Add premerge_baseline_proof.py distinguishing four validation outcomes
(clean pass / current-master failure reproduced / pre-merge baseline-proven
failure / unresolved regression risk). A non-zero exit may only be labeled
"baseline"/"pre-existing" with pre-merge proof: the failure reproduced on the
PR's pre-merge base commit, or a documented known-failure record predating the
PR. Current-master (post-merge) reproduction is explicitly rejected as
sufficient baseline proof.
- premerge_baseline_proof.py: assess_premerge_baseline_proof + labels
- final_report_validator.py: reviewer.premerge_baseline_proof rule on
review_pr and reconcile_already_landed tasks
- skills/llm-project-workflow/templates/review-pr.md: baseline proof section
requiring base commit, tested commit, command, exit status, failure signature
- tests/test_premerge_baseline_proof.py: reject current-master-only proof,
accept pre-merge base proof and documented known-failure records
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Bare remote=prgs resolved to the hardcoded REMOTES default
Scaled-Tech-Consulting/Timesheet instead of the Gitea-Tools repository
the local git remote points at, causing false 404s and risking mutation
of a different repository.
Add remote_repo_guard.assess_remote_repo_match (pure) + formatter, wired
into gitea_mcp_server._resolve so every read/lookup/mutation tool fails
closed when the MCP-resolved org/repo disagrees with the local git remote
URL and the caller did not pass explicit org/repo. The guard is
best-effort: it skips when both org and repo are explicit, when the local
remote URL is unavailable, and is bypassed under pytest unless
GITEA_FORCE_REMOTE_REPO_CHECK is set.
Add tests/test_remote_repo_guard.py (pure-function cases + server wiring
proving a lookup tool cannot silently query a different repository), and
update author/reviewer/merger handoff templates to require explicit
remote/org/repo.
Closes#530
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Define CTH comment types, base template, parser/validator helpers, protocol
documentation with examples, and workflow/runbook/prompt updates so agents
discover and post authoritative thread handoffs before acting.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Consolidate all four canonical workflow files and router SKILL.md:
- review-merge-pr.md (from #334 canonical prompt)
- reconcile-landed-pr.md (reconciliation gates + handoff schema)
- create-issue.md (canonical issue-creation prompt)
- work-issue.md (canonical author/coder prompt)
SKILL.md is now a short router with mode isolation and universal rules.
Adds final-report schemas for all modes and 13 doc-contract tests.
Supersedes partial split work in PR #335; full #333 acceptance in one PR.
Use sys.executable with optional GITEA_TOOLS_TEST_PYTHON override instead of
hard-coded venv/bin/python. Add subprocess timeouts/teardown and skip when no
interpreter is available. Note scratch-clone norm in review-pr template.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Add assess_empty_queue_report to block empty-queue claims without
pr_inventory_trust_gate.status == trusted_empty, reject weak merge-commit
corroboration, extend inventory handoff fields, and wire the gate into
build_final_report and capability-stop terminal validation.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Run pr_inventory_trust_gate on empty gitea_review_pr inventory results,
add assess_reviewer_queue_inventory for multi-repo completeness checks,
and require trusted_empty before empty-queue claims in reports/templates.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Add reviewer_worktree proofs that block stash/reset/checkout -- cleanup of
unrelated local files, require scratch worktree reporting when the main tree
is dirty outside PR scope, and integrate the gate into final report grading
and Controller Handoff review fields.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Extends review_proofs.py with the four #179 proofs, the successor set to
the #173 checkout/inventory proofs:
- assess_capability_evidence: a capability claim (review_pr, merge_pr, ...)
counts only with exact evidence citing gitea_resolve_task_capability
output or equivalent runtime context; no claims at all fails closed.
- assess_sweep_evidence: secret/provenance sweeps must state the exact
command/script/pattern/named method, the scope scanned, and a boolean
result; vague summaries are downgraded and a missing sweep fails closed.
- assess_live_state_recheck: an explicit pre-mutation recheck must prove
the PR is still open, the live head equals the pinned head (full
40-hex), the base branch is unchanged, and blocking review state was
checked and absent; not performing it fails closed.
- assess_role_boundary: a reviewer run using an author namespace (or vice
versa) is clean only with an explicit justification; unreported
namespace usage fails closed.
build_final_report now takes the four proofs as keyword arguments: any
missing or failed proof downgrades the grade, merge_allowed additionally
requires the proven live-state recheck, and a merge performed without it
is a blocked violation. Existing #173 semantics are unchanged otherwise;
gates only get stricter.
tests/test_review_proofs.py adds 29 tests covering the issue's harness
assertions: capability claims without evidence downgraded, vague sweeps
downgraded, missing/stale live-state recheck downgrades and blocks merge
(violation when a merge is claimed anyway), unjustified author-namespace
use downgraded, and the #173 positive baseline preserved.
SKILL.md sections F/G and the review-pr/merge-pr templates now require the
capability evidence, exact sweep, pre-verdict and pre-merge live-state
rechecks, and reviewer-namespace discipline.
Closes#179
Co-Authored-By: Claude Fable 5 <[email protected]>
- Upgrade SKILL.md §K compact format to the issue #182 canonical field set
(Task/Repo/Role/Identity/Issue-PR/Branch-SHA/Files/Validation/Mutations/
Current status/Blockers/Next/Safety) plus role-specific field lists for
review/merge, author, and queue/inventory tasks.
- Point the review-pr, merge-pr, and start-issue template handoff lines at
the exactly-titled Controller Handoff section with their role fields.
- Add review_proofs.assess_controller_handoff(): reports without the exact
section are 'missing' (downgraded), present-but-partial are 'incomplete'
with the absent fields listed, and role extras are enforced per role.
- Add TestControllerHandoff (8 tests) including a SKILL.md doc-contract
test so the documented requirement cannot silently rot.
The handoff supplements the full report; full-report validation rules are
unchanged.
Closes#182
Co-Authored-By: Claude Fable 5 <[email protected]>
Adds review_proofs.py with pure, fail-closed helpers for the reviewer-side
blind queue workflow:
- verify_pinned_head_checkout: proves HEAD == pinned PR head (full 40-hex,
no prefix matches) and diff base == PR base; any mismatch blocks
review/merge.
- assess_inventory_completeness: exhaustive "only PRs found" claims require
every configured repo listed with stated filters, proven pagination, and
reported open-PR totals.
- assess_validation_report: validation results are unclaimable unless the
exact command was stated and its output read; missing pass/fail/skip
counts, unjustified ignored paths, or unexplained deviation from the
canonical command downgrade the report to weak.
- assess_self_review_contamination: contamination must be evidence-backed;
bare same-session claims (either way) yield "unknown" with a
choose-another-PR-or-stop action, never an assumed verdict.
- build_final_report: distinguishes identity eligibility, author/reviewer
distinctness, session contamination, validation-on-pinned-head, merge,
and issue verification; grades "A" only when every proof is present,
downgrades otherwise, and marks a merge without allowing proofs as a
blocked violation.
tests/test_review_proofs.py covers all seven harness assertions from the
issue (unchecked-out pinned head blocks merge; multi-repo inventory;
pagination; missing counts flagged weak; evidence-required contamination;
unread output cannot claim validation passed; ignored paths need
justification).
SKILL.md section F and templates/review-pr.md now require the checkout,
inventory, validation-evidence, and contamination proofs and the
distinguished final report. No review/merge safety gate is weakened.
Closes#173
Co-Authored-By: Claude Fable 5 <[email protected]>
Make the nine-line compact Controller Handoff the default end-of-task
format; reserve the long Controller Handoff Summary for high-risk/complex
tasks (merge/tag/release, failed validation, blocked gates, secrets/prod,
complicated owner decisions, cross-repo state, or explicit owner request).
Compact form is for controller-LLM readability, safety confirmations are
never omitted, and PR bodies still carry full review detail.
Updates SKILL.md §K, llm-workflow-runbooks.md, and the start-issue /
review-pr templates. Documentation only.
Refs #101. Closes#108.
Co-Authored-By: Claude Fable 5 <[email protected]>
Extract the project's operating rules into a reusable, project-agnostic skill
so any repo can adopt the same safe LLM workflow.
- skills/llm-project-workflow/SKILL.md: issue-first; isolated branch worktrees
(main checkout = orchestration only); distinct author/reviewer identities and
profile safety (secrets by reference only; stop if authenticated user == PR
author); branch naming; start/review/merge/cleanup workflows; fail-closed
cases; recovery patterns; and an "Adapting to a project" table for the
forge-specific names.
- templates/: copy/paste prompts for start-issue, review-pr, merge-pr,
recover-bad-state, worktree-cleanup.
- Link the skill from README.md and docs/llm-workflow-runbooks.md (the runbook
is framed as the Gitea-specific application of the portable skill).
Docs-only; no code, no secrets, safe placeholder examples only. No change to
MCP runtime, Gitea API, credential storage, or worktree helpers.
Checks: full suite 287 passed / 0 failures; git diff --check clean; secret scan
of skills/ clean.
Closes#46. Refs #38, #39.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
sysadmin
