Skip to content

ci: run checks for different-episode completion test - #1

Closed
hacktivistxt wants to merge 2 commits into
mainfrom
fix/supervisor-basis-id-feedback
Closed

hacktivistxt wants to merge 2 commits into
mainfrom
fix/supervisor-basis-id-feedback

Conversation

@hacktivistxt

Copy link
Copy Markdown
Owner

CI trigger on fork for the test-only change (mirrors upstream GreyDGL#571). Safe to close once green.

hacktivistxt and others added 2 commits October 29, 2026 09:21
When the Supervisor cited a basis observation whose 32-char hex ID it had
mistyped, the deterministic validator rejected it with only the bad ID, so
the blind retry mis-copied again and the run died on supervisor_contract
after 2 attempts (observed: a near-miss ID differing in 6 of 44 characters).

compile_plan now appends the closest valid observation IDs (difflib) plus the
full available set to both the task-basis and finish-basis errors. These are
fed back to the retry as validation_feedback, so it can copy the correct ID
instead of being told only that its citation is unknown. Adds a focused test
asserting the error names the near-miss's real observation ID.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Completion reuse of a valid same-task observation succeeds when the lease
and grounding trace share an episode. This adds the mirror case: the same
exact-quote DONE delta and reusable ObservationRecord, but with the lease
bound to a different trace_episode_id than the trace carries. The validator
refuses it with "evidence trace belongs to a different episode" before any
grounding is credited, so evidence captured in another episode cannot float
a completion.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant