feat(agent): stabilize autonomous loop with stateful verify/replan an…#1
Merged
Merged
Conversation
…d runtime reliability improvements
|
@mustafahk27 is attempting to deploy a commit to the BurhanCantCode's projects Team on Vercel. A member of the Team first needs to authorize it. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Replaced one-shot flow with looped execution: observe -> plan (1–3 actions) -> execute -> verify -> retry/replan.
Added loop context/state to planner-verifier contracts (current_state, next_required_state, verify status/reason, recent action outcomes).
Added goal_state + planner_note to plans and wired verifier corrective_actions into retry flow.
Added no-progress/repeated-fingerprint blocking and clearer terminal reasons (blocked, budget_exhausted, etc.).
Improved telemetry/eventing with cycle/replan/state/fingerprint fields.
Added runtime hardening: sidecar lifecycle stability, request timeout tuning, diagnostics visibility, and STT confidence gating.
Updated adapter/planner validation and tests for loop/schema behaviour.