec![entry()]).unwrap();
             assert_eq!(written, path);
             let mut tmp_name = path.as_os_str().to_os_string();
-            tmp_name.push(format!(".{}.tmp", std::process::id()));
+            tmp_name.push(format!(".{}.tmp", process::id()));
             assert!(!PathBuf::from(tmp_name).exists());
             let loaded = paths::local_models_override().unwrap();
             assert_eq!(loaded.len(), 1);
@@ -1737,4 +1842,117 @@ hooks:
             std::panic::resume_unwind(panic);
         }
     }
+
+    use crate::testing::TestConfigDirGuard;
+
+    #[test]
+    #[serial_test::serial]
+    fn install_assets_hooks_shares_one_sticky_scope_across_all_three_locations() {
+        use crate::config::conflict::prompt_script;
+
+        let _guard = TestConfigDirGuard::new("hooks-three-locations");
+        let notify = paths::hooks_dir().join("notify.sh");
+        let role_dir = paths::roles_dir().join("hooks");
+        let agent_dir = paths::agents_data_dir().join("probe").join("hooks");
+        let shipped = vec![("hook.sh".to_string(), "shipped\n".to_string())];
+
+        // Drives the exact three installers `install_assets(Hooks)` runs,
+        // threading one sticky scope through all of them.
+        let refresh = |sticky: &mut StickyMode| {
+            hooks::install_builtin_hooks(InstallMode::Prompt, sticky).unwrap();
+            role::install_and_reconcile_role_hooks(
+                &role_dir,
+                &shipped,
+                InstallMode::Prompt,
+                sticky,
+            )
+            .unwrap();
+            agent::install_and_reconcile_agent_hooks(
+                "probe",
+                &shipped,
+                InstallMode::Prompt,
+                sticky,
+            )
+            .unwrap();
+        };
+        let modify_all = || {
+            fs::write(&notify, "local global").unwrap();
+            fs::write(role_dir.join("hook.sh"), "local role").unwrap();
+            fs::write(agent_dir.join("hook.sh"), "local agent").unwrap();
+        };
+
+        let script = prompt_script::install(&[]);
+        refresh(&mut StickyMode::None);
+        assert_eq!(
+            prompt_script::prompts_asked(),
+            0,
+            "a clean install asks nothing"
+        );
+        drop(script);
+
+        // One replace-all at the first (global) conflict must silently
+        // replace the role and agent conflicts too.
+        modify_all();
+        let script = prompt_script::install(&["replace-all"]);
+        let mut sticky = StickyMode::None;
+        refresh(&mut sticky);
+        assert_eq!(prompt_script::prompts_asked(), 1);
+        assert_eq!(sticky, StickyMode::ReplaceAll);
+        assert!(
+            read_to_string(&notify)
+                .unwrap()
+                .starts_with("#!/usr/bin/env bash")
+        );
+        assert_eq!(
+            read_to_string(role_dir.join("hook.sh")).unwrap(),
+            "shipped\n"
+        );
+        assert_eq!(
+            read_to_string(agent_dir.join("hook.sh")).unwrap(),
+            "shipped\n"
+        );
+        drop(script);
+
+        // And one keep-all must keep every location's local edit.
+        modify_all();
+        let script = prompt_script::install(&["keep-all"]);
+        let mut sticky = StickyMode::None;
+        refresh(&mut sticky);
+        assert_eq!(prompt_script::prompts_asked(), 1);
+        assert_eq!(sticky, StickyMode::KeepAll);
+        assert_eq!(read_to_string(&notify).unwrap(), "local global");
+        assert_eq!(
+            read_to_string(role_dir.join("hook.sh")).unwrap(),
+            "local role"
+        );
+        assert_eq!(
+            read_to_string(agent_dir.join("hook.sh")).unwrap(),
+            "local agent"
+        );
+        drop(script);
+    }
+
+    #[test]
+    #[serial_test::serial]
+    fn install_builtins_never_prompts_and_keeps_local_hook_edits() {
+        use crate::config::conflict::prompt_script;
+
+        let _guard = TestConfigDirGuard::new("install-builtins-startup");
+        install_builtins().unwrap();
+        let notify = paths::hooks_dir().join("notify.sh");
+        fs::write(&notify, "# local edit").unwrap();
+
+        // A forced terminal with no scripted answers: any prompt would panic
+        // and the counter would move.
+        let script = prompt_script::install(&[]);
+        install_builtins().unwrap();
+        assert_eq!(prompt_script::prompts_asked(), 0);
+        assert_eq!(read_to_string(&notify).unwrap(), "# local edit");
+        drop(script);
+
+        let _script = prompt_script::install_non_interactive();
+        install_builtins().unwrap();
+        assert_eq!(prompt_script::prompts_asked(), 0);
+        assert_eq!(read_to_string(&notify).unwrap(), "# local edit");
+    }
 }

src/config/paths.rs

@@ -5,7 +5,7 @@ use super::{
     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,
+    SBX_MIXIN_KITS_DIR_NAME, SESSIONS_DIR_NAME, SKILLS_DIR_NAME, WORKSPACE_COYOTE_DIR_NAME,
 };
 use crate::client::ProviderModels;
 use crate::config::REPL_HISTORY_DIR_NAME;
@@ -229,6 +229,17 @@ pub fn workspace_macros_dir() -> PathBuf {
     workspace_config_dir().join(MACROS_DIR_NAME)
 }
 
+pub fn workspace_sessions_dir() -> PathBuf {
+    workspace_config_dir().join(SESSIONS_DIR_NAME)
+}
+
+pub fn workspace_agent_sessions_dir(name: &str) -> PathBuf {
+    workspace_config_dir()
+        .join(AGENTS_DIR_NAME)
+        .join(name)
+        .join(SESSIONS_DIR_NAME)
+}
+
 pub fn workspace_mcp_config_file() -> Option<PathBuf> {
     workspace_mcp_config_file_in(&env::current_dir().unwrap_or_default())
 }
@@ -332,6 +343,10 @@ pub fn agent_data_dir(name: &str) -> PathBuf {
     }
 }
 
+pub fn agent_sessions_dir(name: &str) -> PathBuf {
+    agent_data_dir(name).join(SESSIONS_DIR_NAME)
+}
+
 pub fn agent_graph_file(agent_name: &str) -> PathBuf {
     agent_data_dir(agent_name).join(AGENT_GRAPH_FILE_NAME)
 }
@@ -854,6 +869,21 @@ mod tests {
                 );
             });
         }
+
+        #[test]
+        #[serial]
+        fn workspace_session_dirs_live_under_workspace_config_dir() {
+            with_workspace_dir(|_, ws_dir| {
+                assert_eq!(workspace_sessions_dir(), ws_dir.join(SESSIONS_DIR_NAME));
+                assert_eq!(
+                    workspace_agent_sessions_dir("helper"),
+                    ws_dir
+                        .join(AGENTS_DIR_NAME)
+                        .join("helper")
+                        .join(SESSIONS_DIR_NAME)
+                );
+            });
+        }
     }
 
     mod user_mcp_resolution {

src/config/rag_cache.rs

@@ -47,3 +47,61 @@ impl RagCache {
         Ok(arc)
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::config::AppConfig;
+    use crate::hooks::test_sink;
+    use crate::rag::RagData;
+    use anyhow::anyhow;
+    use serial_test::serial;
+    use std::time::{SystemTime, UNIX_EPOCH};
+
+    /// A cache hit must never reach the loader: the loader closure is where
+    /// a real RAG build (and its `rag.sync.*` hook dispatch) happens, so
+    /// returning the cached entry is what keeps warm-cache lookups silent.
+    #[tokio::test]
+    #[serial]
+    async fn cache_hit_returns_the_cached_rag_without_running_the_loader() {
+        let _sink = test_sink::install();
+        test_sink::drain();
+        let unique = SystemTime::now()
+            .duration_since(UNIX_EPOCH)
+            .unwrap()
+            .as_nanos();
+        let dir = std::env::temp_dir().join(format!("coyote-rag-cache-hit-{unique}"));
+        std::fs::create_dir_all(&dir).unwrap();
+        let path = dir.join("kb.yaml");
+        let data = RagData {
+            driver: "yaml".to_string(),
+            // The only embedding model resolvable in tests; see
+            // `seed_model_registries` in the request_context tests.
+            embedding_model: "test-seeded:test-embedder".to_string(),
+            chunk_size: 1000,
+            chunk_overlap: 100,
+            top_k: 5,
+            ..Default::default()
+        };
+        std::fs::write(&path, serde_yaml::to_string(&data).unwrap()).unwrap();
+        let rag = Arc::new(Rag::load(&AppConfig::default(), "kb", &path).await.unwrap());
+        let _ = std::fs::remove_dir_all(&dir);
+
+        let cache = RagCache::default();
+        let key = RagKey::Named("kb".to_string());
+        cache.insert(key.clone(), &rag);
+
+        let loaded = cache
+            .load_with(key, || async {
+                Err(anyhow!("a cache hit must not rebuild"))
+            })
+            .await
+            .unwrap();
+
+        assert!(Arc::ptr_eq(&loaded, &rag));
+        assert!(
+            test_sink::drain().is_empty(),
+            "a cache hit must dispatch no hooks"
+        );
+    }
+}

src/config/role.rs

@@ -2,6 +2,7 @@ use super::*;
 
 use crate::client::{Message, MessageContent, MessageRole, Model};
 use crate::config::builtin_manifest;
+use crate::config::conflict::{self, InstallMode, StickyMode};
 use crate::function::write_file_atomic;
 use crate::hooks::HooksMap;
 
@@ -179,7 +180,8 @@ impl Role {
     pub fn builtin(name: &str) -> Result<Self> {
         let content = RolesAsset::get(&format!("{name}.md"))
             .ok_or_else(|| anyhow!("Unknown role `{name}`"))?;
-        let content = unsafe { std::str::from_utf8_unchecked(&content.data) };
+        let content =
+            std::str::from_utf8(&content.data).expect("bundled role asset is not valid UTF-8");
         Ok(Role::new(name, content))
     }
 
@@ -193,7 +195,7 @@ impl Role {
     /// 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<()> {
+    pub fn install_builtin_role_hooks(mode: InstallMode, sticky: &mut StickyMode) -> Result<()> {
         let shipped: Vec<(String, String)> = RolesAsset::iter()
             .filter_map(|file| {
                 let name = file.as_ref().strip_prefix("hooks/")?;
@@ -201,12 +203,13 @@ impl Role {
                     return None;
                 }
                 let embedded = RolesAsset::get(file.as_ref())?;
-                let content = unsafe { std::str::from_utf8_unchecked(&embedded.data) };
+                let content = std::str::from_utf8(&embedded.data)
+                    .expect("bundled role hook asset is not valid UTF-8");
                 Some((name.to_string(), content.to_string()))
             })
             .collect();
 
-        install_and_reconcile_role_hooks(&paths::roles_dir().join("hooks"), &shipped, force)
+        install_and_reconcile_role_hooks(&paths::roles_dir().join("hooks"), &shipped, mode, sticky)
     }
 
     pub fn has_args(&self) -> bool {
@@ -641,10 +644,11 @@ fn parse_structure_prompt(prompt: &str) -> (&str, Vec<(&str, &str)>) {
 /// 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(
+pub(crate) fn install_and_reconcile_role_hooks(
     dir: &Path,
     shipped: &[(String, String)],
-    force: bool,
+    mode: InstallMode,
+    sticky: &mut StickyMode,
 ) -> Result<()> {
     if !shipped.is_empty() {
         info!("Installing built-in role hooks in {}", dir.display());
@@ -652,7 +656,9 @@ fn install_and_reconcile_role_hooks(
     let mut written = BTreeSet::new();
     for (name, content) in shipped {
         let path = dir.join(name);
-        if path.exists() && !force {
+        if path.exists()
+            && !conflict::should_replace_existing(&path, content, "roles", mode, sticky)?
+        {
             debug!(
                 "Role hook file already exists, skipping: {}",
                 path.display()
@@ -661,7 +667,8 @@ fn install_and_reconcile_role_hooks(
         }
         ensure_parent_exists(&path)?;
         info!("Creating role hook file: {}", path.display());
-        write_file_atomic(&path, content, Some(0o755))?;
+        write_file_atomic(&path, content, None)?;
+        set_executable_bit_if_script(&path)?;
         written.insert(name.clone());
     }
 
@@ -1049,7 +1056,12 @@ Input 1
     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)
+        install_and_reconcile_role_hooks(
+            &dir,
+            &fixture(&[("a.sh", "#!/bin/sh\n")]),
+            InstallMode::Skip,
+            &mut StickyMode::None,
+        )
         .unwrap();
 
         assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "#!/bin/sh\n");
@@ -1075,6 +1087,41 @@ Input 1
         let _ = fs::remove_dir_all(dir.parent().unwrap());
     }
 
+    /// The installer writes plain and then applies the shared exec-bit
+    /// predicate: users may keep non-executable support files in hooks
+    /// directories, so only recognized script extensions get 0755.
+    #[cfg(unix)]
+    #[test]
+    fn role_hooks_install_leaves_non_script_files_non_executable() {
+        use std::os::unix::fs::PermissionsExt;
+
+        let dir = hooks_fixture_dir("role-hooks-nonscript-");
+
+        install_and_reconcile_role_hooks(
+            &dir,
+            &fixture(&[("README.md", "docs\n"), ("run.sh", "#!/bin/sh\n")]),
+            InstallMode::Skip,
+            &mut StickyMode::None,
+        )
+        .unwrap();
+
+        let readme_mode = fs::metadata(dir.join("README.md"))
+            .unwrap()
+            .permissions()
+            .mode();
+        assert_eq!(
+            readme_mode & 0o111,
+            0,
+            "a non-script file in a hooks dir must stay non-executable"
+        );
+        let script_mode = fs::metadata(dir.join("run.sh"))
+            .unwrap()
+            .permissions()
+            .mode();
+        assert_eq!(script_mode & 0o777, 0o755);
+        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-");
@@ -1082,14 +1129,50 @@ Input 1
         create_dir_all(&dir).unwrap();
         fs::write(dir.join("a.sh"), "SENTINEL").unwrap();
 
-        install_and_reconcile_role_hooks(&dir, &shipped, false).unwrap();
+        install_and_reconcile_role_hooks(&dir, &shipped, InstallMode::Skip, &mut StickyMode::None)
+            .unwrap();
         assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "SENTINEL");
 
-        install_and_reconcile_role_hooks(&dir, &shipped, true).unwrap();
+        install_and_reconcile_role_hooks(&dir, &shipped, InstallMode::Force, &mut StickyMode::None)
+            .unwrap();
         assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "new content\n");
         let _ = fs::remove_dir_all(dir.parent().unwrap());
     }
 
+    #[test]
+    #[serial_test::serial]
+    fn role_hooks_prompt_mode_asks_per_conflict_and_honors_sticky() {
+        use crate::config::conflict::prompt_script;
+
+        let dir = hooks_fixture_dir("role-hooks-prompt-");
+        let shipped = fixture(&[("a.sh", "new content\n"), ("b.sh", "new content\n")]);
+        create_dir_all(&dir).unwrap();
+        fs::write(dir.join("a.sh"), "local a").unwrap();
+        fs::write(dir.join("b.sh"), "local b").unwrap();
+
+        // First conflict answered per-file, second by the sticky replace-all.
+        let script = prompt_script::install(&["replace-all"]);
+        let mut sticky = StickyMode::None;
+        install_and_reconcile_role_hooks(&dir, &shipped, InstallMode::Prompt, &mut sticky).unwrap();
+        assert_eq!(prompt_script::prompts_asked(), 1);
+        assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "new content\n");
+        assert_eq!(read_to_string(dir.join("b.sh")).unwrap(), "new content\n");
+        assert_eq!(sticky, StickyMode::ReplaceAll);
+        drop(script);
+
+        // A sticky mode carried in from an earlier location suppresses all
+        // prompting: `--install-builtins hooks` shares one sticky scope
+        // across the global, role, and agent hook locations.
+        fs::write(dir.join("a.sh"), "local again").unwrap();
+        let script = prompt_script::install(&[]);
+        let mut sticky = StickyMode::KeepAll;
+        install_and_reconcile_role_hooks(&dir, &shipped, InstallMode::Prompt, &mut sticky).unwrap();
+        assert_eq!(prompt_script::prompts_asked(), 0);
+        assert_eq!(read_to_string(dir.join("a.sh")).unwrap(), "local again");
+        drop(script);
+        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-");
@@ -1097,12 +1180,18 @@ Input 1
         install_and_reconcile_role_hooks(
             &dir,
             &fixture(&[("keep.sh", "#!/bin/sh\n"), ("drop.sh", "#!/bin/sh\n")]),
-            false,
+            InstallMode::Skip,
+            &mut StickyMode::None,
         )
         .unwrap();
         fs::write(dir.join("user.sh"), "user-owned").unwrap();
 
-        install_and_reconcile_role_hooks(&dir, &fixture(&[("keep.sh", "#!/bin/sh\n")]), false)
+        install_and_reconcile_role_hooks(
+            &dir,
+            &fixture(&[("keep.sh", "#!/bin/sh\n")]),
+            InstallMode::Skip,
+            &mut StickyMode::None,
+        )
         .unwrap();
 
         assert!(
@@ -1124,14 +1213,20 @@ Input 1
         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)
+        install_and_reconcile_role_hooks(
+            &dir,
+            &fixture(&[("a.sh", "#!/bin/sh\n")]),
+            InstallMode::Skip,
+            &mut StickyMode::None,
+        )
         .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();
+        install_and_reconcile_role_hooks(&dir, &[], InstallMode::Skip, &mut StickyMode::None)
+            .unwrap();
         assert_eq!(
             read_to_string(dir.join("a.sh")).unwrap(),
             "user-owned",
@@ -1144,7 +1239,8 @@ Input 1
     fn role_hooks_empty_shipped_set_creates_nothing() {
         let dir = hooks_fixture_dir("role-hooks-empty-");
 
-        install_and_reconcile_role_hooks(&dir, &[], false).unwrap();
+        install_and_reconcile_role_hooks(&dir, &[], InstallMode::Skip, &mut StickyMode::None)
+            .unwrap();
 
         assert!(!dir.exists(), "an empty shipped set must not create hooks/");
         let _ = fs::remove_dir_all(dir.parent().unwrap());

src/config/session.rs

@@ -12,8 +12,10 @@ use inquire::{Confirm, Text, validator::Validation};
 use serde::{Deserialize, Serialize};
 use serde_json::json;
 use std::collections::HashMap;
-use std::fs::{read_to_string, write};
-use std::path::Path;
+use std::fmt;
+use std::fs::{OpenOptions, read_to_string, remove_file, rename};
+use std::io::{self, Write as _};
+use std::path::{Path, PathBuf};
 use std::sync::LazyLock;
 
 static RE_AUTONAME_PREFIX: LazyLock<Regex> = LazyLock::new(|| Regex::new(r"\d{8}T\d{6}-").unwrap());
@@ -29,6 +31,62 @@ fn cost_is_zero(v: &f64) -> bool {
     *v == 0.0
 }
 
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
+pub enum SessionScope {
+    #[default]
+    Global,
+    Workspace,
+}
+
+impl fmt::Display for SessionScope {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        match self {
+            SessionScope::Global => write!(f, "global"),
+            SessionScope::Workspace => write!(f, "workspace"),
+        }
+    }
+}
+
+pub fn session_scope_dirs(agent: Option<&str>) -> (PathBuf, PathBuf) {
+    match agent {
+        Some(agent) => (
+            paths::workspace_agent_sessions_dir(agent),
+            paths::agent_sessions_dir(agent),
+        ),
+        None => (paths::workspace_sessions_dir(), default_sessions_dir()),
+    }
+}
+
+/// Session names across both scope dirs, workspace first, deduped by name so
+/// a workspace session shadows a global one with the same name.
+pub fn labeled_session_names(
+    workspace_dir: &Path,
+    global_dir: &Path,
+) -> Vec<(String, SessionScope)> {
+    let mut values = Vec::new();
+    let mut seen = HashSet::new();
+    for (dir, scope) in [
+        (workspace_dir, SessionScope::Workspace),
+        (global_dir, SessionScope::Global),
+    ] {
+        for name in list_file_names(dir, ".yaml") {
+            if seen.insert(name.clone()) {
+                values.push((name, scope));
+            }
+        }
+    }
+    values
+}
+
+pub fn merged_session_names(workspace_dir: &Path, global_dir: &Path) -> Vec<String> {
+    let mut names: Vec<String> = labeled_session_names(workspace_dir, global_dir)
+        .into_iter()
+        .map(|(name, _)| name)
+        .collect();
+    names.sort_unstable();
+    names
+}
+
 #[derive(Debug, Clone, Default, Deserialize, Serialize)]
 pub struct Session {
     #[serde(rename(serialize = "model", deserialize = "model"))]
@@ -120,6 +178,8 @@ pub struct Session {
     #[serde(skip)]
     path: Option<String>,
     #[serde(skip)]
+    scope: SessionScope,
+    #[serde(skip)]
     dirty: bool,
     #[serde(skip)]
     save_session_this_time: bool,
@@ -173,6 +233,7 @@ impl Session {
         app: &AppConfig,
         name: &str,
         path: &Path,
+        scope: SessionScope,
     ) -> Result<Self> {
         let content = read_to_string(path)
             .with_context(|| format!("Failed to load session {} at {}", name, path.display()))?;
@@ -180,6 +241,7 @@ impl Session {
             serde_yaml::from_str(&content).with_context(|| format!("Invalid session {name}"))?;
 
         session.model = Model::retrieve_model(app, &session.model_id, ModelType::Chat)?;
+        session.scope = scope;
 
         if let Some(autoname) = name.strip_prefix("_/") {
             session.name = TEMP_SESSION_NAME.to_string();
@@ -250,6 +312,14 @@ impl Session {
         self.name = name;
     }
 
+    pub fn scope(&self) -> SessionScope {
+        self.scope
+    }
+
+    pub fn set_scope(&mut self, scope: SessionScope) {
+        self.scope = scope;
+    }
+
     pub fn clear_autoname(&mut self) {
         self.autoname = None;
     }
@@ -313,6 +383,7 @@ impl Session {
     pub fn export(&self) -> Result<String> {
         let mut data = json!({
             "path": self.path,
+            "scope": self.scope.to_string(),
             "model": self.model().id(),
         });
         if let Some(temperature) = self.temperature() {
@@ -403,6 +474,7 @@ impl Session {
         if let Some(path) = &self.path {
             items.push(("path", path.to_string()));
         }
+        items.push(("scope", self.scope.to_string()));
 
         if let Some(autoname) = self.autoname() {
             items.push(("autoname", autoname.to_string()));
@@ -719,17 +791,50 @@ impl Session {
         self.reclaimable_tokens(keep_last) >= (threshold / COMPRESSION_MIN_RECLAIM_DIVISOR).max(1)
     }
 
-    /// Estimated tokens of the messages that compression would actually fold
-    /// away: everything except the leading system message (whose content is
-    /// carried into the summary message) and the `keep_last` tail (kept verbatim).
-    fn reclaimable_tokens(&self, keep_last: usize) -> usize {
+    /// Whether the prompt is close enough to the model's hard input limit
+    /// that compression must run regardless of how `compression_threshold`
+    /// is configured. Sizes the prompt as the larger of the API-reported
+    /// measurement from the last request that reported usage and the local
+    /// estimate, because the estimate can run well below the provider's
+    /// real count.
+    pub fn safety_valve_triggered(
+        &self,
+        valve: f32,
+        keep_last: usize,
+        last_prompt_tokens: Option<usize>,
+    ) -> bool {
+        if self.compressing || !valve.is_finite() || valve <= 0.0 {
+            return false;
+        }
+        let Some(max_input_tokens) = self.model().max_input_tokens() else {
+            return false;
+        };
+        // With nothing to fold away, compressing is a no-op; firing anyway
+        // would spin compress attempts while a single in-flight turn holds
+        // all the tokens.
+        if self.reclaimable_tokens(keep_last) == 0 {
+            return false;
+        }
+        last_prompt_tokens.unwrap_or(0).max(self.tokens())
+            >= (valve * max_input_tokens as f32) as usize
+    }
+
+    /// The messages that compression would actually fold away: everything
+    /// except the leading system message (whose content is carried into the
+    /// summary message) and the `keep_last` tail (kept verbatim).
+    pub fn foldable_messages(&self, keep_last: usize) -> &[Message] {
         let start = usize::from(
             self.messages
                 .first()
                 .is_some_and(|v| v.role == MessageRole::System),
         );
         let end = self.messages.len().saturating_sub(keep_last).max(start);
-        self.model().total_tokens(&self.messages[start..end])
+        &self.messages[start..end]
+    }
+
+    /// Estimated tokens of the messages compression would fold away.
+    fn reclaimable_tokens(&self, keep_last: usize) -> usize {
+        self.model().total_tokens(self.foldable_messages(keep_last))
     }
 
     pub fn compressing(&self) -> bool {
@@ -853,17 +958,52 @@ impl Session {
     pub fn save(&mut self, session_name: &str, session_path: &Path, is_repl: bool) -> Result<()> {
         ensure_parent_exists(session_path)?;
 
-        self.path = Some(session_path.display().to_string());
-
         let content = serde_yaml::to_string(&self)
             .with_context(|| format!("Failed to serde session '{}'", self.name))?;
-        write(session_path, content).with_context(|| {
+        // Write through a sibling temp file and rename it over the target so a
+        // symlink planted at the session path is replaced, never followed. The
+        // temp file is opened with create_new so a symlink planted at the temp
+        // path is not followed either; a stale entry there is removed and the
+        // open retried once.
+        let mut tmp_name = session_path.as_os_str().to_os_string();
+        tmp_name.push(format!(".{}.tmp", process::id()));
+        let tmp_path = PathBuf::from(tmp_name);
+        let write_context = || {
             format!(
                 "Failed to write session '{}' to '{}'",
                 self.name,
                 session_path.display()
             )
-        })?;
+        };
+        let open_tmp = || {
+            OpenOptions::new()
+                .write(true)
+                .create_new(true)
+                .open(&tmp_path)
+        };
+        let mut tmp_file = match open_tmp() {
+            Ok(file) => file,
+            Err(error) if error.kind() == io::ErrorKind::AlreadyExists => {
+                remove_file(&tmp_path).with_context(write_context)?;
+                open_tmp().with_context(write_context)?
+            }
+            Err(error) => return Err(error).with_context(write_context),
+        };
+        if let Err(error) = tmp_file
+            .write_all(content.as_bytes())
+            .and_then(|_| tmp_file.flush())
+        {
+            drop(tmp_file);
+            let _ = remove_file(&tmp_path);
+            return Err(error).with_context(write_context);
+        }
+        drop(tmp_file);
+        if let Err(error) = rename(&tmp_path, session_path) {
+            let _ = remove_file(&tmp_path);
+            return Err(error).with_context(write_context);
+        }
+
+        self.path = Some(session_path.display().to_string());
 
         if is_repl {
             println!("✓ Saved the session to '{}'.", session_path.display());
@@ -1109,7 +1249,7 @@ impl AutoName {
 mod tests {
     use super::*;
     use crate::client::{
-        Message, MessageContent, MessageContentToolCalls, MessageRole, Model, TokenUsage,
+        Message, MessageContent, MessageContentToolCalls, MessageRole, Model, ModelData, TokenUsage,
     };
     use crate::config::{AppConfig, AppState, RequestContext, WorkingMode};
     use crate::function::{Functions, ToolCall, ToolResult};
@@ -1284,6 +1424,16 @@ mod tests {
         );
     }
 
+    #[test]
+    fn session_scope_is_not_serialized() {
+        let mut session = Session::default();
+        session.set_scope(SessionScope::Workspace);
+
+        let yaml = serde_yaml::to_string(&session).unwrap();
+
+        assert!(!yaml.contains("scope"));
+    }
+
     #[test]
     fn session_deserialization_ignores_injected_role_hooks() {
         // A session file is attacker-writable data: a `role_hooks:` key
@@ -1323,8 +1473,10 @@ mod tests {
     fn session_export_includes_real_usage_only_when_reported() {
         let empty = Session::default().export().unwrap();
         assert!(!empty.contains("real_input_tokens"));
+        assert!(empty.contains("scope: global"));
 
         let mut session = Session::default();
+        session.set_scope(SessionScope::Workspace);
         session.accumulate_token_usage(&TokenUsage {
             input_tokens: Some(5),
             output_tokens: Some(7),
@@ -1332,12 +1484,97 @@ mod tests {
             cache_read_input_tokens: Some(3),
         });
         let exported = session.export().unwrap();
+        assert!(exported.contains("scope: workspace"));
         assert!(exported.contains("real_input_tokens: 5"));
         assert!(exported.contains("real_output_tokens: 7"));
         assert!(exported.contains("cache_read_tokens: 3"));
         assert!(!exported.contains("cache_creation_tokens"));
     }
 
+    fn rendered_lines(session: &Session) -> Vec<String> {
+        let options = crate::render::RenderOptions {
+            raw_markdown: true,
+            ..Default::default()
+        };
+        let mut render = MarkdownRender::init(options).unwrap();
+        session
+            .render(&mut render, &None)
+            .unwrap()
+            .lines()
+            .map(str::to_string)
+            .collect()
+    }
+
+    #[test]
+    fn session_render_reports_scope_line() {
+        let mut session = Session::default();
+        assert!(
+            rendered_lines(&session)
+                .iter()
+                .any(|line| line.starts_with("scope") && line.ends_with("global"))
+        );
+
+        session.set_scope(SessionScope::Workspace);
+        assert!(
+            rendered_lines(&session)
+                .iter()
+                .any(|line| line.starts_with("scope") && line.ends_with("workspace"))
+        );
+    }
+
+    #[cfg(unix)]
+    #[test]
+    fn session_save_replaces_a_symlink_instead_of_following_it() {
+        let unique = std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap()
+            .as_nanos();
+        let dir = std::env::temp_dir().join(format!("coyote-session-save-symlink-{unique}"));
+        let sessions_dir = dir.join("sessions");
+        std::fs::create_dir_all(&sessions_dir).unwrap();
+        let target = dir.join("target.txt");
+        std::fs::write(&target, "untouched").unwrap();
+        let link = sessions_dir.join("link.yaml");
+        std::os::unix::fs::symlink(&target, &link).unwrap();
+
+        let mut session = Session::default();
+        session.save("link", &link, false).unwrap();
+
+        assert_eq!(read_to_string(&target).unwrap(), "untouched");
+        assert!(link.symlink_metadata().unwrap().is_file());
+        assert!(read_to_string(&link).unwrap().contains("model:"));
+        assert_eq!(session.name(), "link");
+        std::fs::remove_dir_all(&dir).unwrap();
+    }
+
+    #[cfg(unix)]
+    #[test]
+    fn session_save_does_not_follow_a_symlink_planted_at_the_temp_path() {
+        let unique = std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap()
+            .as_nanos();
+        let dir = std::env::temp_dir().join(format!("coyote-session-save-tmp-symlink-{unique}"));
+        let sessions_dir = dir.join("sessions");
+        std::fs::create_dir_all(&sessions_dir).unwrap();
+        let target = dir.join("target.txt");
+        std::fs::write(&target, "untouched").unwrap();
+        let destination = sessions_dir.join("notes.yaml");
+        let mut tmp_name = destination.as_os_str().to_os_string();
+        tmp_name.push(format!(".{}.tmp", process::id()));
+        let tmp_path = PathBuf::from(tmp_name);
+        std::os::unix::fs::symlink(&target, &tmp_path).unwrap();
+
+        let mut session = Session::default();
+        session.save("notes", &destination, false).unwrap();
+
+        assert_eq!(read_to_string(&target).unwrap(), "untouched");
+        assert!(destination.symlink_metadata().unwrap().is_file());
+        assert!(read_to_string(&destination).unwrap().contains("model:"));
+        assert!(!tmp_path.exists(), "temp file must not be left behind");
+        std::fs::remove_dir_all(&dir).unwrap();
+    }
+
     #[test]
     fn session_todo_state_survives_yaml_round_trip() {
         let mut session = Session::default();
@@ -1578,6 +1815,85 @@ mod tests {
         assert!(session.needs_compression(100, 1));
     }
 
+    /// A session with a system message, a large user message, and a small
+    /// assistant reply, on a model with the given input limit. With
+    /// `keep_last = 1` the user message is reclaimable; with `keep_last = 2`
+    /// nothing is.
+    fn valve_session(max_input_tokens: Option<usize>) -> Session {
+        let mut session = Session::default();
+        let mut data = ModelData::new("valve-model");
+        data.max_input_tokens = max_input_tokens;
+        session.set_model(Model::from_config("provider", &[data]).remove(0));
+        session.messages.push(Message::new(
+            MessageRole::System,
+            MessageContent::Text("x".repeat(400)),
+        ));
+        session.messages.push(Message::new(
+            MessageRole::User,
+            MessageContent::Text("y".repeat(4000)),
+        ));
+        session.messages.push(Message::new(
+            MessageRole::Assistant,
+            MessageContent::Text("ok".to_string()),
+        ));
+        session.update_tokens();
+        session
+    }
+
+    #[test]
+    fn session_safety_valve_fires_from_estimate() {
+        let session = valve_session(Some(1000));
+
+        assert!(session.tokens() >= 800);
+        assert!(session.safety_valve_triggered(0.8, 1, None));
+    }
+
+    #[test]
+    fn session_safety_valve_fires_from_real_usage_over_estimate() {
+        let session = valve_session(Some(1_000_000));
+
+        assert!(!session.safety_valve_triggered(0.8, 1, None));
+        assert!(!session.safety_valve_triggered(0.8, 1, Some(700_000)));
+        assert!(session.safety_valve_triggered(0.8, 1, Some(800_000)));
+    }
+
+    #[test]
+    fn session_safety_valve_disabled_when_zero() {
+        let session = valve_session(Some(1000));
+
+        assert!(!session.safety_valve_triggered(0.0, 1, Some(1_000_000)));
+    }
+
+    #[test]
+    fn session_safety_valve_disabled_when_nan() {
+        let session = valve_session(Some(1000));
+
+        assert!(!session.safety_valve_triggered(f32::NAN, 1, Some(1_000_000)));
+    }
+
+    #[test]
+    fn session_safety_valve_respects_compressing() {
+        let mut session = valve_session(Some(1000));
+        session.set_compressing(true);
+
+        assert!(!session.safety_valve_triggered(0.8, 1, Some(1_000_000)));
+    }
+
+    #[test]
+    fn session_safety_valve_requires_reclaimable_tokens() {
+        let session = valve_session(Some(1000));
+
+        assert!(!session.safety_valve_triggered(0.8, 2, Some(1_000_000)));
+        assert!(session.safety_valve_triggered(0.8, 1, Some(1_000_000)));
+    }
+
+    #[test]
+    fn session_safety_valve_requires_model_max_input_tokens() {
+        let session = valve_session(None);
+
+        assert!(!session.safety_valve_triggered(0.8, 1, Some(1_000_000)));
+    }
+
     #[test]
     fn session_set_compressing_flag() {
         let mut session = Session::default();

src/config/skill.rs

@@ -100,7 +100,8 @@ impl Skill {
 
             let embedded_file = SkillsAsset::get(&file)
                 .ok_or_else(|| anyhow!("Failed to load embedded skill file: {}", file.as_ref()))?;
-            let content = unsafe { std::str::from_utf8_unchecked(&embedded_file.data) };
+            let content = std::str::from_utf8(&embedded_file.data)
+                .expect("bundled skill asset is not valid UTF-8");
             let file_path = paths::skills_dir().join(file.as_ref());
 
             if file_path.exists() && !force {

src/config/tool_scope.rs

@@ -918,7 +918,7 @@ mod tests {
     use super::*;
     use crate::config::mcp_tool_policy::LayerSource;
     use crate::function::ToolCall;
-    use crate::testing::{install_warn_collector, warn_messages};
+    use crate::testing::{install_log_collector, warn_snapshot};
     use std::sync::atomic::Ordering;
 
     #[test]
@@ -1083,7 +1083,7 @@ mod tests {
 
     #[tokio::test]
     async fn catalog_items_warns_when_resource_listing_fails() {
-        install_warn_collector();
+        install_log_collector();
         let fixture = FixtureServer {
             resources_capability: true,
             fail_resource_listings: true,
@@ -1093,7 +1093,7 @@ mod tests {
 
         runtime.catalog_items("fixture").await.unwrap();
 
-        let messages = warn_messages().lock().unwrap();
+        let messages = warn_snapshot();
         assert!(
             messages
                 .iter()
@@ -1547,7 +1547,7 @@ mod tests {
 
     #[tokio::test]
     async fn prompt_catalog_degrades_when_one_server_fails() {
-        install_warn_collector();
+        install_log_collector();
         let healthy = FixtureServer {
             prompts_capability: true,
             ..Default::default()
@@ -1564,7 +1564,7 @@ mod tests {
 
         assert_eq!(items.len(), 1);
         assert_eq!(items[0].server, "fixture");
-        let messages = warn_messages().lock().unwrap();
+        let messages = warn_snapshot();
         assert!(
             messages
                 .iter()
@@ -1794,7 +1794,7 @@ mod tests {
 
     #[tokio::test]
     async fn catalog_items_warns_on_dead_context_patterns() {
-        install_warn_collector();
+        install_log_collector();
         let (mut runtime, _server) = fixture_runtime(FixtureServer::default()).await;
         let mut filter = single_layer_filter(LayerSource::Global, &["*"]);
         filter.push_layer(LayerSource::Session, &["zzz_*".to_string()]);
@@ -1802,7 +1802,7 @@ mod tests {
 
         runtime.catalog_items("fixture").await.unwrap();
 
-        let messages = warn_messages().lock().unwrap();
+        let messages = warn_snapshot();
         assert!(
             messages.iter().any(|msg| msg.contains("'zzz_*'")
                 && msg.contains("session (.set)")

src/function/agents.rs

@@ -4,7 +4,7 @@ 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, paths,
+    list_agents_with_descriptions, load_agent_variables,
 };
 use crate::hooks::{self, HookEvent, ResolvedHook};
 use crate::supervisor::mailbox::{Envelope, EnvelopePayload, Inbox, PeerRegistry, graph_agent_id};
@@ -15,7 +15,8 @@ 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::{SecondsFormat, Utc};
+use chrono::Utc;
+use hooks::McpServerHooks;
 use indexmap::IndexMap;
 use log::{debug, warn};
 use parking_lot::RwLock;
@@ -961,10 +962,11 @@ async fn populate_agent_mcp_runtime(ctx: &mut RequestContext, server_ids: &[Stri
         })
         .unwrap_or_default();
 
+    let mcp_hooks = McpServerHooks::resolve(ctx);
     for (id, spec) in server_specs {
         let handle = app
             .mcp_factory
-            .acquire(&id, &spec, app.mcp_log_path.as_deref())
+            .acquire(&id, &spec, app.mcp_log_path.as_deref(), &mcp_hooks)
             .await?;
         ctx.tool_scope.mcp_runtime.insert(id, handle);
     }
@@ -997,44 +999,15 @@ 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.
+/// Pre-resolved `agent.completed`/`agent.interrupted`/`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>,
+    interrupted: Vec<ResolvedHook>,
     session_name: Option<String>,
     agent_id: String,
     agent_name: String,
@@ -1045,6 +1018,7 @@ impl SpawnResultHooks {
         Self {
             completed: child_ctx.resolved_hooks(HookEvent::AgentCompleted),
             failed: child_ctx.resolved_hooks(HookEvent::AgentFailed),
+            interrupted: child_ctx.resolved_hooks(HookEvent::AgentInterrupted),
             session_name: child_ctx
                 .session
                 .as_ref()
@@ -1054,14 +1028,16 @@ impl SpawnResultHooks {
         }
     }
 
-    /// Fires `agent.completed`, or `agent.failed` when `error` is given.
-    fn fire(self, error: Option<&str>) {
+    fn fire(self, error: Option<&str>, child_abort: &AbortSignal) {
         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(_) if child_abort.aborted_ctrlc() => {
+                (HookEvent::AgentInterrupted, self.interrupted)
+            }
             Some(error) => {
                 extras.push(("COYOTE_AGENT_ERROR", error.to_string()));
                 (HookEvent::AgentFailed, self.failed)
@@ -1070,7 +1046,7 @@ impl SpawnResultHooks {
         hooks::fire_resolved(
             event,
             resolved,
-            hook_base_envs(event, self.session_name.as_deref(), Some(&self.agent_name)),
+            hooks::base_envs_parts(event, self.session_name.as_deref(), Some(&self.agent_name)),
             &extras,
             None,
         );
@@ -1246,6 +1222,7 @@ async fn handle_spawn(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
     let spawn_agent_id = agent_id.clone();
     let spawn_agent_name = agent_name.clone();
     let spawn_abort = child_abort.clone();
+    let hook_abort = child_abort.clone();
     let spawn_notifications = Arc::clone(&ctx.notification_queue);
     let child_supervisor = child_ctx.supervisor.clone();
 
@@ -1268,8 +1245,8 @@ 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)),
+            AgentExitStatus::Completed => result_hooks.fire(None, &hook_abort),
+            AgentExitStatus::Failed(e) => result_hooks.fire(Some(e), &hook_abort),
         }
         spawn_notifications.push(agent_notification(
             &agent_result.id,
@@ -1801,6 +1778,18 @@ fn handle_reply_escalation(ctx: &mut RequestContext, args: &Value) -> Result<Val
             let from_agent = request.from_agent_name.clone();
             let question = request.question.clone();
             let _ = request.reply_tx.send(reply.to_string());
+            hooks::fire(
+                HookEvent::EscalationAnswered,
+                ctx,
+                &[
+                    ("COYOTE_ESCALATION_ID", escalation_id.to_string()),
+                    ("COYOTE_ESCALATION_FROM_AGENT_ID", request.from_agent_id),
+                    ("COYOTE_ESCALATION_FROM_AGENT_NAME", from_agent.clone()),
+                    ("COYOTE_ESCALATION_QUESTION", question.clone()),
+                    ("COYOTE_ESCALATION_REPLY", reply.to_string()),
+                ],
+                None,
+            );
             Ok(json!({
                 "status": "ok",
                 "message": format!("Reply sent to agent '{from_agent}' for escalation '{escalation_id}'"),
@@ -2281,6 +2270,9 @@ mod tests {
                  \x20 agent.completed:\n\
                  \x20   - name: {marker}_completed\n\
                  \x20     command: \"true\"\n\
+                 \x20 agent.interrupted:\n\
+                 \x20   - name: {marker}_interrupted\n\
+                 \x20     command: \"true\"\n\
                  \x20 agent.failed:\n\
                  \x20   - name: {marker}_failed\n\
                  \x20     command: \"true\"\n\
@@ -2377,8 +2369,56 @@ mod tests {
     }
 
     #[test]
-    fn hook_base_envs_carries_optional_names_only_when_present() {
-        let envs = hook_base_envs(HookEvent::AgentCompleted, None, None);
+    #[serial]
+    fn cancelled_spawned_agent_fires_interrupted_not_failed() {
+        let _guard = TestConfigDirGuard::new();
+        let _sink = hooks::test_sink::install();
+        let agent_name = unique_agent_name("test_hook_spawn_cancel");
+        write_graph_agent_with_hooks(&agent_name, "t049_spawn_cancel", true);
+
+        let id = 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");
+            // The `agent__cancel` signal, fired before the spawn task runs:
+            // on this current-thread runtime the task only progresses once
+            // awaited, so its failure arm observes the ctrl-c deterministically.
+            handle.abort_signal.set_ctrlc();
+            handle
+                .join_handle
+                .await
+                .expect("spawn task must not panic")
+                .expect("spawn task must return an AgentResult");
+            id
+        });
+
+        let interrupted = hook_captures_named("t049_spawn_cancel_interrupted");
+        assert_eq!(interrupted.len(), 1, "{interrupted:?}");
+        assert_eq!(interrupted[0].envs["COYOTE_EVENT"], "agent.interrupted");
+        assert_eq!(interrupted[0].envs["COYOTE_AGENT_ID"], id);
+        assert_eq!(interrupted[0].envs["COYOTE_AGENT_NAME"], agent_name);
+        assert!(
+            !interrupted[0].envs.contains_key("COYOTE_AGENT_ERROR"),
+            "an interruption is not a failure and carries no error env"
+        );
+
+        assert!(hook_captures_named("t049_spawn_cancel_failed").is_empty());
+        assert!(hook_captures_named("t049_spawn_cancel_completed").is_empty());
+    }
+
+    #[test]
+    fn agent_event_base_envs_carry_optional_names_only_when_present() {
+        let envs = hooks::base_envs_parts(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"));
@@ -2390,7 +2430,7 @@ mod tests {
                 .any(|(key, value)| key == "COYOTE_EVENT" && value == "agent.completed")
         );
 
-        let envs = hook_base_envs(HookEvent::AgentFailed, Some("sess"), Some("bot"));
+        let envs = hooks::base_envs_parts(HookEvent::AgentFailed, Some("sess"), Some("bot"));
         assert!(
             envs.iter()
                 .any(|(key, value)| key == "COYOTE_SESSION_ID" && value == "sess")
@@ -3354,6 +3394,79 @@ mod tests {
         assert!(result.is_err());
     }
 
+    /// `escalation.answered` belongs to the successful take -> reply arm
+    /// alone: exactly once per escalation, and never from the failure arms
+    /// (unknown id, already-taken id).
+    #[test]
+    #[serial]
+    fn reply_escalation_fires_answered_once_and_never_on_failure_arms() {
+        let _sink = hooks::test_sink::install();
+        let marker = "t049_answered_once";
+        let mut hooks_map = hooks::HooksMap::default();
+        hooks_map.insert(
+            "escalation.answered".to_string(),
+            vec![hooks::HookDef {
+                name: marker.to_string(),
+                command: "true".to_string(),
+            }],
+        );
+        let mut app = AppState::test_default();
+        app.config = Arc::new(AppConfig {
+            hooks: hooks_map,
+            ..Default::default()
+        });
+        let mut ctx = RequestContext::new(Arc::new(app), WorkingMode::Cmd);
+        let queue = Arc::new(EscalationQueue::new());
+        let (tx, rx) = tokio::sync::oneshot::channel();
+        queue.submit(EscalationRequest {
+            id: "esc_once".into(),
+            from_agent_id: "a1".into(),
+            from_agent_name: "explore".into(),
+            question: "[input] What do?".into(),
+            options: None,
+            reply_tx: tx,
+        });
+        ctx.escalation_queue = Some(queue);
+
+        // Unknown id: an error result, and no event.
+        let miss = handle_reply_escalation(
+            &mut ctx,
+            &json!({"escalation_id": "missing", "reply": "nope"}),
+        )
+        .unwrap();
+        assert_eq!(miss["status"], "error");
+        assert!(
+            hook_captures_named(marker).is_empty(),
+            "a failed reply must not fire escalation.answered"
+        );
+
+        // The successful take -> reply arm fires it exactly once.
+        let ok = handle_reply_escalation(
+            &mut ctx,
+            &json!({"escalation_id": "esc_once", "reply": "do X"}),
+        )
+        .unwrap();
+        assert_eq!(ok["status"], "ok");
+        assert_eq!(rx.blocking_recv().unwrap(), "do X");
+        let answered = hook_captures_named(marker);
+        assert_eq!(answered.len(), 1, "{answered:?}");
+        assert_eq!(answered[0].envs["COYOTE_ESCALATION_ID"], "esc_once");
+        assert_eq!(answered[0].envs["COYOTE_ESCALATION_REPLY"], "do X");
+
+        // Replying again to the same id hits the already-taken arm: still one.
+        let again = handle_reply_escalation(
+            &mut ctx,
+            &json!({"escalation_id": "esc_once", "reply": "again"}),
+        )
+        .unwrap();
+        assert_eq!(again["status"], "error");
+        assert_eq!(
+            hook_captures_named(marker).len(),
+            1,
+            "a second reply must not re-fire escalation.answered"
+        );
+    }
+
     #[test]
     fn handle_task_create_simple() {
         let mut ctx = ctx_with_supervisor(4, 3);

src/function/jobs.rs

@@ -111,6 +111,18 @@ impl JobHookSnapshot {
     }
 }
 
+fn fire_job_started(ctx: &RequestContext, job_id: &str, tool: &str) {
+    hooks::fire(
+        HookEvent::JobStarted,
+        ctx,
+        &[
+            ("COYOTE_JOB_ID", job_id.to_string()),
+            ("COYOTE_TOOL_NAME", tool.to_string()),
+        ],
+        None,
+    );
+}
+
 pub struct RingBuf {
     buf: Vec<u8>,
     capacity: usize,
@@ -529,15 +541,7 @@ async fn handle_start(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
         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,
-        );
+        fire_job_started(ctx, &job_id, &tool);
         tokio::spawn(async move {
             let result = run_mcp_job(job_ctx, server, inner_tool, inner_args).await;
             let success = result.is_ok();
@@ -559,15 +563,7 @@ async fn handle_start(ctx: &mut RequestContext, args: &Value) -> Result<Value> {
         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,
-        );
+        fire_job_started(ctx, &job_id, &tool);
         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));

src/function/mod.rs

@@ -2694,7 +2694,7 @@ impl ToolCallTracker {
     }
 }
 
-fn format_call_log(cmd_name: &str, cmd_args: &[String], json_data: &serde_json::Value) -> String {
+fn format_call_log(cmd_name: &str, cmd_args: &[String], json_data: &Value) -> String {
     if *NO_COLOR {
         return format!("Call {cmd_name} {}", cmd_args.join(" "));
     }
@@ -2713,8 +2713,8 @@ fn format_call_log(cmd_name: &str, cmd_args: &[String], json_data: &serde_json::
     )
 }
 
-fn format_json_colored_keys(value: &serde_json::Value) -> String {
-    let serde_json::Value::Object(map) = value else {
+fn format_json_colored_keys(value: &Value) -> String {
+    let Value::Object(map) = value else {
         return dimmed_text(&value.to_string());
     };
     if map.is_empty() {
@@ -3486,16 +3486,15 @@ mod tests {
 
     #[test]
     fn bundled_bash_tools_generate_declarations() {
-        let tools_dir =
-            std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("assets/functions/tools");
+        let tools_dir = Path::new(env!("CARGO_MANIFEST_DIR")).join("assets/functions/tools");
         let mut checked = Vec::new();
-        for entry in std::fs::read_dir(&tools_dir).unwrap() {
+        for entry in fs::read_dir(&tools_dir).unwrap() {
             let path = entry.unwrap().path();
             if path.extension().and_then(OsStr::to_str) != Some("sh") {
                 continue;
             }
             let name = path.file_stem().unwrap().to_string_lossy().to_string();
-            let src = std::fs::read_to_string(&path).unwrap();
+            let src = fs::read_to_string(&path).unwrap();
             let (_, declarations) = bash::build_bash_tool(&src, &name)
                 .unwrap_or_else(|e| panic!("bundled tool '{name}' failed to parse: {e}"));
             assert!(
@@ -4673,7 +4672,7 @@ mod tests {
         .unwrap()
         .expect("nonzero exit must return an error payload");
 
-        let json: serde_json::Value = serde_json::from_str(&result).unwrap();
+        let json: Value = serde_json::from_str(&result).unwrap();
         assert!(
             json["tool_call_error"]
                 .as_str()
@@ -4702,7 +4701,7 @@ mod tests {
         .unwrap()
         .expect("nonzero exit must return an error payload");
 
-        let json: serde_json::Value = serde_json::from_str(&result).unwrap();
+        let json: Value = serde_json::from_str(&result).unwrap();
         assert!(
             json["tool_call_error"]
                 .as_str()
@@ -4741,7 +4740,7 @@ mod tests {
         let elapsed = started.elapsed();
 
         assert!(elapsed < Duration::from_secs(1), "took {elapsed:?}");
-        let json: serde_json::Value = serde_json::from_str(&result).unwrap();
+        let json: Value = serde_json::from_str(&result).unwrap();
         assert_eq!(json["tool_call_error"], "Tool call 'bash' aborted");
     }
 
@@ -4823,6 +4822,24 @@ mod tests {
     fn built_shims_resolve_paths_at_runtime_after_relocation() {
         use std::os::unix::fs::PermissionsExt;
 
+        // A shim written moments ago can still be open for writing somewhere
+        // in the process (schedule-dependent), making exec fail with
+        // ETXTBSY; retry briefly instead of flaking.
+        fn output_with_etxtbsy_retry(command: &mut Command) -> io::Result<process::Output> {
+            let mut attempts = 0;
+            loop {
+                match command.output() {
+                    Err(err)
+                        if err.kind() == io::ErrorKind::ExecutableFileBusy && attempts < 10 =>
+                    {
+                        attempts += 1;
+                        thread::sleep(Duration::from_millis(50));
+                    }
+                    ret => return ret,
+                }
+            }
+        }
+
         let root = temp_file("-shim-relocate-", "");
         let home_a = root.join("home-a");
         let config_a = home_a.join("coyote");
@@ -4886,14 +4903,14 @@ mod tests {
             return;
         }
 
-        let output = process::Command::new(&moved_shim)
+        let mut command = Command::new(&moved_shim);
+        command
             .arg("{}")
             .env_remove(&config_env)
             .env_remove(&functions_env)
             .env_remove("LLM_OUTPUT")
-            .env_remove("LLM_TOOL_DATA_FILE")
-            .output()
-            .unwrap();
+            .env_remove("LLM_TOOL_DATA_FILE");
+        let output = output_with_etxtbsy_retry(&mut command).unwrap();
         let stdout = String::from_utf8_lossy(&output.stdout);
         assert!(
             output.status.success(),

src/function/user_interaction.rs

@@ -1,5 +1,6 @@
 use super::{FunctionDeclaration, JsonSchema};
 use crate::config::RequestContext;
+use crate::hooks::{self, HookEvent};
 use crate::supervisor::escalation::{EscalationRequest, new_escalation_id};
 use crate::utils::{ACP_SERVER, HEADLESS, queue_acp_permission};
 
@@ -278,22 +279,37 @@ async fn handle_escalated(ctx: &RequestContext, action: &str, args: &Value) -> R
     let escalation_id = new_escalation_id();
     let (tx, rx) = oneshot::channel();
 
+    let question = format!("[{action}] {question}");
     let request = EscalationRequest {
         id: escalation_id.clone(),
-        from_agent_id,
+        from_agent_id: from_agent_id.clone(),
         from_agent_name: from_agent_name.clone(),
-        question: format!("[{action}] {question}"),
+        question: question.clone(),
         options,
         reply_tx: tx,
     };
 
     root_queue.submit(request);
 
+    hooks::fire(
+        HookEvent::EscalationRaised,
+        ctx,
+        &[
+            ("COYOTE_ESCALATION_ID", escalation_id),
+            ("COYOTE_ESCALATION_FROM_AGENT_ID", from_agent_id),
+            ("COYOTE_ESCALATION_FROM_AGENT_NAME", from_agent_name),
+            ("COYOTE_ESCALATION_QUESTION", question),
+        ],
+        None,
+    );
+
     await_escalation_reply(rx, timeout_secs).await
 }
 
 /// Waits for the parent's reply. `timeout_secs == 0` waits indefinitely; a
 /// dropped sender (the parent cancelled the request) resolves either way.
+/// Both fallback arms resolve without touching the escalation queue, so
+/// neither fires an escalation event: the request was never answered.
 async fn await_escalation_reply(rx: oneshot::Receiver<String>, timeout_secs: u64) -> Result<Value> {
     let reply = if timeout_secs == 0 {
         rx.await
@@ -346,8 +362,14 @@ fn parse_options(args: &Value) -> Result<Vec<String>> {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::config::{AppConfig, AppState, WorkingMode};
+    use crate::function::agents::handle_agent_tool;
+    use crate::hooks::{HookDef, HooksMap, test_sink};
+    use crate::supervisor::escalation::EscalationQueue;
+    use serial_test::serial;
     use std::fs;
     use std::path::{Path, PathBuf};
+    use std::sync::Arc;
 
     #[test]
     fn headless_select_returns_structured_json() {
@@ -374,6 +396,160 @@ mod tests {
         assert_eq!(DEFAULT_ESCALATION_TIMEOUT_SECS, 0);
     }
 
+    fn ctx_with_escalation_hooks(marker: &str) -> RequestContext {
+        let mut hooks = HooksMap::default();
+        for event in ["escalation.raised", "escalation.answered"] {
+            hooks.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,
+            ..Default::default()
+        });
+        RequestContext::new(Arc::new(app), WorkingMode::Cmd)
+    }
+
+    fn marker_captures(marker: &str, event: &str) -> Vec<test_sink::Capture> {
+        test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name == format!("{marker}-{event}"))
+            .collect()
+    }
+
+    /// `escalation.raised` (child seam) and `escalation.answered` (parent
+    /// seam) must describe the same origin agent for one escalation id: the
+    /// answered envs come from the taken queue request, never from the
+    /// replying context.
+    #[tokio::test]
+    #[serial]
+    async fn escalation_raised_and_answered_agree_on_origin_envs() {
+        let _sink = test_sink::install();
+        let marker = "esc-parity-k4w";
+
+        let queue = Arc::new(EscalationQueue::new());
+        let mut child_ctx = ctx_with_escalation_hooks(marker);
+        child_ctx.escalation_queue = Some(Arc::clone(&queue));
+        child_ctx.self_agent_id = Some("esc-child-1".to_string());
+        let mut parent_ctx = ctx_with_escalation_hooks(marker);
+        parent_ctx.escalation_queue = Some(Arc::clone(&queue));
+
+        let raise_args = json!({ "question": "which db?" });
+        let raise = handle_escalated(&child_ctx, "input", &raise_args);
+        let reply = async {
+            // Bounded poll: on the current-thread runtime the raise future
+            // submits before its first await, so this resolves immediately.
+            let mut escalation_id = None;
+            for _ in 0..1000 {
+                if let Some(entry) = queue.pending_summary().first() {
+                    escalation_id = entry["escalation_id"].as_str().map(str::to_string);
+                    break;
+                }
+                tokio::task::yield_now().await;
+            }
+            let escalation_id = escalation_id.expect("escalation must reach the queue");
+            handle_agent_tool(
+                &mut parent_ctx,
+                "agent__reply_escalation",
+                &json!({ "escalation_id": escalation_id, "reply": "postgres" }),
+            )
+            .await
+            .unwrap()
+        };
+        let (raised_result, replied) = tokio::join!(raise, reply);
+        assert_eq!(raised_result.unwrap()["answer"], "postgres");
+        assert_eq!(replied["status"], "ok");
+
+        let raised = marker_captures(marker, "escalation.raised");
+        let answered = marker_captures(marker, "escalation.answered");
+        assert_eq!(raised.len(), 1, "{raised:?}");
+        assert_eq!(answered.len(), 1, "{answered:?}");
+        for key in [
+            "COYOTE_ESCALATION_ID",
+            "COYOTE_ESCALATION_FROM_AGENT_ID",
+            "COYOTE_ESCALATION_FROM_AGENT_NAME",
+            "COYOTE_ESCALATION_QUESTION",
+        ] {
+            assert!(raised[0].envs.contains_key(key), "{key} missing on raised");
+            assert_eq!(raised[0].envs.get(key), answered[0].envs.get(key), "{key}");
+        }
+        assert_eq!(
+            raised[0]
+                .envs
+                .get("COYOTE_ESCALATION_FROM_AGENT_ID")
+                .map(String::as_str),
+            Some("esc-child-1")
+        );
+        assert_eq!(
+            raised[0]
+                .envs
+                .get("COYOTE_ESCALATION_QUESTION")
+                .map(String::as_str),
+            Some("[input] which db?")
+        );
+        assert_eq!(
+            answered[0]
+                .envs
+                .get("COYOTE_ESCALATION_REPLY")
+                .map(String::as_str),
+            Some("postgres")
+        );
+        assert!(!raised[0].envs.contains_key("COYOTE_ESCALATION_REPLY"));
+    }
+
+    /// `COYOTE_ESCALATION_QUESTION` rides through the standard env
+    /// truncation: a huge question is trimmed to 2048 bytes on the raised
+    /// seam, never passed through whole.
+    #[tokio::test]
+    #[serial]
+    async fn escalation_question_env_is_truncated_to_2048_bytes() {
+        let _sink = test_sink::install();
+        let marker = "esc-trunc-p9j";
+
+        let queue = Arc::new(EscalationQueue::new());
+        let mut child_ctx = ctx_with_escalation_hooks(marker);
+        child_ctx.escalation_queue = Some(Arc::clone(&queue));
+        child_ctx.self_agent_id = Some("esc-child-trunc".to_string());
+
+        let raise_args = json!({ "question": "q".repeat(3000) });
+        let raise = handle_escalated(&child_ctx, "input", &raise_args);
+        let reply = async {
+            // Bounded poll: on the current-thread runtime the raise future
+            // submits before its first await, so this resolves immediately.
+            let mut request = None;
+            for _ in 0..1000 {
+                if let Some(entry) = queue.pending_summary().first() {
+                    let id = entry["escalation_id"].as_str().unwrap().to_string();
+                    request = queue.take(&id);
+                    break;
+                }
+                tokio::task::yield_now().await;
+            }
+            let request = request.expect("escalation must reach the queue");
+            let _ = request.reply_tx.send("ok".to_string());
+        };
+        let (raised_result, ()) = tokio::join!(raise, reply);
+        assert_eq!(raised_result.unwrap()["answer"], "ok");
+
+        let raised = marker_captures(marker, "escalation.raised");
+        assert_eq!(raised.len(), 1, "{raised:?}");
+        let question = raised[0]
+            .envs
+            .get("COYOTE_ESCALATION_QUESTION")
+            .expect("QUESTION env must be present on escalation.raised");
+        assert_eq!(
+            question.len(),
+            2048,
+            "QUESTION env must be 2048-byte truncated"
+        );
+        assert!(question.starts_with("[input] qqq"));
+    }
+
     #[tokio::test(start_paused = true)]
     async fn zero_timeout_waits_indefinitely_for_the_reply() {
         let (tx, rx) = oneshot::channel();

src/graph/agent.rs

@@ -50,6 +50,21 @@ impl AgentNodeExecutor {
         )
         .await;
         if let Err(e) = &result {
+            if parent_ctx
+                .session_abort
+                .as_ref()
+                .is_some_and(|signal| signal.aborted_ctrlc())
+            {
+                hooks::fire(
+                    HookEvent::AgentInterrupted,
+                    parent_ctx,
+                    &[
+                        ("COYOTE_AGENT_ID", agent_hook_id),
+                        ("COYOTE_AGENT_NAME", node.agent.clone()),
+                    ],
+                    None,
+                );
+            } else {
                 hooks::fire(
                     HookEvent::AgentFailed,
                     parent_ctx,
@@ -61,6 +76,7 @@ impl AgentNodeExecutor {
                     None,
                 );
             }
+        }
         outcome_from(node_id, node, state_manager, result)
     }
 }
@@ -338,10 +354,12 @@ fn apply_state_updates(node: &AgentNode, state_manager: &mut StateManager, outpu
 mod tests {
     use super::super::types::AgentNode;
     use super::*;
-    use crate::config::{AppState, WorkingMode, default_max_agent_depth};
+    use crate::config::{AppConfig, AppState, WorkingMode, default_max_agent_depth};
+    use crate::hooks::{HookDef, HooksMap, test_sink};
     use crate::supervisor::mailbox::{Inbox, PeerRegistry, graph_agent_id};
-    use crate::testing::{install_warn_collector, warn_messages};
+    use crate::testing::{install_log_collector, warn_snapshot};
     use serde_json::json;
+    use serial_test::serial;
     use std::collections::HashMap;
     use std::sync::Arc;
 
@@ -416,6 +434,95 @@ mod tests {
         RequestContext::new(Arc::new(AppState::test_default()), WorkingMode::Cmd)
     }
 
+    fn ctx_with_agent_hooks(marker: &str) -> RequestContext {
+        let mut hooks = HooksMap::default();
+        for event in ["agent.interrupted", "agent.failed"] {
+            hooks.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,
+            ..Default::default()
+        });
+        RequestContext::new(Arc::new(app), WorkingMode::Cmd)
+    }
+
+    /// A fired session signal (the user's interrupt) reclassifies a failed
+    /// agent node: `agent.interrupted` fires instead of `agent.failed`.
+    #[tokio::test]
+    #[serial]
+    async fn execute_failure_with_fired_session_abort_fires_agent_interrupted() {
+        let _sink = test_sink::install();
+        let marker = "graph-agent-int-z2f";
+        let mut ctx = ctx_with_agent_hooks(marker);
+        // Past max depth the node fails before touching agent config on disk.
+        ctx.current_depth = default_max_agent_depth();
+        let session = create_abort_signal();
+        session.set_ctrlc();
+        ctx.session_abort = Some(session);
+        let node = node_with("hi", None);
+        let mut state = manager_with(&[]);
+
+        AgentNodeExecutor::execute("test_node", &node, &mut state, &mut ctx, false)
+            .await
+            .expect_err("agent past max depth should fail");
+
+        let captures: Vec<_> = test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name.starts_with(marker))
+            .collect();
+        assert_eq!(captures.len(), 1, "{captures:?}");
+        assert_eq!(captures[0].hook_name, format!("{marker}-agent.interrupted"));
+        assert_eq!(
+            captures[0]
+                .envs
+                .get("COYOTE_AGENT_NAME")
+                .map(String::as_str),
+            Some("test_agent")
+        );
+        assert!(
+            !captures[0].envs.contains_key("COYOTE_AGENT_ERROR"),
+            "an interruption is not a failure and carries no error env"
+        );
+    }
+
+    /// The inverse gate: a failure whose session signal never fired stays
+    /// `agent.failed` with its error env — the presence of a signal alone
+    /// must not reclassify a real failure as an interruption.
+    #[tokio::test]
+    #[serial]
+    async fn execute_failure_without_fired_session_abort_fires_agent_failed() {
+        let _sink = test_sink::install();
+        let marker = "graph-agent-fail-inv-x7q";
+        let mut ctx = ctx_with_agent_hooks(marker);
+        // Past max depth the node fails before touching agent config on disk.
+        ctx.current_depth = default_max_agent_depth();
+        ctx.session_abort = Some(create_abort_signal());
+        let node = node_with("hi", None);
+        let mut state = manager_with(&[]);
+
+        AgentNodeExecutor::execute("test_node", &node, &mut state, &mut ctx, false)
+            .await
+            .expect_err("agent past max depth should fail");
+
+        let captures: Vec<_> = test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name.starts_with(marker))
+            .collect();
+        assert_eq!(captures.len(), 1, "{captures:?}");
+        assert_eq!(captures[0].hook_name, format!("{marker}-agent.failed"));
+        assert!(
+            captures[0].envs.contains_key("COYOTE_AGENT_ERROR"),
+            "a real failure keeps its error env"
+        );
+    }
+
     fn retryable_node(max_attempts: u32) -> AgentNode {
         let mut node = node_with("hi", None);
         node.max_attempts = max_attempts;
@@ -676,7 +783,7 @@ mod tests {
 
     #[tokio::test]
     async fn retry_transient_warns_once_per_retried_attempt_with_the_context_chain() {
-        install_warn_collector();
+        install_log_collector();
         let mut ctx = plain_ctx();
         let node = retryable_node(3);
         let mut attempts = 0u32;
@@ -700,12 +807,9 @@ mod tests {
         .expect_err("all attempts fail");
 
         assert_eq!(attempts, 3);
-        let warns: Vec<String> = warn_messages()
-            .lock()
-            .unwrap()
-            .iter()
+        let warns: Vec<String> = warn_snapshot()
+            .into_iter()
             .filter(|m| m.contains("'warn_capture'"))
-            .cloned()
             .collect();
         assert_eq!(
             warns.len(),
@@ -861,7 +965,7 @@ mod tests {
 
     #[test]
     fn outcome_from_fallback_warn_names_the_node_and_the_fallback_target() {
-        install_warn_collector();
+        install_log_collector();
         let mut node = node_with("hi", None);
         node.fallback = Some("recover".into());
         let mut state = manager_with(&[]);
@@ -875,12 +979,9 @@ mod tests {
         .unwrap();
 
         assert_eq!(outcome, AgentExecutionOutcome::FellBack("recover".into()));
-        let warns: Vec<String> = warn_messages()
-            .lock()
-            .unwrap()
-            .iter()
+        let warns: Vec<String> = warn_snapshot()
+            .into_iter()
             .filter(|m| m.contains("'fallback_warn_capture'"))
-            .cloned()
             .collect();
         assert_eq!(warns.len(), 1, "exactly one fallback warn: {warns:?}");
         assert!(

src/graph/executor.rs

@@ -11,7 +11,6 @@ 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};
@@ -550,7 +549,7 @@ impl NodeHookEmitter {
         hooks::fire_resolved(
             event,
             resolved.to_vec(),
-            hook_base_envs(
+            hooks::base_envs_parts(
                 event,
                 self.session_name.as_deref(),
                 self.agent_name.as_deref(),
@@ -1133,14 +1132,12 @@ mod integration_tests {
     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};
+    use crate::utils::{create_abort_signal, temp_file};
     use parking_lot::Mutex;
     use serial_test::serial;
-    use std::env;
     use std::fs;
     #[cfg(unix)]
     use std::mem;
-    use std::time::{SystemTime, UNIX_EPOCH};
 
     fn cmd_available(name: &str) -> bool {
         which::which(name).is_ok()
@@ -1268,7 +1265,7 @@ nodes:
             eprintln!("skipping: bash or python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-executor-tests");
         materialize_probe_agent(0.0);
         let ws = TestWorkspace::new();
         ws.write_script("dispatcher.sh", "#!/bin/bash\necho '{}'\n");
@@ -1619,7 +1616,7 @@ nodes:
     /// 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();
+        crate::testing::install_log_collector();
         let _sink = hooks::test_sink::install();
         let mut ctx = make_ctx();
 
@@ -1660,10 +1657,7 @@ nodes:
         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();
+        let debugs = crate::testing::debug_snapshot();
         assert!(
             debugs
                 .iter()
@@ -1685,7 +1679,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-executor-tests");
         materialize_probe_agent(0.0);
         let ws = TestWorkspace::new();
 
@@ -2368,47 +2362,7 @@ nodes:
         assert_eq!(events[0].event, "job_completed");
     }
 
-    struct TestConfigDirGuard {
-        key: String,
-        previous: Option<std::ffi::OsString>,
-        path: PathBuf,
-    }
-
-    impl TestConfigDirGuard {
-        fn new() -> Self {
-            let key = get_env_name("config_dir");
-            let previous = env::var_os(&key);
-            let unique = SystemTime::now()
-                .duration_since(UNIX_EPOCH)
-                .unwrap()
-                .as_nanos();
-            let path = env::temp_dir().join(format!("coyote-graph-executor-tests-{unique}"));
-            fs::create_dir_all(&path).unwrap();
-            unsafe {
-                env::set_var(&key, &path);
-            }
-            Self {
-                key,
-                previous,
-                path,
-            }
-        }
-    }
-
-    impl Drop for TestConfigDirGuard {
-        fn drop(&mut self) {
-            if let Some(previous) = &self.previous {
-                unsafe {
-                    env::set_var(&self.key, previous);
-                }
-            } else {
-                unsafe {
-                    env::remove_var(&self.key);
-                }
-            }
-            let _ = fs::remove_dir_all(&self.path);
-        }
-    }
+    use crate::testing::TestConfigDirGuard;
 
     const PROBE_AGENT: &str = "timeout-probe";
 
@@ -2658,7 +2612,7 @@ nodes:
             eprintln!("skipping: bash or python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-executor-tests");
         materialize_probe_agent(5.0);
         let ws = TestWorkspace::new();
         // The abort must land after the worker tasks exist (their retirement

src/graph/map.rs

@@ -746,14 +746,12 @@ mod chain_tests {
     use super::*;
     use crate::config::paths;
     use crate::config::{AppState, Role, WorkingMode};
-    use crate::utils::{AbortSignal, create_abort_signal, get_env_name, temp_file};
+    use crate::utils::{AbortSignal, create_abort_signal, temp_file};
     use indexmap::IndexMap;
     use serde_json::json;
     use serial_test::serial;
-    use std::env;
     use std::fs;
     use std::path::PathBuf;
-    use std::time::{SystemTime, UNIX_EPOCH};
 
     fn cmd_available(name: &str) -> bool {
         which::which(name).is_ok()
@@ -1739,47 +1737,7 @@ nodes:
         }
     }
 
-    struct TestConfigDirGuard {
-        key: String,
-        previous: Option<std::ffi::OsString>,
-        path: PathBuf,
-    }
-
-    impl TestConfigDirGuard {
-        fn new() -> Self {
-            let key = get_env_name("config_dir");
-            let previous = env::var_os(&key);
-            let unique = SystemTime::now()
-                .duration_since(UNIX_EPOCH)
-                .unwrap()
-                .as_nanos();
-            let path = env::temp_dir().join(format!("coyote-graph-map-tests-{unique}"));
-            fs::create_dir_all(&path).unwrap();
-            unsafe {
-                env::set_var(&key, &path);
-            }
-            Self {
-                key,
-                previous,
-                path,
-            }
-        }
-    }
-
-    impl Drop for TestConfigDirGuard {
-        fn drop(&mut self) {
-            if let Some(previous) = &self.previous {
-                unsafe {
-                    env::set_var(&self.key, previous);
-                }
-            } else {
-                unsafe {
-                    env::remove_var(&self.key);
-                }
-            }
-            let _ = fs::remove_dir_all(&self.path);
-        }
-    }
+    use crate::testing::TestConfigDirGuard;
 
     const PROBE_AGENT: &str = "timeout-probe";
 
@@ -2031,7 +1989,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-map-tests");
         materialize_probe_agent(0.0);
         let h = Harness::new(&flagged_probe_graph(None));
         let peers = manual_peer("worker");
@@ -2057,7 +2015,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-map-tests");
         materialize_probe_agent(0.0);
         let ws = TestWorkspace::new();
         let yaml = format!(
@@ -2107,7 +2065,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-map-tests");
         materialize_probe_agent(5.0);
         let h = Harness::new(&flagged_probe_graph(Some(1)));
         let (registry, assignments) = h.provision("worker", 2);
@@ -2144,7 +2102,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-map-tests");
         materialize_probe_agent(1.5);
         let h = Harness::new(&flagged_probe_graph(Some(0)));
         let peers = manual_peer("worker");
@@ -2167,7 +2125,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-map-tests");
         materialize_probe_agent(0.0);
         let h = Harness::new(&format!(
             r#"
@@ -2272,7 +2230,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-map-tests");
         materialize_echo_inputs_agent();
         let parent = echo_inputs_parent_graph("    inputs:\n      width: \"{{n}}\"\n");
 
@@ -2291,7 +2249,7 @@ nodes:
             eprintln!("skipping: python3 not available");
             return;
         }
-        let _guard = TestConfigDirGuard::new();
+        let _guard = TestConfigDirGuard::new("graph-map-tests");
         materialize_echo_inputs_agent();
         let parent = echo_inputs_parent_graph("");
 

src/main.rs

@@ -58,8 +58,37 @@ use std::path::PathBuf;
 use std::sync::atomic::Ordering;
 use std::{env, fs, process, sync::Arc};
 
-#[tokio::main]
-async fn main() -> Result<()> {
+const MAIN_STACK_SIZE: usize = 16 * 1024 * 1024;
+
+/// Bootstraps the async entry point on a dedicated thread with an explicit
+/// large stack instead of `#[tokio::main]`, which would poll the root
+/// future on the (small, non-configurable) OS main thread. Everything else
+/// matches the macro expansion: same multi-thread runtime flavor, same
+/// `enable_all()` driver set (so `tokio::signal::ctrl_c()` keeps working),
+/// same `block_on` of the async body, and the `Result` propagates
+/// unchanged. Worker threads get the same headroom because spawned tasks
+/// (graph nodes, subagents) embed the same class of giant state machine.
+/// The thread is named "main" and panics are re-raised on the real main
+/// thread without re-invoking the panic hook, keeping panic output and the
+/// exit code identical to the direct arrangement.
+fn main() -> Result<()> {
+    std::thread::Builder::new()
+        .name("main".into())
+        .stack_size(MAIN_STACK_SIZE)
+        .spawn(|| {
+            tokio::runtime::Builder::new_multi_thread()
+                .enable_all()
+                .thread_stack_size(MAIN_STACK_SIZE)
+                .build()
+                .expect("failed to build the tokio runtime")
+                .block_on(async_main())
+        })
+        .expect("failed to spawn the main bootstrap thread")
+        .join()
+        .unwrap_or_else(|panic| std::panic::resume_unwind(panic))
+}
+
+async fn async_main() -> Result<()> {
     load_env_file()?;
     CompleteEnv::with_factory(Cli::command).complete();
     let cli = Cli::parse();
@@ -113,6 +142,15 @@ async fn main() -> Result<()> {
         || cli.list_macros
         || cli.list_skills
         || cli.list_sessions;
+    let readout_flag = (cli.info
+        || cli.list_models
+        || cli.list_roles
+        || cli.list_agents
+        || cli.list_rags
+        || cli.list_macros
+        || cli.list_skills
+        || cli.list_sessions)
+        && !cli.sync_models;
     let vault_flags = cli.add_secret.is_some()
         || cli.get_secret.is_some()
         || cli.update_secret.is_some()
@@ -140,7 +178,18 @@ async fn main() -> Result<()> {
         return config::list_installed_bundles();
     }
 
+    let mcp_inspect =
+        cli.mcp_list && cli.mcp_get.is_none() && cli.mcp_remove.is_none() && cli.mcp_add.is_none();
+    let vault_inspect = cli.list_secrets
+        && cli.add_secret.is_none()
+        && cli.get_secret.is_none()
+        && cli.update_secret.is_none()
+        && cli.delete_secret.is_none();
+    let inspection_only =
+        (readout_flag || vault_inspect || mcp_inspect) && cli.agent.is_none() && cli.role.is_none();
+    if !inspection_only {
         install_builtins()?;
+    }
 
     if let Some(category) = cli.install_builtins {
         return config::install_assets(category);
@@ -164,7 +213,7 @@ async fn main() -> Result<()> {
     }
 
     if let Some(client_arg) = &cli.authenticate {
-        let cfg = Config::load_with_interpolation(true).await?;
+        let cfg = Config::load_with_interpolation(true, false).await?;
         let app_config = AppConfig::from_config(cfg)?;
         let (client_name, provider) =
             resolve_oauth_client(client_arg.as_deref(), &app_config.clients)?;
@@ -173,7 +222,7 @@ async fn main() -> Result<()> {
     }
 
     if let Some(server_name) = &cli.auth_mcp {
-        let cfg = Config::load_with_interpolation(true).await?;
+        let cfg = Config::load_with_interpolation(true, false).await?;
         let app_config = AppConfig::from_config(cfg)?;
         let vault = Vault::init(&app_config)?;
         let mcp_path = paths::mcp_config_file();
@@ -225,9 +274,17 @@ async fn main() -> Result<()> {
     let mcp_action =
         cli.mcp_list || cli.mcp_get.is_some() || cli.mcp_remove.is_some() || cli.mcp_add.is_some();
     if mcp_action {
-        let cfg = Config::load_with_interpolation(true).await?;
-        let app_config = AppConfig::from_config(cfg)?;
-        let vault = Vault::init(&app_config)?;
+        let cfg = Config::load_with_interpolation(true, mcp_inspect).await?;
+        let app_config = if mcp_inspect {
+            AppConfig::from_config_lenient(cfg)?
+        } else {
+            AppConfig::from_config(cfg)?
+        };
+        let vault = if mcp_inspect {
+            Vault::init_lenient(&app_config)
+        } else {
+            Vault::init(&app_config)?
+        };
 
         mcp::manage::handle(&cli, &vault)?;
 
@@ -235,16 +292,24 @@ async fn main() -> Result<()> {
     }
 
     if vault_flags {
-        let cfg = Config::load_with_interpolation(true).await?;
-        let app_config = AppConfig::from_config(cfg)?;
+        let cfg = Config::load_with_interpolation(true, vault_inspect).await?;
+        let app_config = if vault_inspect {
+            AppConfig::from_config_lenient(cfg)?
+        } else {
+            AppConfig::from_config(cfg)?
+        };
         let vault = Vault::init(&app_config)?;
         return Vault::handle_vault_flags(cli, &vault);
     }
 
     let abort_signal = create_abort_signal();
     let start_mcp_servers = cli.agent.is_none() && cli.role.is_none();
-    let cfg = Config::load_with_interpolation(info_flag).await?;
-    let mut app_config = AppConfig::from_config(cfg)?;
+    let cfg = Config::load_with_interpolation(info_flag, readout_flag).await?;
+    let mut app_config = if readout_flag {
+        AppConfig::from_config_lenient(cfg)?
+    } else {
+        AppConfig::from_config(cfg)?
+    };
     if cli.no_workspace_mcp {
         app_config.no_workspace_mcp = true;
     }
@@ -258,14 +323,17 @@ async fn main() -> Result<()> {
             log_path,
             start_mcp_servers,
             info_flag,
+            inspection_only,
             abort_signal.clone(),
         )
         .await?,
     );
     let mut ctx = RequestContext::bootstrap(app_state, working_mode, info_flag)?;
     let app_config = Arc::clone(&ctx.app.config);
+    if !inspection_only {
         ctx.bootstrap_tools(&app_config, start_mcp_servers, abort_signal.clone())
             .await?;
+    }
 
     {
         let app = &*ctx.app.config;
@@ -306,9 +374,12 @@ async fn run(
     }
 
     if cli.list_models {
-        for model in list_models(ctx.app.config.as_ref(), ModelType::Chat) {
-            println!("{}", model.id());
-        }
+        let models = list_models(ctx.app.config.as_ref(), ModelType::Chat)
+            .iter()
+            .map(|model| model.id())
+            .collect::<Vec<_>>()
+            .join("\n");
+        println!("{models}");
         return Ok(());
     }
     if cli.list_roles {
@@ -389,11 +460,12 @@ async fn run(
         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.
+        // flags below (--list-sessions, --info, --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 a run is
+        // actually committed, including the --macro arm, which executes
+        // rather than inspects.
     } else {
         let app: Arc<AppConfig> = Arc::clone(&ctx.app.config);
         if let Some(prompt) = &cli.temp_role {
@@ -526,8 +598,11 @@ async fn run(
         }
     }
     if let Some(name) = &cli.macro_name {
-        macro_execute(&mut ctx, name, text.as_deref(), abort_signal.clone()).await?;
-        return Ok(());
+        ctx.top_level_agent_started();
+        let result = macro_execute(&mut ctx, name, text.as_deref(), abort_signal.clone()).await;
+        ctx.top_level_agent_finished(result.as_ref().err(), Some(&abort_signal));
+        hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
+        return result;
     }
     if cli.execute && !is_repl {
         // Dispatch committed: open the top-level agent bracket only now,
@@ -538,7 +613,7 @@ async fn run(
             shell_execute(&mut ctx, &SHELL, input, abort_signal.clone()).await
         }
         .await;
-        ctx.top_level_agent_finished(result.as_ref().err());
+        ctx.top_level_agent_finished(result.as_ref().err(), Some(&abort_signal));
         hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
         return result;
     }
@@ -572,7 +647,7 @@ async fn run(
                 start_directive(&mut ctx, input, cli.code, abort_signal.clone()).await
             }
             .await;
-            ctx.top_level_agent_finished(result.as_ref().err());
+            ctx.top_level_agent_finished(result.as_ref().err(), Some(&abort_signal));
             hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
             result
         }
@@ -706,7 +781,7 @@ 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);
+                    ctx.top_level_agent_finished(None, None);
                     hooks::drain_pending(EXIT_HOOK_DRAIN_TIMEOUT).await;
                     process::exit(code);
                 }

src/rag/mod.rs

@@ -13,6 +13,7 @@ mod splitter;
 use self::graph::{KnowledgeGraph, extract_entities};
 use self::provider::RagProvider;
 use self::providers::{DuckDbProvider, QdrantProvider, YamlProvider};
+use crate::hooks::RagSyncHooks;
 use crate::sandbox::mcp_credentials;
 use crate::vault::{Vault, interpolate_secrets};
 
@@ -144,6 +145,7 @@ impl Rag {
         doc_paths: &[String],
         config: &RagInitConfig,
         abort_signal: AbortSignal,
+        sync_hooks: RagSyncHooks,
     ) -> Result<Self> {
         if doc_paths.is_empty() {
             bail!("Cannot build RAG knowledge base '{name}' with no documents");
@@ -154,15 +156,27 @@ impl Rag {
         let mut rag = Self::create(app, name, save_path, data).await?;
         let loaders = app.document_loaders.clone();
         let (spinner, spinner_rx) = Spinner::create("");
-        abortable_run_with_spinner_rx(
+        sync_hooks.fire_started(&rag.name, &rag.path);
+        let synced = abortable_run_with_spinner_rx(
             rag.sync_documents(doc_paths, true, false, loaders, Some(spinner)),
             spinner_rx,
             abort_signal,
         )
-        .await?;
-        if rag.save()? {
-            println!("✓ Saved RAG to '{}'.", save_path.display());
+        .await;
+        if let Err(err) = synced {
+            sync_hooks.fire_failed(&rag.name, &rag.path, &err);
+            return Err(err);
         }
+
+        match rag.save() {
+            Ok(true) => println!("✓ Saved RAG to '{}'.", save_path.display()),
+            Ok(false) => {}
+            Err(err) => {
+                sync_hooks.fire_failed(&rag.name, &rag.path, &err);
+                return Err(err);
+            }
+        }
+        sync_hooks.fire_completed(&rag.name, &rag.path, rag.file_count());
         Ok(rag)
     }
 
@@ -261,6 +275,7 @@ impl Rag {
         doc_paths: &[String],
         abort_signal: AbortSignal,
         prompt_for_driver: bool,
+        sync_hooks: RagSyncHooks,
     ) -> Result<Self> {
         if !*IS_STDOUT_TERMINAL {
             bail!("Failed to init rag in non-interactive mode");
@@ -305,15 +320,27 @@ impl Rag {
         };
         let loaders = app.document_loaders.clone();
         let (spinner, spinner_rx) = Spinner::create("");
-        abortable_run_with_spinner_rx(
+        sync_hooks.fire_started(&rag.name, &rag.path);
+        let synced = abortable_run_with_spinner_rx(
             rag.sync_documents(&paths, true, false, loaders, Some(spinner)),
             spinner_rx,
             abort_signal,
         )
-        .await?;
-        if rag.save()? {
-            println!("✓ Saved RAG to '{}'.", save_path.display());
+        .await;
+        if let Err(err) = synced {
+            sync_hooks.fire_failed(&rag.name, &rag.path, &err);
+            return Err(err);
         }
+
+        match rag.save() {
+            Ok(true) => println!("✓ Saved RAG to '{}'.", save_path.display()),
+            Ok(false) => {}
+            Err(err) => {
+                sync_hooks.fire_failed(&rag.name, &rag.path, &err);
+                return Err(err);
+            }
+        }
+        sync_hooks.fire_completed(&rag.name, &rag.path, rag.file_count());
         Ok(rag)
     }
 
@@ -636,10 +663,12 @@ impl Rag {
         force_reingest: bool,
         app: &AppConfig,
         abort_signal: AbortSignal,
+        sync_hooks: RagSyncHooks,
     ) -> Result<()> {
         let loaders = app.document_loaders.clone();
         let (spinner, spinner_rx) = Spinner::create("");
-        abortable_run_with_spinner_rx(
+        sync_hooks.fire_started(&self.name, &self.path);
+        let synced = abortable_run_with_spinner_rx(
             self.sync_documents(
                 document_paths,
                 refresh,
@@ -650,10 +679,21 @@ impl Rag {
             spinner_rx,
             abort_signal,
         )
-        .await?;
-        if self.save()? {
-            println!("✓ Saved rag to '{}'.", self.path);
+        .await;
+        if let Err(err) = synced {
+            sync_hooks.fire_failed(&self.name, &self.path, &err);
+            return Err(err);
         }
+
+        match self.save() {
+            Ok(true) => println!("✓ Saved rag to '{}'.", self.path),
+            Ok(false) => {}
+            Err(err) => {
+                sync_hooks.fire_failed(&self.name, &self.path, &err);
+                return Err(err);
+            }
+        }
+        sync_hooks.fire_completed(&self.name, &self.path, self.file_count());
         Ok(())
     }
 
@@ -2280,6 +2320,8 @@ where
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::hooks::{HookDef, HooksMap, test_sink};
+    use serial_test::serial;
     use std::path::PathBuf;
     use std::sync::atomic::{AtomicU64, Ordering};
     use std::time::{SystemTime, UNIX_EPOCH};
@@ -2313,6 +2355,340 @@ mod tests {
         }
     }
 
+    fn rag_hooks_ctx(marker: &str) -> RequestContext {
+        let mut hooks_map = HooksMap::default();
+        for event in ["rag.sync.started", "rag.sync.completed", "rag.sync.failed"] {
+            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::Cmd)
+    }
+
+    fn rag_captures(marker: &str) -> Vec<test_sink::Capture> {
+        test_sink::snapshot()
+            .into_iter()
+            .filter(|capture| capture.hook_name.starts_with(marker))
+            .collect()
+    }
+
+    fn buildable_data() -> RagData {
+        RagData {
+            driver: "yaml".to_string(),
+            // The only embedding model resolvable in tests: the model
+            // registry is a process-global OnceLock pre-seeded by
+            // `seed_model_registries` in the request_context tests.
+            embedding_model: "test-seeded:test-embedder".to_string(),
+            chunk_size: 1000,
+            chunk_overlap: 100,
+            top_k: 5,
+            ..Default::default()
+        }
+    }
+
+    /// An AppConfig whose client list can construct the "test-seeded"
+    /// embeddings client: init_with_config instantiates the client even
+    /// when a sync has nothing to embed.
+    fn seeded_client_app() -> AppConfig {
+        let mut client = ClientConfig::default();
+        if let ClientConfig::OpenAIConfig(config) = &mut client {
+            config.name = Some("test-seeded".to_string());
+            let mut embedder = ModelData::new("test-embedder");
+            embedder.model_type = "embedding".to_string();
+            config.models = vec![embedder];
+        }
+        AppConfig {
+            clients: vec![client],
+            ..Default::default()
+        }
+    }
+
+    fn init_config() -> RagInitConfig {
+        RagInitConfig {
+            embedding_model: Some("test-seeded:test-embedder".to_string()),
+            chunk_size: Some(1000),
+            chunk_overlap: Some(100),
+            ..Default::default()
+        }
+    }
+
+    fn yaml_rag(name: &str, path: &Path, data: RagData) -> Rag {
+        Rag {
+            app_config: Arc::new(AppConfig::default()),
+            name: name.to_string(),
+            path: path.display().to_string(),
+            embedding_model: Model::new("openai", "text-embedding-3-small"),
+            bm25: data.build_bm25(),
+            provider: Box::new(YamlProvider::from_data(&data)),
+            node_to_docs: IndexMap::new(),
+            data,
+            last_sources: RwLock::new(None),
+        }
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn refresh_document_paths_fires_started_then_completed_with_doc_count() {
+        let _sink = test_sink::install();
+        let marker = "rag-sync-ok-v5k";
+        let dir = TempDir::new("sync-hooks-ok");
+        let doc = dir.path.join("doc.txt");
+        fs::write(&doc, "hello rag hooks").unwrap();
+        let doc_path = doc.display().to_string();
+
+        // The prepopulated file entry must use the exact string
+        // sync_documents resolves, so the sync sees an unchanged corpus and
+        // never needs an embeddings client.
+        let loaders = HashMap::new();
+        let (_, _, _, _, local_paths) = resolve_paths(&loaders, std::slice::from_ref(&doc_path))
+            .await
+            .unwrap();
+        let resolved_path = local_paths.iter().next().unwrap().clone();
+
+        let mut data = buildable_data();
+        data.next_file_id = 1;
+        data.files.insert(
+            0,
+            RagFile {
+                hash: sha256("hello rag hooks"),
+                path: resolved_path,
+                documents: vec![],
+            },
+        );
+        let rag_path = dir.path.join("kb.yaml");
+        let rag_path_display = rag_path.display().to_string();
+        let mut rag = yaml_rag("kb", &rag_path, data);
+        let sync_hooks = RagSyncHooks::resolve(&rag_hooks_ctx(marker));
+
+        rag.refresh_document_paths(
+            &[doc_path],
+            false,
+            false,
+            &AppConfig::default(),
+            create_abort_signal(),
+            sync_hooks,
+        )
+        .await
+        .unwrap();
+
+        let captures = rag_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].hook_name, format!("{marker}-rag.sync.started"));
+        assert_eq!(
+            captures[0].envs.get("COYOTE_RAG_NAME").map(String::as_str),
+            Some("kb")
+        );
+        assert_eq!(
+            captures[0].envs.get("COYOTE_RAG_PATH").map(String::as_str),
+            Some(rag_path_display.as_str())
+        );
+        assert_eq!(
+            captures[1].hook_name,
+            format!("{marker}-rag.sync.completed")
+        );
+        assert_eq!(
+            captures[1]
+                .envs
+                .get("COYOTE_RAG_DOC_COUNT")
+                .map(String::as_str),
+            Some("1")
+        );
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn refresh_document_paths_fires_started_then_failed_on_sync_error() {
+        let _sink = test_sink::install();
+        let marker = "rag-sync-fail-b8m";
+        let dir = TempDir::new("sync-hooks-fail");
+        let missing = dir.path.join("missing.txt").display().to_string();
+        let rag_path = dir.path.join("kb.yaml");
+        let mut rag = yaml_rag("kb", &rag_path, buildable_data());
+        let sync_hooks = RagSyncHooks::resolve(&rag_hooks_ctx(marker));
+
+        let result = rag
+            .refresh_document_paths(
+                &[missing],
+                false,
+                false,
+                &AppConfig::default(),
+                create_abort_signal(),
+                sync_hooks,
+            )
+            .await;
+
+        assert!(result.is_err(), "syncing a nonexistent document must fail");
+        let captures = rag_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].hook_name, format!("{marker}-rag.sync.started"));
+        assert_eq!(captures[1].hook_name, format!("{marker}-rag.sync.failed"));
+        assert_eq!(
+            captures[1].envs.get("COYOTE_RAG_NAME").map(String::as_str),
+            Some("kb")
+        );
+        assert!(
+            captures[1]
+                .envs
+                .get("COYOTE_ERROR")
+                .is_some_and(|error| !error.is_empty())
+        );
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn init_with_config_fires_started_then_completed_after_save() {
+        let _sink = test_sink::install();
+        let marker = "rag-init-ok-q7t";
+        let dir = TempDir::new("init-hooks-ok");
+        // An empty document syncs without embedding anything, so the build
+        // needs no live embeddings endpoint.
+        let doc = dir.path.join("doc.txt");
+        fs::write(&doc, "").unwrap();
+        let save_path = dir.path.join("kb.yaml");
+        let sync_hooks = RagSyncHooks::resolve(&rag_hooks_ctx(marker));
+
+        let rag = Rag::init_with_config(
+            &seeded_client_app(),
+            "kb-init",
+            &save_path,
+            &[doc.display().to_string()],
+            &init_config(),
+            create_abort_signal(),
+            sync_hooks,
+        )
+        .await
+        .unwrap();
+
+        assert_eq!(rag.file_count(), 1);
+        assert!(
+            save_path.exists(),
+            "completed must only fire after the knowledge base was saved"
+        );
+        let captures = rag_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].hook_name, format!("{marker}-rag.sync.started"));
+        assert_eq!(
+            captures[1].hook_name,
+            format!("{marker}-rag.sync.completed")
+        );
+        assert_eq!(
+            captures[1]
+                .envs
+                .get("COYOTE_RAG_DOC_COUNT")
+                .map(String::as_str),
+            Some("1")
+        );
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn init_with_config_fires_failed_when_save_fails() {
+        let _sink = test_sink::install();
+        let marker = "rag-init-save-fail-w2j";
+        let dir = TempDir::new("init-hooks-save-fail");
+        let doc = dir.path.join("doc.txt");
+        fs::write(&doc, "").unwrap();
+        // A regular file where save() expects a parent directory makes the
+        // save fail after a successful sync.
+        let blocker = dir.path.join("blocker");
+        fs::write(&blocker, "not a directory").unwrap();
+        let save_path = blocker.join("kb.yaml");
+        let sync_hooks = RagSyncHooks::resolve(&rag_hooks_ctx(marker));
+
+        let result = Rag::init_with_config(
+            &seeded_client_app(),
+            "kb-init",
+            &save_path,
+            &[doc.display().to_string()],
+            &init_config(),
+            create_abort_signal(),
+            sync_hooks,
+        )
+        .await;
+
+        assert!(
+            result.is_err(),
+            "an unwritable save path must fail the init"
+        );
+        let captures = rag_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].hook_name, format!("{marker}-rag.sync.started"));
+        assert_eq!(captures[1].hook_name, format!("{marker}-rag.sync.failed"));
+        assert!(
+            captures[1]
+                .envs
+                .get("COYOTE_ERROR")
+                .is_some_and(|error| !error.is_empty())
+        );
+    }
+
+    // The user-abort arm in abortable_run_with_spinner_rx only exists when
+    // stdout is a terminal, so a unit test cannot reach it; its
+    // bail!("Aborted.") surfaces through the same `synced` Err arm this
+    // sync error drives.
+    #[tokio::test]
+    #[serial]
+    async fn init_with_config_fires_failed_on_sync_error() {
+        let _sink = test_sink::install();
+        let marker = "rag-init-fail-d4n";
+        let dir = TempDir::new("init-hooks-fail");
+        let missing = dir.path.join("missing.txt").display().to_string();
+        let save_path = dir.path.join("kb.yaml");
+        let sync_hooks = RagSyncHooks::resolve(&rag_hooks_ctx(marker));
+
+        let result = Rag::init_with_config(
+            &seeded_client_app(),
+            "kb-init",
+            &save_path,
+            &[missing],
+            &init_config(),
+            create_abort_signal(),
+            sync_hooks,
+        )
+        .await;
+
+        assert!(result.is_err(), "syncing a nonexistent document must fail");
+        assert!(!save_path.exists());
+        let captures = rag_captures(marker);
+        assert_eq!(captures.len(), 2, "{captures:?}");
+        assert_eq!(captures[0].hook_name, format!("{marker}-rag.sync.started"));
+        assert_eq!(captures[1].hook_name, format!("{marker}-rag.sync.failed"));
+        assert!(
+            captures[1]
+                .envs
+                .get("COYOTE_ERROR")
+                .is_some_and(|error| !error.is_empty())
+        );
+    }
+
+    #[tokio::test]
+    #[serial]
+    async fn pure_load_fires_no_rag_sync_events() {
+        let _sink = test_sink::install();
+        test_sink::drain();
+        let dir = TempDir::new("sync-hooks-load");
+        let path = dir.path.join("kb.yaml");
+        fs::write(&path, serde_yaml::to_string(&buildable_data()).unwrap()).unwrap();
+
+        let rag = Rag::load(&AppConfig::default(), "kb", &path).await.unwrap();
+
+        assert_eq!(rag.file_count(), 0);
+        let captures = test_sink::drain();
+        assert!(
+            captures.is_empty(),
+            "a pure load must dispatch no hooks: {captures:?}"
+        );
+    }
+
     #[test]
     fn attached_ragdata_serializes_driver_and_attached() {
         let mut data = RagData {

src/sandbox/mixins.rs

@@ -197,6 +197,11 @@ pub fn discover() -> Result<Vec<DiscoveredMixin>> {
     ) {
         out.push(read_mixin(path)?);
     }
+    for agent_dir in subdirs_of(&paths::agents_data_dir()) {
+        for path in collect_mixins(&agent_dir.join("hooks"), &[ScanMode::Flat]) {
+            out.push(read_mixin(path)?);
+        }
+    }
     for path in collect_mixins(&paths::rags_dir(), &[ScanMode::Flat]) {
         out.push(read_mixin(path)?);
     }
@@ -206,6 +211,9 @@ pub fn discover() -> Result<Vec<DiscoveredMixin>> {
     for path in collect_mixins(&paths::roles_dir().join("hooks"), &[ScanMode::Flat]) {
         out.push(read_mixin(path)?);
     }
+    for path in collect_mixins(&paths::hooks_dir(), &[ScanMode::Flat]) {
+        out.push(read_mixin(path)?);
+    }
 
     if let Ok(cwd) = env::current_dir()
         && let Some(path) = paths::find_workspace_sbx_mixin(&cwd)
@@ -1005,6 +1013,51 @@ network:
         let _ = fs::remove_dir_all(&root);
     }
 
+    #[test]
+    #[serial_test::serial]
+    fn discover_scans_global_and_agent_hooks_mixins_but_never_the_manifest() {
+        use crate::config::builtin_manifest::BUILTIN_MANIFEST_FILE;
+        use crate::utils::get_env_name;
+
+        let root = unique_root("discover-hooks-dirs");
+        let hooks = root.join("hooks");
+        let agent_hooks = root.join("agents").join("researcher").join("hooks");
+        fs::create_dir_all(&hooks).unwrap();
+        fs::create_dir_all(&agent_hooks).unwrap();
+        let global_mixin = hooks.join("notify.sbx-mixin.yaml");
+        let agent_mixin = agent_hooks.join("guard.sbx-mixin.yaml");
+        fs::write(&global_mixin, "kind: mixin\n").unwrap();
+        fs::write(&agent_mixin, "kind: mixin\n").unwrap();
+        // The builtin installer's hidden manifest lives in both hooks dirs
+        // but is not a mixin and must never be picked up.
+        fs::write(hooks.join(BUILTIN_MANIFEST_FILE), "notify.sh\n").unwrap();
+        fs::write(agent_hooks.join(BUILTIN_MANIFEST_FILE), "guard.sh\n").unwrap();
+
+        let _config = crate::testing::EnvVarGuard::set(get_env_name("config_dir"), &root);
+        let found: Vec<PathBuf> = discover()
+            .unwrap()
+            .into_iter()
+            .map(|mixin| mixin.path)
+            .collect();
+
+        assert!(
+            found.contains(&global_mixin),
+            "missing global hooks mixin: {found:?}"
+        );
+        assert!(
+            found.contains(&agent_mixin),
+            "missing agent hooks mixin: {found:?}"
+        );
+        assert!(
+            found.iter().all(|path| path
+                .file_name()
+                .is_none_or(|name| name != BUILTIN_MANIFEST_FILE)),
+            "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/supervisor/mod.rs

@@ -190,6 +190,17 @@ impl Supervisor {
             .count()
     }
 
+    pub fn has_active_tasks(&self) -> bool {
+        self.effective_active_count() > 0
+            || self.active_job_count() > 0
+            || self.agents().any(|agent| {
+                agent
+                    .child_supervisor
+                    .as_ref()
+                    .is_some_and(|child_sup| child_sup.read().has_active_tasks())
+            })
+    }
+
     pub fn max_concurrent(&self) -> usize {
         self.max_concurrent
     }
@@ -449,6 +460,85 @@ mod tests {
         assert!(result.unwrap_err().to_string().contains("at capacity"));
     }
 
+    #[test]
+    fn has_active_tasks_false_when_empty_or_all_finished() {
+        let mut sup = Supervisor::new(4, 3);
+        assert!(!sup.has_active_tasks());
+        // make_handle drops its runtime, aborting the task, so the
+        // registered agent is already finished.
+        sup.register(make_handle("a1", "explore", 1)).unwrap();
+        assert!(!sup.has_active_tasks());
+    }
+
+    #[test]
+    fn has_active_tasks_true_with_running_agent() {
+        // Keep the runtime alive so the task is never polled and the agent
+        // counts as running.
+        let rt = Builder::new_current_thread().enable_all().build().unwrap();
+        let join_handle = rt.spawn(async {
+            Ok::<AgentResult, Error>(AgentResult {
+                id: "done".into(),
+                agent_name: "test".into(),
+                output: "result".into(),
+                exit_status: AgentExitStatus::Completed,
+            })
+        });
+        let running_handle = AgentHandle {
+            id: "a1".to_string(),
+            agent_name: "explore".to_string(),
+            depth: 1,
+            inbox: Arc::new(Inbox::new()),
+            abort_signal: create_abort_signal(),
+            join_handle,
+            child_supervisor: None,
+        };
+        let mut sup = Supervisor::new(4, 3);
+        sup.register(running_handle).unwrap();
+        assert!(sup.has_active_tasks());
+    }
+
+    #[test]
+    fn has_active_tasks_true_with_running_job() {
+        let mut sup = Supervisor::new(4, 3).with_max_concurrent_jobs(1);
+        sup.register(make_job("j1", create_abort_signal())).unwrap();
+        assert!(sup.has_active_tasks());
+    }
+
+    #[test]
+    fn has_active_tasks_true_with_only_grandchild_activity() {
+        // Keep the runtime alive so the grandchild task is never polled and
+        // counts as running.
+        let rt = Builder::new_current_thread().enable_all().build().unwrap();
+        let join_handle = rt.spawn(async {
+            Ok::<AgentResult, Error>(AgentResult {
+                id: "done".into(),
+                agent_name: "test".into(),
+                output: "result".into(),
+                exit_status: AgentExitStatus::Completed,
+            })
+        });
+        let grandchild = AgentHandle {
+            id: "g1".to_string(),
+            agent_name: "worker".to_string(),
+            depth: 2,
+            inbox: Arc::new(Inbox::new()),
+            abort_signal: create_abort_signal(),
+            join_handle,
+            child_supervisor: None,
+        };
+        let mut child_sup = Supervisor::new(4, 3);
+        child_sup.register(grandchild).unwrap();
+
+        // make_handle's direct task is already finished, so the only live
+        // work sits one supervisor level down.
+        let mut parent_handle = make_handle("a1", "explore", 1);
+        parent_handle.child_supervisor = Some(Arc::new(RwLock::new(child_sup)));
+        let mut sup = Supervisor::new(4, 3);
+        sup.register(parent_handle).unwrap();
+
+        assert!(sup.has_active_tasks());
+    }
+
     #[test]
     fn supervisor_register_rejects_exceeding_depth() {
         let mut sup = Supervisor::new(4, 2);

src/testing.rs

@@ -1,6 +1,10 @@
 //! Test-only helpers shared across modules' unit tests.
 
+use crate::config::WORKSPACE_COYOTE_DIR_NAME;
+use crate::utils;
 use log::{Level, LevelFilter, Log, Metadata, Record};
+use std::ffi::{OsStr, OsString};
+use std::path::PathBuf;
 use std::sync::{Mutex, Once, OnceLock};
 
 struct TestLogCollector;
@@ -8,25 +12,30 @@ struct TestLogCollector;
 static WARN_MESSAGES: OnceLock<Mutex<Vec<String>>> = OnceLock::new();
 static DEBUG_MESSAGES: OnceLock<Mutex<Vec<String>>> = OnceLock::new();
 
-/// Debug capture is restricted to the hooks module so the buffer is not
-/// flooded by debug output from the rest of the crate. Matching is
-/// module-boundary-aware: only this exact module or its `::` submodules
+/// Debug capture is restricted to the modules whose tests assert on debug
+/// output so the buffer is not flooded by the rest of the crate. Matching is
+/// module-boundary-aware: only these exact modules or their `::` submodules
 /// qualify, so a sibling like `hooks_registry` would not.
-const DEBUG_TARGET_PREFIX: &str = concat!(env!("CARGO_CRATE_NAME"), "::hooks");
+const DEBUG_TARGET_PREFIXES: [&str; 2] = [
+    concat!(env!("CARGO_CRATE_NAME"), "::hooks"),
+    concat!(env!("CARGO_CRATE_NAME"), "::config::agent"),
+];
 
 fn captures_warn(metadata: &Metadata) -> bool {
     metadata.level() <= Level::Warn
 }
 
-fn captures_hooks_debug(metadata: &Metadata) -> bool {
+fn captures_module_debug(metadata: &Metadata) -> bool {
     if metadata.level() != Level::Debug {
         return false;
     }
     let target = metadata.target();
-    target == DEBUG_TARGET_PREFIX
+    DEBUG_TARGET_PREFIXES.iter().any(|prefix| {
+        target == *prefix
             || target
-            .strip_prefix(DEBUG_TARGET_PREFIX)
+                .strip_prefix(prefix)
                 .is_some_and(|rest| rest.starts_with("::"))
+    })
 }
 
 /// Every warn- or error-level message captured since the collector was
@@ -37,16 +46,35 @@ pub(crate) fn warn_messages() -> &'static Mutex<Vec<String>> {
     WARN_MESSAGES.get_or_init(Mutex::default)
 }
 
-/// Every debug-level message from the hooks module captured since the
-/// collector was installed. Same marker-filtering discipline as
-/// [`warn_messages`].
+/// Every debug-level message from the [`DEBUG_TARGET_PREFIXES`] modules
+/// 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)
 }
 
+/// A copy of everything in [`warn_messages`], recovering from poisoning the
+/// same way the collector itself does.
+pub(crate) fn warn_snapshot() -> Vec<String> {
+    snapshot_of(warn_messages())
+}
+
+/// A copy of everything in [`debug_messages`], recovering from poisoning the
+/// same way the collector itself does.
+pub(crate) fn debug_snapshot() -> Vec<String> {
+    snapshot_of(debug_messages())
+}
+
+fn snapshot_of(buffer: &Mutex<Vec<String>>) -> Vec<String> {
+    buffer
+        .lock()
+        .unwrap_or_else(|poisoned| poisoned.into_inner())
+        .clone()
+}
+
 impl Log for TestLogCollector {
     fn enabled(&self, metadata: &Metadata) -> bool {
-        captures_warn(metadata) || captures_hooks_debug(metadata)
+        captures_warn(metadata) || captures_module_debug(metadata)
     }
 
     // A test that panics while holding a buffer poisons its mutex; the logger
@@ -57,7 +85,7 @@ impl Log for TestLogCollector {
                 .lock()
                 .unwrap_or_else(|poisoned| poisoned.into_inner())
                 .push(record.args().to_string());
-        } else if captures_hooks_debug(record.metadata()) {
+        } else if captures_module_debug(record.metadata()) {
             debug_messages()
                 .lock()
                 .unwrap_or_else(|poisoned| poisoned.into_inner())
@@ -68,15 +96,105 @@ impl Log for TestLogCollector {
     fn flush(&self) {}
 }
 
-/// Installs the process-wide log collector. `log::set_logger` accepts one
-/// logger per process, so every test that captures warns or hooks debug
-/// output must install through this shared entry point. The max level is
-/// Debug so the hooks debug capture sees its records; warn capture is
+/// Installs the process-wide log collector capturing warn-level messages and
+/// debug messages from the [`DEBUG_TARGET_PREFIXES`] modules.
+/// `log::set_logger` accepts one logger per process, so every test that
+/// captures either stream must install through this shared entry point. The
+/// max level is Debug so the debug capture sees its records; warn capture is
 /// unaffected.
-pub(crate) fn install_warn_collector() {
+pub(crate) fn install_log_collector() {
     static INSTALL: Once = Once::new();
     INSTALL.call_once(|| {
         log::set_logger(&TestLogCollector).expect("no other logger should be installed");
         log::set_max_level(LevelFilter::Debug);
     });
 }
+
+/// Sets (or removes) an environment variable for the guard's lifetime and
+/// restores the previous value on drop, including on panic, so a failing
+/// assertion cannot leak the override into subsequent tests. Tests using it
+/// must serialize (`#[serial]`) — the process environment is global.
+pub(crate) struct EnvVarGuard {
+    key: String,
+    previous: Option<OsString>,
+}
+
+impl EnvVarGuard {
+    pub(crate) fn set(key: impl Into<String>, value: impl AsRef<OsStr>) -> Self {
+        let key = key.into();
+        let previous = std::env::var_os(&key);
+        unsafe {
+            std::env::set_var(&key, value);
+        }
+        Self { key, previous }
+    }
+
+    pub(crate) fn unset(key: impl Into<String>) -> Self {
+        let key = key.into();
+        let previous = std::env::var_os(&key);
+        unsafe {
+            std::env::remove_var(&key);
+        }
+        Self { key, previous }
+    }
+}
+
+impl Drop for EnvVarGuard {
+    fn drop(&mut self) {
+        unsafe {
+            match &self.previous {
+                Some(previous) => std::env::set_var(&self.key, previous),
+                None => std::env::remove_var(&self.key),
+            }
+        }
+    }
+}
+
+/// Points the config dir and the workspace config dir at fresh temp
+/// directories for the guard's lifetime and removes them on drop, including
+/// on panic, so the developer's real `./.coyote/` never leaks into a test.
+/// The sessions-dir override is cleared too, so Global-scope session writes
+/// land under the temp config dir rather than the developer's real one.
+/// Tests using it must serialize (`#[serial]`) — the env vars are
+/// process-global.
+pub(crate) struct TestConfigDirGuard {
+    _env: EnvVarGuard,
+    _workspace_env: EnvVarGuard,
+    _sessions_env: EnvVarGuard,
+    pub(crate) path: PathBuf,
+    workspace_path: PathBuf,
+}
+
+impl TestConfigDirGuard {
+    pub(crate) fn new(label: &str) -> Self {
+        let unique = std::time::SystemTime::now()
+            .duration_since(std::time::UNIX_EPOCH)
+            .unwrap()
+            .as_nanos();
+        let path = std::env::temp_dir().join(format!("coyote-{label}-{unique}"));
+        std::fs::create_dir_all(&path).unwrap();
+        let workspace_path = std::env::temp_dir()
+            .join(format!("coyote-{label}-ws-{unique}"))
+            .join(WORKSPACE_COYOTE_DIR_NAME);
+        std::fs::create_dir_all(&workspace_path).unwrap();
+        Self {
+            _env: EnvVarGuard::set(utils::get_env_name("config_dir"), &path),
+            _workspace_env: EnvVarGuard::set(
+                utils::get_env_name("workspace_config_dir"),
+                &workspace_path,
+            ),
+            _sessions_env: EnvVarGuard::unset(utils::get_env_name("sessions_dir")),
+            path,
+            workspace_path,
+        }
+    }
+}
+
+impl Drop for TestConfigDirGuard {
+    fn drop(&mut self) {
+        let _ = std::fs::remove_dir_all(&self.path);
+        if let Some(root) = self.workspace_path.parent() {
+            let _ = std::fs::remove_dir_all(root);
+        }
+    }
+}

src/vault/mod.rs

@@ -332,8 +332,14 @@ impl Vault {
         }
 
         if cli.list_secrets {
+            if vault.sandbox_mode {
+                println!(
+                    "The vault is unavailable in sandbox mode. Use `coyote --list-secrets` on your host."
+                );
+            } else {
                 vault.list_secrets(true)?;
             }
+        }
 
         Ok(())
     }
@@ -410,4 +416,23 @@ mod tests {
             }
         }
     }
+
+    #[test]
+    fn list_secrets_flag_ok_in_sandbox() {
+        use clap::Parser;
+
+        // Built directly rather than via IS_SANDBOX so this test cannot race
+        // the env juggling in vault_disabled_in_sandbox.
+        let vault = Vault {
+            sandbox_mode: true,
+            ..Vault::default()
+        };
+        let cli = Cli::try_parse_from(["coyote", "--list-secrets"]).unwrap();
+
+        // Pins the --list-secrets sandbox contract: rc=0 with an informational
+        // readout instead of the hard failure the mutating flags keep. The
+        // message goes straight to stdout, so only Ok is asserted here.
+        Vault::handle_vault_flags(cli, &vault)
+            .expect("--list-secrets must succeed in sandbox mode");
+    }
 }

tests/inspection_flags.rs

@@ -0,0 +1,546 @@
+//! Binary-level contract for inspection flags on a pristine config dir:
+//! exit 0 and NOTHING written into the config dir (no first-run wizard,
+//! no builtins bootstrap). Only --info guarantees output on stdout; the
+//! list flags legitimately emit an empty listing on a pristine dir, so
+//! their contract is exit 0 + zero writes. Vault-backed flags like
+//! --list-secrets depend on host state and are covered by
+//! scripts/usage-probe-inspection.sh instead. Agent runs, by contrast,
+//! must still bootstrap builtins even when combined with --info — see
+//! agent_info_on_empty_config_dir_bootstraps_builtins. Flags that write,
+//! like --sync-models, are NOT inspection flags and must stay on the
+//! bootstrap path — see sync_models_stays_on_bootstrap_path.
+//!
+//! Every test runs against a fresh fake HOME and (unless sandbox mode is the
+//! subject under test) a scrubbed IS_SANDBOX/provider env, so host state —
+//! a real ~/.coyote_password or a sandbox shell — cannot mask
+//! virgin-environment regressions.
+
+use std::fs;
+use std::path::{Path, PathBuf};
+use std::process::{Command, Stdio};
+use std::time::{SystemTime, UNIX_EPOCH};
+use std::{env, process};
+
+fn fresh_config_dir(label: &str) -> PathBuf {
+    let unique = SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap()
+        .as_nanos();
+    let tmp_dir = env::temp_dir().join(format!("coyote-inspection-{label}-{unique}"));
+    fs::create_dir_all(&tmp_dir).unwrap();
+    tmp_dir
+}
+
+fn probe_inspection_flag(flag: &str, require_stdout: bool) {
+    let label = flag.trim_start_matches("--");
+    let tmp_dir = fresh_config_dir(label);
+    let home_dir = fresh_config_dir(&format!("{label}-home"));
+
+    let output = Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .arg(flag)
+        .env("COYOTE_CONFIG_DIR", &tmp_dir)
+        // A fresh fake HOME hides any real ~/.coyote_password on the host;
+        // USERPROFILE is the best-effort Windows equivalent (dirs resolves
+        // home via the Known Folder API there). HOME is set, never removed:
+        // dirs::home_dir() panics inside gman when home can't be determined.
+        .env("HOME", &home_dir)
+        .env("USERPROFILE", &home_dir)
+        // A leaked sandbox/provider env would reroute the vault and config
+        // paths under test.
+        .env_remove("IS_SANDBOX")
+        .env_remove("COYOTE_PROVIDER")
+        .env_remove("COYOTE_PLATFORM")
+        // Workspace mcp.json discovery resolves from the CWD, so pin it to
+        // the isolated fake HOME to keep host state out of the probe.
+        .current_dir(&home_dir)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap();
+
+    let leftover: Vec<_> = fs::read_dir(&tmp_dir)
+        .unwrap()
+        .map(|entry| entry.unwrap().file_name())
+        .collect();
+    assert!(
+        !home_dir.join(".coyote_password").exists(),
+        "{flag}: the lenient inspection path must never bootstrap a password file"
+    );
+    let _ = fs::remove_dir_all(&tmp_dir);
+    let _ = fs::remove_dir_all(&home_dir);
+
+    assert!(
+        output.status.success(),
+        "{flag}: expected exit 0 on an empty config dir, got {:?}\nstdout: {}\nstderr: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+    if require_stdout {
+        assert!(
+            !output.stdout.is_empty(),
+            "{flag}: expected some output on stdout"
+        );
+    }
+    assert!(
+        leftover.is_empty(),
+        "{flag}: inspection flags must write nothing into the config dir: {leftover:?}"
+    );
+}
+
+#[test]
+fn info_on_empty_config_dir_writes_nothing() {
+    probe_inspection_flag("--info", true);
+}
+
+// List flags on a pristine dir correctly print an empty listing, so the
+// contract is exit 0 + zero writes only (no stdout assertion).
+
+#[test]
+fn list_models_on_empty_config_dir_writes_nothing() {
+    probe_inspection_flag("--list-models", false);
+}
+
+#[test]
+fn list_agents_on_empty_config_dir_writes_nothing() {
+    probe_inspection_flag("--list-agents", false);
+}
+
+#[test]
+fn mcp_list_on_empty_config_dir_writes_nothing() {
+    probe_inspection_flag("--mcp-list", false);
+}
+
+// The wizard bypass must not swallow the builtins bootstrap for agent runs:
+// `--agent <builtin> --info` on a totally fresh config dir has to install
+// the bundled definitions before it can render the agent readout.
+#[test]
+fn agent_info_on_empty_config_dir_bootstraps_builtins() {
+    let tmp_dir = fresh_config_dir("agent-info");
+    let home_dir = fresh_config_dir("agent-info-home");
+
+    let output = Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .args(["--agent", "adversary", "--info"])
+        .env("COYOTE_CONFIG_DIR", &tmp_dir)
+        .env("HOME", &home_dir)
+        .env("USERPROFILE", &home_dir)
+        .env_remove("IS_SANDBOX")
+        .env_remove("COYOTE_PROVIDER")
+        .env_remove("COYOTE_PLATFORM")
+        .current_dir(&home_dir)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap();
+
+    let agents_dir = tmp_dir.join("agents");
+    let builtins_installed =
+        agents_dir.is_dir() && fs::read_dir(&agents_dir).unwrap().next().is_some();
+    let _ = fs::remove_dir_all(&tmp_dir);
+    let _ = fs::remove_dir_all(&home_dir);
+
+    assert!(
+        output.status.success(),
+        "--agent adversary --info: expected exit 0 on an empty config dir, got {:?}\nstdout: {}\nstderr: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+    assert!(
+        builtins_installed,
+        "--agent adversary --info: expected builtin agents installed into {}",
+        agents_dir.display()
+    );
+    // The --info readout echoes the loaded agent definition including its
+    // global_tools, so a builtin tool name there proves the definitions were
+    // loaded into the agent's tool scope, not just written to disk.
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    assert!(
+        stdout.contains("fs_cat.sh"),
+        "--agent adversary --info: expected builtin tool fs_cat.sh in the readout\nstdout: {stdout}"
+    );
+}
+
+// Sandbox-mode vault contract: `--list-secrets` is an inspection readout and
+// must exit 0 with an informational message (and zero writes) when the vault
+// is unreachable inside a sandbox, while mutating vault flags stay strict.
+#[test]
+fn sandbox_list_secrets_prints_informational_message_and_writes_nothing() {
+    let tmp_dir = fresh_config_dir("sandbox-list-secrets");
+    let home_dir = fresh_config_dir("sandbox-list-secrets-home");
+
+    let output = Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .arg("--list-secrets")
+        .env("COYOTE_CONFIG_DIR", &tmp_dir)
+        .env("IS_SANDBOX", "1")
+        .env("HOME", &home_dir)
+        .env("USERPROFILE", &home_dir)
+        .current_dir(&home_dir)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap();
+
+    let leftover: Vec<_> = fs::read_dir(&tmp_dir)
+        .unwrap()
+        .map(|entry| entry.unwrap().file_name())
+        .collect();
+    let _ = fs::remove_dir_all(&tmp_dir);
+    let _ = fs::remove_dir_all(&home_dir);
+
+    assert!(
+        output.status.success(),
+        "--list-secrets in sandbox mode: expected exit 0, got {:?}\nstdout: {}\nstderr: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+    let combined = format!(
+        "{}{}",
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+    assert!(
+        combined.contains("The vault is unavailable in sandbox mode"),
+        "--list-secrets in sandbox mode: expected the informational readout, got: {combined}"
+    );
+    assert!(
+        leftover.is_empty(),
+        "--list-secrets in sandbox mode: expected zero writes into the config dir: {leftover:?}"
+    );
+}
+
+// Mutating vault flags are NOT inspection flags: in sandbox mode they must
+// fail hard with the vault-management error, never the soft informational
+// message. A minimal valid config is provided so the run gets past model
+// resolution and reaches the vault gate.
+#[test]
+fn sandbox_mutating_vault_flag_stays_strict() {
+    let tmp_dir = fresh_config_dir("sandbox-delete-secret");
+    let home_dir = fresh_config_dir("sandbox-delete-secret-home");
+    fs::write(
+        tmp_dir.join("config.yaml"),
+        "model: dryrun:dry-model\n\
+         dry_run: true\n\
+         clients:\n\
+         \x20 - type: openai\n\
+         \x20   name: dryrun\n\
+         \x20   auth: none\n\
+         \x20   api_key: unused\n\
+         \x20   models:\n\
+         \x20     - name: dry-model\n\
+         \x20       max_input_tokens: 100000\n\
+         \x20       supports_function_calling: true\n\
+         save: false\n",
+    )
+    .unwrap();
+
+    let output = Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .args(["--delete-secret", "probe"])
+        .env("COYOTE_CONFIG_DIR", &tmp_dir)
+        .env("IS_SANDBOX", "1")
+        .env("HOME", &home_dir)
+        .env("USERPROFILE", &home_dir)
+        .current_dir(&home_dir)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap();
+    let _ = fs::remove_dir_all(&tmp_dir);
+    let _ = fs::remove_dir_all(&home_dir);
+
+    assert!(
+        !output.status.success(),
+        "--delete-secret in sandbox mode: expected a non-zero exit, got {:?}\nstdout: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stdout)
+    );
+    let combined = format!(
+        "{}{}",
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+    assert!(
+        combined.contains("Vault management is disabled in sandbox mode"),
+        "--delete-secret in sandbox mode: expected the strict vault error, got: {combined}"
+    );
+}
+
+// The --mcp-list leniency must not leak into the mutating MCP flags on the
+// host path: with no password file (fresh fake HOME) and no sandbox env,
+// --mcp-get/--mcp-remove/--mcp-add have to fail on the strict vault
+// requirement rather than operate with an unconfigured vault.
+fn probe_strict_mcp_flag(label: &str, args: &[&str]) {
+    let tmp_dir = fresh_config_dir(&format!("{label}-no-vault"));
+    let home_dir = fresh_config_dir(&format!("{label}-no-vault-home"));
+    fs::write(
+        tmp_dir.join("config.yaml"),
+        "model: dryrun:dry-model\n\
+         dry_run: true\n\
+         clients:\n\
+         \x20 - type: openai\n\
+         \x20   name: dryrun\n\
+         \x20   auth: none\n\
+         \x20   api_key: unused\n\
+         \x20   models:\n\
+         \x20     - name: dry-model\n\
+         \x20       max_input_tokens: 100000\n\
+         \x20       supports_function_calling: true\n\
+         save: false\n",
+    )
+    .unwrap();
+    fs::write(
+        tmp_dir.join("mcp.json"),
+        r#"{"mcpServers":{"probe-server":{"type":"stdio","command":"echo","args":["hi"]}}}"#,
+    )
+    .unwrap();
+
+    let output = Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .args(args)
+        .env("COYOTE_CONFIG_DIR", &tmp_dir)
+        .env("HOME", &home_dir)
+        .env("USERPROFILE", &home_dir)
+        .env_remove("IS_SANDBOX")
+        .env_remove("COYOTE_PROVIDER")
+        .env_remove("COYOTE_PLATFORM")
+        .current_dir(&home_dir)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap();
+    // The strict path must not touch the server registry either.
+    let mcp_json_after = fs::read_to_string(tmp_dir.join("mcp.json")).unwrap();
+    let _ = fs::remove_dir_all(&tmp_dir);
+    let _ = fs::remove_dir_all(&home_dir);
+
+    assert!(
+        !output.status.success(),
+        "{label} without a vault: expected a non-zero exit, got {:?}\nstdout: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stdout)
+    );
+    let combined = format!(
+        "{}{}",
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+    assert!(
+        combined.contains("A password file is required"),
+        "{label} without a vault: expected the strict vault error, got: {combined}"
+    );
+    assert!(
+        mcp_json_after.contains("probe-server"),
+        "{label} without a vault: mcp.json must be left untouched, got: {mcp_json_after}"
+    );
+}
+
+#[test]
+fn mcp_mutating_flag_stays_strict_without_vault() {
+    probe_strict_mcp_flag("mcp-remove", &["--mcp-remove", "probe-server"]);
+}
+
+// --mcp-get is read-only but consumes resolved server config (which may
+// embed secrets), so it stays on the strict vault path by design.
+#[test]
+fn mcp_get_stays_strict_without_vault() {
+    probe_strict_mcp_flag("mcp-get", &["--mcp-get", "probe-server"]);
+}
+
+#[test]
+fn mcp_add_stays_strict_without_vault() {
+    probe_strict_mcp_flag("mcp-add", &["--mcp-add", "newsrv", "--", "echo", "hi"]);
+}
+
+// The listing leniency exercised with content: a configured, secret-free
+// server must be listed even when no vault exists (no password file, no
+// sandbox env), and the readout must not write anything new into the
+// config dir.
+#[test]
+fn mcp_list_lists_configured_server_without_vault() {
+    let tmp_dir = fresh_config_dir("mcp-list-configured");
+    let home_dir = fresh_config_dir("mcp-list-configured-home");
+    fs::write(
+        tmp_dir.join("mcp.json"),
+        r#"{"mcpServers":{"probe-server":{"type":"stdio","command":"echo","args":["hi"]}}}"#,
+    )
+    .unwrap();
+
+    let output = Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .arg("--mcp-list")
+        .env("COYOTE_CONFIG_DIR", &tmp_dir)
+        .env("HOME", &home_dir)
+        .env("USERPROFILE", &home_dir)
+        .env_remove("IS_SANDBOX")
+        .env_remove("COYOTE_PROVIDER")
+        .env_remove("COYOTE_PLATFORM")
+        .current_dir(&home_dir)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap();
+
+    let leftover: Vec<_> = fs::read_dir(&tmp_dir)
+        .unwrap()
+        .map(|entry| entry.unwrap().file_name())
+        .collect();
+    let _ = fs::remove_dir_all(&tmp_dir);
+    let _ = fs::remove_dir_all(&home_dir);
+
+    assert!(
+        output.status.success(),
+        "--mcp-list with a configured server and no vault: expected exit 0, got {:?}\nstderr: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stderr)
+    );
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    assert!(
+        stdout.contains("probe-server"),
+        "--mcp-list with a configured server: expected 'probe-server' in stdout, got: {stdout}"
+    );
+    assert_eq!(
+        leftover,
+        vec![std::ffi::OsString::from("mcp.json")],
+        "--mcp-list must not write into the config dir beyond the pre-seeded mcp.json"
+    );
+}
+
+// --sync-models downloads and writes models-override.yaml, so it is NOT an
+// inspection flag: on a pristine config dir it must take the bootstrap path
+// (builtins installed) and, off a terminal, fail on the missing config
+// instead of silently operating on defaults. The host path is the one under
+// test: a leaked IS_SANDBOX (or provider env) would reroute the missing
+// config to the sandbox wizard prompt instead of the fast failure.
+#[test]
+fn sync_models_stays_on_bootstrap_path() {
+    let tmp_dir = fresh_config_dir("sync-models");
+    let home_dir = fresh_config_dir("sync-models-home");
+
+    let output = Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .arg("--sync-models")
+        .env("COYOTE_CONFIG_DIR", &tmp_dir)
+        .env("HOME", &home_dir)
+        .env("USERPROFILE", &home_dir)
+        .env_remove("IS_SANDBOX")
+        .env_remove("COYOTE_PROVIDER")
+        .env_remove("COYOTE_PLATFORM")
+        .current_dir(&home_dir)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap();
+
+    let bootstrapped = fs::read_dir(&tmp_dir).unwrap().next().is_some();
+    let _ = fs::remove_dir_all(&tmp_dir);
+    let _ = fs::remove_dir_all(&home_dir);
+
+    assert!(
+        !output.status.success(),
+        "--sync-models: expected the strict missing-config failure on an empty config dir, got {:?}\nstdout: {}\nstderr: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+    assert!(
+        bootstrapped,
+        "--sync-models: expected the builtins bootstrap to populate the config dir"
+    );
+}
+
+fn run_list_sessions(
+    cwd: &Path,
+    config_dir: &Path,
+    global_sessions: &Path,
+    home_dir: &Path,
+) -> process::Output {
+    Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .arg("--list-sessions")
+        .env("COYOTE_CONFIG_DIR", config_dir)
+        .env("COYOTE_SESSIONS_DIR", global_sessions)
+        .env("HOME", home_dir)
+        .env("USERPROFILE", home_dir)
+        .env_remove("IS_SANDBOX")
+        .env_remove("COYOTE_PROVIDER")
+        .env_remove("COYOTE_PLATFORM")
+        .env_remove("COYOTE_WORKSPACE_CONFIG_DIR")
+        .current_dir(cwd)
+        .stdin(Stdio::null())
+        .output()
+        .unwrap()
+}
+
+fn seed_session(dir: &Path, name: &str) {
+    fs::create_dir_all(dir).unwrap();
+    fs::write(dir.join(format!("{name}.yaml")), "messages: []\n").unwrap();
+}
+
+#[test]
+fn usage_probe_list_sessions_merges_cwd_workspace_scope_with_global() {
+    let config_dir = fresh_config_dir("list-sessions-ws");
+    let home_dir = fresh_config_dir("list-sessions-ws-home");
+    let global_sessions = fresh_config_dir("list-sessions-ws-global");
+    let workspace = fresh_config_dir("list-sessions-ws-cwd");
+    let bare_cwd = fresh_config_dir("list-sessions-ws-bare");
+    let workspace_sessions = workspace.join(".coyote").join("sessions");
+
+    seed_session(&global_sessions, "both");
+    seed_session(&global_sessions, "glob-only");
+    seed_session(&workspace_sessions, "both");
+    seed_session(&workspace_sessions, "ws-only");
+
+    let in_workspace = run_list_sessions(&workspace, &config_dir, &global_sessions, &home_dir);
+    let in_bare = run_list_sessions(&bare_cwd, &config_dir, &global_sessions, &home_dir);
+
+    let config_leftover: Vec<_> = fs::read_dir(&config_dir)
+        .unwrap()
+        .map(|entry| entry.unwrap().file_name())
+        .collect();
+    let bare_created_workspace = bare_cwd.join(".coyote").exists();
+    let workspace_entries: Vec<_> = fs::read_dir(&workspace_sessions)
+        .unwrap()
+        .map(|entry| entry.unwrap().file_name().to_string_lossy().into_owned())
+        .collect();
+    for dir in [
+        &config_dir,
+        &home_dir,
+        &global_sessions,
+        &workspace,
+        &bare_cwd,
+    ] {
+        let _ = fs::remove_dir_all(dir);
+    }
+
+    for (label, output) in [("workspace", &in_workspace), ("bare", &in_bare)] {
+        assert!(
+            output.status.success(),
+            "--list-sessions ({label}): expected exit 0, got {:?}\nstdout: {}\nstderr: {}",
+            output.status,
+            String::from_utf8_lossy(&output.stdout),
+            String::from_utf8_lossy(&output.stderr)
+        );
+    }
+
+    let lines = |output: &process::Output| -> Vec<String> {
+        String::from_utf8_lossy(&output.stdout)
+            .lines()
+            .map(str::to_owned)
+            .collect()
+    };
+    assert_eq!(
+        lines(&in_workspace),
+        vec!["both", "glob-only", "ws-only"],
+        "workspace CWD: merged, deduplicated, sorted"
+    );
+    assert_eq!(
+        lines(&in_bare),
+        vec!["both", "glob-only"],
+        "CWD without .coyote/: behaviour unchanged (global listing only)"
+    );
+    assert!(
+        !bare_created_workspace,
+        "--list-sessions must never create .coyote/ in the CWD"
+    );
+    assert!(
+        config_leftover.is_empty(),
+        "--list-sessions must write nothing into the config dir: {config_leftover:?}"
+    );
+    let mut workspace_entries = workspace_entries;
+    workspace_entries.sort_unstable();
+    assert_eq!(
+        workspace_entries,
+        vec!["both.yaml", "ws-only.yaml"],
+        "listing is read-only for the workspace sessions dir"
+    );
+}

tests/macro_bracketing.rs

@@ -0,0 +1,293 @@
+//! Binary-level contract for --macro bracket symmetry: a committed macro
+//! run fires agent.started plus EXACTLY ONE terminal agent event
+//! (agent.completed / agent.failed / agent.interrupted), whether the agent
+//! arrives via the --agent flag or an in-macro `.agent` step, in both
+//! isolation modes, on success and failure alike. The markers ride on
+//! global agent.* hooks admitted through the agent's `global_hooks: ["*"]`
+//! wildcard, so the fixture also exercises the whitelist grammar
+//! end-to-end — and stays observable even if a failing step leaves the
+//! context without a loaded agent.
+
+use std::env;
+use std::fs;
+use std::path::{Path, PathBuf};
+use std::process::{Command, Output, Stdio};
+use std::thread;
+use std::time::{Duration, Instant, SystemTime, UNIX_EPOCH};
+
+const MARKERS: [&str; 4] = ["STARTED", "COMPLETED", "FAILED", "INTERRUPTED"];
+
+fn fresh_config_dir(label: &str) -> PathBuf {
+    let unique = SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap()
+        .as_nanos();
+    let tmp_dir = env::temp_dir().join(format!("coyote-macro-bracketing-{label}-{unique}"));
+    fs::create_dir_all(&tmp_dir).unwrap();
+    tmp_dir
+}
+
+/// Removes the fixture dir even when an assertion panics mid-run, so failed
+/// runs do not accumulate temp dirs.
+struct TempDirGuard(PathBuf);
+
+impl Drop for TempDirGuard {
+    fn drop(&mut self) {
+        let _ = fs::remove_dir_all(&self.0);
+    }
+}
+
+/// Path of the file `marker`'s hook appends to. Every event gets its OWN
+/// file because cmd opens `>>` targets write-exclusive (no shared write
+/// access): the STARTED and terminal hook children run concurrently, and
+/// when both appended to one shared log, overlapping opens made the loser
+/// fail with a sharing violation and silently drop its line — a permanent
+/// marker loss that surfaced as a Windows-CI-only flake. Separate files
+/// make writer overlap impossible: each event fires at most once per
+/// bracket, and re-opened brackets are step-separated, so every file has
+/// one writer at a time.
+fn marker_log(dir: &Path, marker: &str) -> PathBuf {
+    dir.join(format!("agent-events-{marker}.log"))
+}
+
+/// Builds the hook command that appends `marker` to its own marker file, in
+/// the dialect of the shell the hook engine dispatches through: `sh -c`
+/// elsewhere, `cmd /C` on Windows. The cmd form parenthesizes the echo
+/// because `echo X >> f` under cmd writes "X " with a trailing space, which
+/// would break exact marker matching. Both forms double-quote the path, so
+/// the command also survives YAML single-quoting and spaces in temp paths.
+fn marker_command(marker: &str, dir: &Path) -> String {
+    let log = marker_log(dir, marker);
+    let log = log.display();
+    if cfg!(windows) {
+        format!(r#"(echo {marker})>> "{log}""#)
+    } else {
+        format!(r#"echo {marker} >> "{log}""#)
+    }
+}
+
+/// Lays out a config dir with a dry_run model, global agent.* hooks that
+/// append one marker line per event to that event's marker file, a
+/// `probe-macro` agent that whitelists everything, and a `probe` macro with
+/// the given YAML body.
+fn write_fixture(dir: &Path, macro_yaml: &str) {
+    // Without IS_SANDBOX (scrubbed below) a run insists on a vault password
+    // file, so the fixture provides one.
+    let vault_pass = dir.join("vault-pass");
+    fs::write(&vault_pass, "test-password\n").unwrap();
+    // Paths land in single-quoted YAML scalars: double-quoted ones would read
+    // the backslashes in a Windows temp path (`C:\Users\...`) as escapes.
+    fs::write(
+        dir.join("config.yaml"),
+        format!(
+            "model: dryrun:dry-model\n\
+             dry_run: true\n\
+             vault_password_file: '{vault_pass}'\n\
+             clients:\n\
+             \x20 - type: openai\n\
+             \x20   name: dryrun\n\
+             \x20   auth: none\n\
+             \x20   api_key: 'unused'\n\
+             \x20   models:\n\
+             \x20     - name: dry-model\n\
+             \x20       max_input_tokens: 100000\n\
+             \x20       supports_function_calling: true\n\
+             save: false\n\
+             memory: false\n\
+             stream: false\n\
+             hooks:\n\
+             \x20 agent.started:\n\
+             \x20   - name: mark\n\
+             \x20     command: '{started}'\n\
+             \x20 agent.completed:\n\
+             \x20   - name: mark\n\
+             \x20     command: '{completed}'\n\
+             \x20 agent.failed:\n\
+             \x20   - name: mark\n\
+             \x20     command: '{failed}'\n\
+             \x20 agent.interrupted:\n\
+             \x20   - name: mark\n\
+             \x20     command: '{interrupted}'\n",
+            vault_pass = vault_pass.display(),
+            started = marker_command("STARTED", dir),
+            completed = marker_command("COMPLETED", dir),
+            failed = marker_command("FAILED", dir),
+            interrupted = marker_command("INTERRUPTED", dir),
+        ),
+    )
+    .unwrap();
+
+    let agent_dir = dir.join("agents/probe-macro");
+    fs::create_dir_all(&agent_dir).unwrap();
+    fs::write(
+        agent_dir.join("config.yaml"),
+        "name: probe-macro\n\
+         description: macro bracketing probe agent\n\
+         version: 0.1.0\n\
+         instructions: |\n\
+         \x20 You are a probe agent. Reply briefly.\n\
+         global_hooks:\n\
+         \x20 - \"*\"\n",
+    )
+    .unwrap();
+
+    let macros_dir = dir.join("macros");
+    fs::create_dir_all(&macros_dir).unwrap();
+    fs::write(macros_dir.join("probe.yaml"), macro_yaml).unwrap();
+}
+
+fn run_coyote(dir: &Path, args: &[&str]) -> Output {
+    Command::new(env!("CARGO_BIN_EXE_coyote"))
+        .args(args)
+        .current_dir(dir)
+        .env("COYOTE_CONFIG_DIR", dir)
+        .env_remove("IS_SANDBOX")
+        .stdin(Stdio::null())
+        .output()
+        .unwrap()
+}
+
+/// Counts `marker`'s exact-match lines in its own marker file; a missing
+/// file is zero fires. Matching stays byte-exact on both platforms because
+/// `lines()` strips the CRLF that cmd's echo emits on Windows.
+fn marker_count(dir: &Path, marker: &str) -> usize {
+    fs::read_to_string(marker_log(dir, marker))
+        .unwrap_or_default()
+        .lines()
+        .filter(|line| *line == marker)
+        .count()
+}
+
+fn dump_markers(dir: &Path) -> String {
+    MARKERS
+        .iter()
+        .map(|marker| {
+            let contents = fs::read_to_string(marker_log(dir, marker)).unwrap_or_default();
+            format!("{marker}: {contents:?}")
+        })
+        .collect::<Vec<_>>()
+        .join(", ")
+}
+
+/// Bounded poll until every expected marker is present. The binary's exit
+/// drain only acknowledges that each hook process SPAWNED — the hooks
+/// themselves keep running concurrently after `output()` returns, and
+/// nothing orders their writes (the STARTED writer can land after the
+/// terminal one). Waiting on all expected markers, not just the terminal
+/// one, keeps the exact-count assertions below race-free.
+fn wait_for_markers(dir: &Path, needles: &[&str]) {
+    let deadline = Instant::now() + Duration::from_secs(10);
+    loop {
+        if needles.iter().all(|needle| marker_count(dir, needle) > 0) {
+            return;
+        }
+        assert!(
+            Instant::now() < deadline,
+            "timed out waiting for {needles:?}; markers so far: {}",
+            dump_markers(dir)
+        );
+        thread::sleep(Duration::from_millis(50));
+    }
+}
+
+fn assert_marker_count(dir: &Path, marker: &str, expected: usize) {
+    let count = marker_count(dir, marker);
+    assert_eq!(
+        count,
+        expected,
+        "expected {expected}x {marker}; markers so far: {}",
+        dump_markers(dir)
+    );
+}
+
+fn assert_started_and_single_terminal(dir: &Path, terminal: &str) {
+    assert_marker_count(dir, "STARTED", 1);
+    for marker in ["COMPLETED", "FAILED", "INTERRUPTED"] {
+        let expected = usize::from(marker == terminal);
+        assert_marker_count(dir, marker, expected);
+    }
+}
+
+fn probe_macro_run(label: &str, macro_yaml: &str, args: &[&str], expect_success: bool) {
+    let dir = fresh_config_dir(label);
+    let _cleanup = TempDirGuard(dir.clone());
+    write_fixture(&dir, macro_yaml);
+
+    let output = run_coyote(&dir, args);
+    assert_eq!(
+        output.status.success(),
+        expect_success,
+        "{label}: unexpected exit {:?}\nstdout: {}\nstderr: {}",
+        output.status,
+        String::from_utf8_lossy(&output.stdout),
+        String::from_utf8_lossy(&output.stderr)
+    );
+
+    let terminal = if expect_success {
+        "COMPLETED"
+    } else {
+        "FAILED"
+    };
+    wait_for_markers(&dir, &["STARTED", terminal]);
+    assert_started_and_single_terminal(&dir, terminal);
+}
+
+#[test]
+fn agent_macro_run_fires_started_and_exactly_one_completed() {
+    probe_macro_run(
+        "agent-flag-success",
+        "steps:\n  - \".set temperature 0.5\"\n",
+        &["--agent", "probe-macro", "--macro", "probe"],
+        true,
+    );
+}
+
+#[test]
+fn agent_macro_failure_closes_the_bracket_with_exactly_one_failed() {
+    probe_macro_run(
+        "agent-flag-failure",
+        "steps:\n  - \".agent no-such-agent-zz\"\n",
+        &["--agent", "probe-macro", "--macro", "probe"],
+        false,
+    );
+}
+
+#[test]
+fn isolated_in_macro_agent_step_fires_started_and_exactly_one_completed() {
+    probe_macro_run(
+        "isolated-step-success",
+        "steps:\n  - \".agent probe-macro\"\n  - \".set temperature 0.5\"\n",
+        &["--macro", "probe"],
+        true,
+    );
+}
+
+#[test]
+fn isolated_in_macro_agent_step_failure_closes_the_bracket() {
+    probe_macro_run(
+        "isolated-step-failure",
+        "steps:\n  - \".agent probe-macro\"\n  - \".agent no-such-agent-zz\"\n",
+        &["--macro", "probe"],
+        false,
+    );
+}
+
+#[test]
+fn non_isolated_in_macro_agent_step_fires_started_and_exactly_one_completed() {
+    probe_macro_run(
+        "non-isolated-step-success",
+        "isolated: false\nsteps:\n  - \".agent probe-macro\"\n  - \".set temperature 0.5\"\n",
+        &["--macro", "probe"],
+        true,
+    );
+}
+
+#[test]
+fn non_isolated_in_macro_agent_step_failure_closes_the_bracket() {
+    probe_macro_run(
+        "non-isolated-step-failure",
+        "isolated: false\nsteps:\n  - \".agent probe-macro\"\n  - \".agent no-such-agent-zz\"\n",
+        &["--macro", "probe"],
+        false,
+    );
+}