Gitinbox/OpenOPC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(company): make delivery-review self-evolution survive the hardened runtime

Browse Source 
Approving (or sending feedback on) the delivery review card runs employee
self-evolution as company work items, but the finalizer required the
turn's FINAL chat text to be bare JSON. The hardened native runtime
appends a verification status line to every final text and the manager
dispatch guard displaces the final message with a justification, so every
reflection died with invalid_self_evolution_json even when the model
produced valid patches on all three attempts, and the FAILED items
polluted the delivered run's terminal verdict.

- Add a submit_self_evolution_patches tool as the authoritative result
  channel (exposed only on self-evolution work items, approval-exempt).
  The text parser becomes a fallback that scans fenced blocks and
  balanced JSON objects, and retry feedback now carries the concrete
  parse failure plus the tool instruction.
- Settle abandoned reflections as CANCELLED (self_evolution_abandoned)
  and exclude kind=self_evolution from run-lifecycle settlement so an
  opt-in reflection can never dirty a delivered run.
- Claim the review card with a consuming CAS before spawning (duplicate
  approve/feedback replies answer idempotently instead of re-entering),
  bound the reflection run with a 40-minute deadline that cancels
  leftover self-evolution items, and hand the claim back to pending when
  the consumed run crashes mid-flight.

Verified live on real runs: the unfixed code failed the approve path in
90s with zero patches recorded; with the fix both the approve and the
feedback paths recorded patches end-to-end (CEO->COO and CEO->CMO
cascades, zero retries, human feedback reflected in patch content).
tests/: 1924 passed.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
LZH-YS1998
2026-07-29 00:36:53 +08:00
parent d14f3920e0
commit 6c5acbf10e
6 changed files with 719 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
opc/core/company_tools.py
+11
View File
@@ -58,12 +58,14 @@ DEBUG_ADMIN_TOOL_NAMES: tuple[str, ...] = (
MEETING_RESPONSE_TOOL_NAMES: tuple[str, ...] = ("respond_meeting",)
HUMAN_REVIEW_TOOL_NAMES: tuple[str, ...] = ("close_human_review",)
SELF_EVOLUTION_TOOL_NAMES: tuple[str, ...] = ("submit_self_evolution_patches",)
COMPANY_COLLABORATION_TOOL_NAMES: tuple[str, ...] = (
*COORDINATOR_DEFAULT_TOOL_NAMES,
*MEETING_RESPONSE_TOOL_NAMES,
*HUMAN_REVIEW_TOOL_NAMES,
*SELF_EVOLUTION_TOOL_NAMES,
)
COMPANY_DEBUG_TOOL_NAMES: tuple[str, ...] = DEBUG_ADMIN_TOOL_NAMES
@@ -166,6 +168,13 @@ def _is_execute_or_review_work_item(task: object | None) -> bool:
return turn_type in {"execute", "review"}
def is_self_evolution_work_item(task: object | None) -> bool:
metadata = _task_metadata(task)
if _work_item_turn_type(metadata) == "self_evolution":
return True
return bool(metadata.get("self_evolution_work_item", False))
def _has_active_meeting(task: object | None, runtime_state: dict[str, Any]) -> bool:
metadata = _task_metadata(task)
peer_wait = dict(metadata.get("peer_wait", {}) or {})
@@ -306,6 +315,8 @@ def resolve_allowed_collaboration_tools(
allowed.update(MEETING_RESPONSE_TOOL_NAMES)
if _human_review_close_allowed(task, state):
allowed.update(HUMAN_REVIEW_TOOL_NAMES)
if is_self_evolution_work_item(task):
allowed.update(SELF_EVOLUTION_TOOL_NAMES)
return allowed