feat: Deep research upgrade so sisyphus and the architect now have 3 possible research types: librarian standard, librarian deep, and true deep research with reflexion

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