Maniacs_Mansion/MealQuest
11
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Skill harness interface and repair retry #53

Merged
approver_agent merged 2 commits from task/skill-interface-pipeline_38e7bf98-f1d1-4301-b73b-7ec4b51e8b68 into feature/d4a8ed83-9cee-459c-aca3-efd1ccf17ecd-ai-harness 2026-10-05 07:55:34 -04:00
Conversation 2 Commits 2 Files Changed 3
+432
2 Commits
Author SHA1 Message Date
dev_agentandClaude Opus 5.5 7be4879f6d Validate post-processed skill output and quote failed JSON in repair
CI / ci (push) Successful in 1m33s
Details
CI / ci (pull_request) Successful in 1m32s
Details 
The harness now validates a skill's output again after PostProcess, so
output that post-processing makes invalid (e.g. a whitespace-only echo
trimmed to empty) enters the single repair turn instead of returning as
a success. The repair turn now quotes Response.JSON as the previous
assistant reply whenever structured output was returned, falling back to
Response.Text only when there is none.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-05 07:49:23 -04:00
dev_agentandClaude Opus 5.5 9ed5cb1192 Add skill harness with one repair retry
CI / ci (push) Successful in 1m31s
Details
CI / ci (pull_request) Successful in 1m30s
Details
Independent review Changes required — 2 medium finding(s) (#53)
Details 
internal/ai/harness defines the generic Skill interface (Name, Version,
Render, Schema, Validate, PostProcess) and Run, which renders the prompt,
calls Provider.Generate with the skill's schema and the household
temperature, strictly decodes and validates the reply, and on failure sends
exactly one repair turn quoting the problems. A second failure returns a
*BadOutputError matching llm.ErrBadOutput with both problem lists. Provider
errors other than ErrBadOutput pass through unchanged.

Maestro task 38e7bf98-f1d1-4301-b73b-7ec4b51e8b68.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-04 17:08:52 -04:00