Return wrapped {prs, pagination} from gitea_list_prs with has_more,
inventory_complete, and page traversal via api_fetch_page. Route
gitea_review_pr inventory through gitea_list_prs so trust gates can
prove pagination finality. Add assess_list_prs_pagination_proof verifier.
Closes#340
Introduce assess_mutation_ledger_report so reviewer final reports cannot
claim no file edits when the action log records performed mutations.
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.
Workflow reports included the authenticated user's personal email even
when username/profile identity was sufficient (observed: 'Identity:
jcwalker3 / [email protected]' in a reconciliation handoff).
Add format_identity_summary() producing the canonical no-email identity
line ('<username> / <profile>' with optional role/remote, reducing an
email passed in the username slot to its local part), and
assess_email_disclosure() flagging personal email addresses in report
text unless the report itself justifies the disclosure (tool proof,
explicit request, or identity disambiguation).
Tests cover no-email summaries for author and reviewer identities,
role/remote suffixes, email-in-username reduction, clean reports,
single and multiple unjustified disclosures, and justified
disambiguation.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Resolve _GUIDE_RULES conflict by keeping both operator guide keys:
shell_spawn_hard_stop (#258, landed on master via PR #281) and
subagent_delegation (#266, this branch).
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Introduce assess_request_changes_approval_proof in review_proofs.py so
review workflows can fail closed when approving an unchanged head after a
prior REQUEST_CHANGES unless explicit override proof is provided.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Adds subagent_gate.py following the author_proofs/review_proofs pure-policy
pattern:
- assess_subagent_delegation: deterministic write tasks (issue claim,
branch creation, code edits, commits, PR creation, review, merge,
cleanup) are blocked for subagents unless explicitly allowed with a
recorded justification and the full inherited gate context (issue lock,
branch/worktree path, identity/profile, allowed tool class, command
deny list, validation ledger requirement, final report schema);
read-only delegation stays allowed; unknown task types fail closed.
- validate_subagent_report: subagent output is accepted only when it
carries the same proof fields as a parent workflow final report.
- Operator guide: new subagent_delegation rule in _GUIDE_RULES so MCP
clients discover the policy.
- tests/test_subagent_gate.py: 13 tests covering blocked write
delegation, justification requirement, missing/blank inherited
context, allowed read-only delegation, unknown tasks, and invalid
subagent final reports.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Introduce validation_ledger with command ledger format, full-suite claim
checks, and structured final-report verification so sessions cannot
overclaim validation or misreport review/merge state.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
test_skip_scan_walk_root_skips_sibling_worktrees_only derived its
fixture paths from __file__, so the branches/ sibling-worktree skip
assertion only held when the suite ran from a branches/<slug> worktree
whose orchestration checkout has a real branches/ directory —
skip_python_scan_walk_root skips a branches/ walk root only when
<project_root>/branches exists on disk. From the main checkout or any
plain clone the test failed with 'AssertionError: False is not true'.
Build the <main>/branches/<worktree> layout in a TemporaryDirectory and
assert against those paths instead. All four behavioural assertions are
preserved and no production code changes.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Allow issue lock from base-equivalent branches/ worktrees instead of
requiring the literal master/main branch name. Runtime preflight and
mark_issue/lock_issue now inspect the declared active task workspace so
dirty control-checkout state does not block clean task worktrees.
Closes#275
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Allow issue lock from base-equivalent branches/ worktrees instead of
requiring the literal master/main branch name. Runtime preflight and
mark_issue/lock_issue now inspect the declared active task workspace so
dirty control-checkout state does not block clean task worktrees.
Closes#275
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Document MCP-native gitea_commit_files as the only approved commit path when
gitea.repo.commit is allowed; ban WebFetch, Playwright, and manual base64
workarounds in runbooks and safety model. Add doc tests.
Closes#260.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Add runbook section, root-level .gitignore patterns, and detection helper
for _encode_/_emit_/_inline_ throwaway scripts. Surface non-blocking
warnings from assess_preflight_status and gitea_lock_issue.
Closes#261
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Add runbook guidance for deleting throwaway _encode/_emit/_inline commit
helpers after MCP commit attempts, ignore those patterns in .gitignore,
and cross-link the worktree-cleanup template.
Closes#261.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Add commit_files and gitea_commit_files resolver entries for
gitea.repo.commit, align gitea_commit_files tool gates with other
issue-write mutations, and add regression tests for author allow,
reviewer deny, preflight order, and resolver/tool alignment.
Refs #262
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
The forbidden-mutation loop in assess_issue_filing_mutation_scope never
appended reasons; align aggregation with issue-selection handoff checks.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
gitea_get_runtime_context now reports per-task allowed_in_current_session
flags, matching configured profiles, and aggregate session_capabilities so
LLMs can determine author/comment/review/merge ability without guessing
launcher profile config.
Refs #139
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Require mutations only from branches/ worktrees after proving project
root, cwd, branch, stable main-checkout branch, and session worktree
path. Surface in portable skill, runbooks, wiki, operator guide, and
start-issue template.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Match git conflict markers on whole lines only so decorative equals
borders in mcp_discoverability.py no longer false-positive. Scan
session worktrees under branches/ without skipping the entire tree
when the worktree path contains "branches".
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Require lease verification (open PRs, branches, worktrees, leases,
merged completion) before any issue or PR work. Surface the rule in
the portable skill, Gitea runbooks, operator guide, and start-issue
template; add doc-contract tests.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Document that build triggers live on the gated jenkins-write-mcp server,
not the read-only jenkins-mcp surface. Add registration and safety-model
cross-links plus doc tests that fail if trigger tools reappear on the read
boundary.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Update TestPreflightVerification for #252 delta-based preflight checks
on the rebased #228 branch.
Refs #228
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Pre-flight order tracking now compares porcelain baselines captured at
process start, whoami, and capability resolution instead of treating any
shared-worktree dirt as a sticky violation. Fresh gitea_whoami re-evaluates
and clears violations; runtime context reports preflight_block_reasons when
mutations would fail.
Refs #252
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Operators can supply an active PR backlog for one repo while agents
inventory another and falsely report trusted_empty. reconcile_queue_target
locks the target repo from operator context/backlog before list_prs runs;
pr_inventory_trust_gate blocks target_repo_mismatch and unresolved locks.
assess_reviewer_queue_inventory wires the lock into the canonical path.
Tests cover Gitea-Tools backlog vs mcp-control-plane inventory mismatch,
ambiguous dual-repo context, conflicting directive vs backlog, and final-
report field requirements.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Update test_reviewer_profile_can_proceed_from_inventory_to_review_gates
to return APPROVED state on POST and include GET /reviews verification
responses required by #244 review submission gates.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Gitea expects review event APPROVED, not APPROVE; the wrong event left
submissions as PENDING drafts. Verify terminal verdicts after submit,
submit pending drafts when needed, and block merge when approval_visible
is false.
gitea_lock_issue and gitea_create_pr accept worktree_path so lock
preconditions validate the caller's scratch clone instead of the shared
MCP server CWD. Lock records store the validated path; PR creation fails
closed when the declared path does not match.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
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]>
Replace blocklist-based git mutation detection with fail-closed allowlist
semantics: any git command not matching the readonly set is forbidden.
Catches checkout HEAD --, checkout ., git switch variants, and uncommon
stash subcommands that bypassed the old regex.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Issues already represented by open PRs must not be selected for fresh work
unless the operator explicitly requests continuation. Adds classification,
continuation report proofs (old/new head SHA, PR author, branch), contradictory
no-PR claim detection, and edited-PR inventory coverage checks.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Re-introduce assess_empty_queue_report and parse_trust_gate_status_from_report
dropped when #208 was reverted from master. Wire build_final_report grading,
inventory handoff trust-gate fields, and tests so capability_stop_terminal
imports resolve while issue-lock proof enforcement remains.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Add sync_from_capability_result() so reviewer terminal mode is
operation-scoped: a later allowed author capability resolution clears
stale denial state and unblocks read-only tools like gitea_list_prs.
Error messages now name the denied task and explain how to clear stale
state. Inline trust-gate parsing fixes broken imports in
assess_capability_stop_report on master.
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]>
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]>
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]>
Bootstrap repo-tracked wiki pages (10 required pages), the operator-
confirmed sync script, PR template publication gate, and safety tests so
Gitea-Tools can publish to the live Gitea Wiki per issue #224.
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Fix 8 suite failures triggered when GITEA_MCP_CONFIG/GITEA_MCP_PROFILE
are set in the operator environment.
- TestGetAuthHeader: clear MCP config env and DYNAMIC_CONFIGS in setUp
- TestCreatePR/TestIssueLocking: add CREATE_PR_ENV author fixture and
patch reviewer-stop gate so tests reach intended code paths
Closes#227
sysadmin
