feat: notifications, milestone-aware resume, CLI wiring#32
Open
feat: notifications, milestone-aware resume, CLI wiring#32
Conversation
…rompt hardening
Sprint 1 of enforcement hardening. Adds foundational validation infrastructure:
- checkpoint.py: string ID support (int|str), load_checkpoint_by_name(),
load_all_checkpoints() keeps numeric-only to protect downstream consumers
- queue.py: baseline_cmd attribute with load/save roundtrip
- supervisor.py: validation constants, _validate_evidence_verdicts(),
_validate_par_evidence() with type guard, _validate_sprint_summary(),
preflight .worktrees gitignore check, build_prompt() frontend injection
- supervisor-sprint-prompt.md: PAR evidence instructions, pre-verified
baseline section, {frontend_instructions} placeholder
20 new tests (152 total). Validators are foundations — integration into
_attempt_sprint() is Sprint 2 scope.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…idation hardening Sprint 2 of enforcement hardening. Integrates Sprint 1 validators into execution: - Baseline test gate: _resolve_baseline_cmd() with priority chain, run_baseline_tests(), integrated in execute_sprint() inside try block - PAR validation: separate par_retries counter (not shared with Claude retries), max 2 PAR retries before mark_failed - Summary validation: invalid summaries treated as json_parse_error - PR verification: 3 retries with 5s delay, empty pr_url = failure - Milestone writes: baseline_passed, implemented, par_validated, pr_created in checkpoints (preserved in failure paths too) - Parallel safety: queue reload after execute_parallel, checkpoint on worker exception - Prompt rebuilt each iteration (no unbounded growth) - Attempt counter independent of retry counter for log filenames 24 new tests (176 total). Review fixes applied: stale queue.save, log counter, prompt growth, parallel checkpoint, empty pr_url, milestones. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sprint 3 of enforcement hardening. Adds notification infrastructure and crash recovery improvements: - 5 new notification methods: holistic review start/complete, par_validation_failed, baseline_failed, resume_recovery - Notification wiring in _attempt_sprint() and execute_sprint() - _check_pr_exists() helper with robust JSON parsing - Milestone-aware resume(): reads checkpoints, saves resume_context, detects holistic review in_progress, notifies recovery stats - CLI: cmd_resume passes notifier to resume() - Parallel safety verified from Sprint 2 (no changes needed) 9 new tests (185 total). Review fix: _check_pr_exists JSON parsing hardened against whitespace edge cases. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This was referenced Mar 23, 2026
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
Sprint 3/6 of Supervisor Enforcement Hardening.
_attempt_sprint()andexecute_sprint()_check_pr_exists()helper with robust JSON parsingresume()with checkpoint reading andresume_contextcmd_resumepasses notifierDepends on: PR #30 (Sprint 2)
Tests: 185 total (9 new), all passing.
PAR:
_check_pr_existsJSON parsing hardenedTest plan
_check_pr_existsrobust JSON handling🤖 Generated with Claude Code