Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hint delivery, muting, and lifetime counters were spread across the supervisor's invocation record and individual trigger handlers. Collect that bookkeeping in a small per-agent
RuntimeHintsobject, with shared enqueue and drain operations.The existing triggers still determine when and what to suggest. Hint text, public APIs, limits, and prompt instructions are unchanged. Muted Bash hints do not spend their budgets; hints muted after enqueue are discarded on delivery without refunding their budgets. Environment-prefix counts remain per variable, and the redundant already-hinted set is removed. Quote-error detection and its distinct per-prompt attempt limit stay in the engine.
Validation: all 301 tests pass with
uv run pytest tests/. Focused coverage checks budget exhaustion, mute/unmute behavior, pending delivery, independent agent state, and environment-prefix thresholds. Ruff lint/format checks andgit diff --checkpass. No live-model evaluation was run.