Repository navigation
Fix ISS-013: add lightweight per-skill-run telemetry log - #101
Merged
Merged
Conversation
New py_mono/skill/telemetry.py: log_skill_run()/read_skill_runs() append/read a flat JSON-lines log (skill, provider, model, duration_ms, success, timestamp) at telemetry/skill_runs.jsonl. A write failure logs a warning and never breaks skill execution. Hooked into run_skill_safe (py_mono/skill/approval.py), the single existing chokepoint every skill execution already passes through for approval/tool-access enforcement - times the skill.run() call and logs exactly one record via try/finally, for both successful and failed runs. Provider/model come from context.session_manager.get_active_provider(), falling back to <unknown> when no session manager is present. Minimal version only, as scoped: Milestone 6's model/task fitness check (ISS-014) is the immediate consumer; Milestone 7's failure-driven evolution will extend this same log rather than building a second one. telemetry/ added to .gitignore, matching the existing workspace//dynamic_tools/ pattern. Adds tests/test_skill_telemetry.py (5 tests) and 3 new tests in tests/test_skill_approval.py. See specs/011-add-skill-run-telemetry/.
3 tasks done
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
py_mono/skill/telemetry.py:log_skill_run/read_skill_runsappend/read a flat JSON-lines log (skill,provider,model,duration_ms,success,timestamp) attelemetry/skill_runs.jsonl. Write failures are logged and swallowed, never breaking skill execution.run_skill_safe(py_mono/skill/approval.py) — the single existing chokepoint every skill execution already passes through — viatry/finally, so both successful and failed runs are logged.telemetry/added to.gitignore, matching the existingworkspace//dynamic_tools/pattern (operational data, not source).docs/ROADMAP_PLAN.md:ISS-014(model/task fitness check) is the immediate consumer; Milestone 7 extends this same log rather than building a second one.ISS-013indocs/ISSUES.md; SDD trail inspecs/011-add-skill-run-telemetry/.Test plan
pytest tests/test_skill_telemetry.py tests/test_skill_approval.py -v— 12 passedISS-005failures tracked/fixed separately in Fix ISS-005: root-cause three pre-existing test failures #96, unrelated to this change)python -m compileall -q py_mono skills— clean