Fix #71: complete the .agent issue-layer mirror; add a parity guard - #118
Open
laird wants to merge 26 commits into
Open
Fix #71: complete the .agent issue-layer mirror; add a parity guard#118laird wants to merge 26 commits into
laird wants to merge 26 commits into
Conversation
…g to N-clean; scope + exercise preflight; swarm cadence)
Design spec for adding a human-gated planning capability to the manager session (brainstorm → spec → critical review → decompose to stories → existing fleet implements), plus renaming /fix→/dev and /fix-loop→/dev-loop with aliases. Reuses existing skills and the decomposed/subtask convention; adds two backlog-aware behaviors to the manager loop. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Critical-design-review round 1 approved the planning-pipeline spec as-is: 0 literal-wrongness findings, 0 forced decisions. Empirically confirmed the two load-bearing hand-off facts (subtask is claimable; decomposed parents are excluded from claiming). Recorded the CDR approval in the spec status and carried the three CIR-deferred items forward as notes B8/B9 (+ existing B5). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…eview-1 to autocoder-planning-pipeline-implementation-plan
Tracks the 2026-07-28 handoff documenting the /fix→/dev rename and peters-toolkit:bugfix integration, plus the still-unaddressed critical review of the planning-pipeline implementation plan. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…aim lock until a terminal outcome
…ver reached the ship branch
…ini/droid markers, stale comments)
…rs.sh (GraphQL replay lands new files 644)
… exclusion, drift repair), marketplace to 3.32.0
…ound/improved/learned per round, verdict chapter)
…e v2 removal Atlassian removed POST /rest/api/2/search from Jira Cloud (HTTP 410, CHANGE-2046). list and any-claimable now use POST /rest/api/3/search/jql with an explicit fields list, nextPageToken pagination (no startAt), and existence-of-first-page instead of the removed total for any-claimable. Issue lifecycle endpoints stay on v2 (not removed; plain-string bodies). The fake serves the new contract, enforces a settable page cap to exercise the token loop, and returns 410 on v2 search so regressions cannot pass. Live verification against real Jira Cloud pending by coordinator.
…text Live smoke showed /rest/api/3/search/jql returns description as an ADF document object, not v2's plain string. The list reshape now walks ADF content nodes collecting text (paragraphs joined with newlines; tolerates null, plain strings, malformed nodes), so body stays a plain string for all consumers. v2 CRUD read paths are untouched (still plain strings). The fake now serves ADF descriptions from v3 search to pin the contract.
…mp autocoder 4.10.1 / marketplace 3.32.1
…-smoke-test.sh; live validation pending an ADO sandbox)
…gents The SKILL.md had no model guidance. Top-level coordinator (scope/grade/fix decisions) uses the deep model; subagents and swarm workers use the balanced model. Mirrors the autocoder manager/worker tier pattern. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
… model selection (#110) * feat(autocoder): add model-config startup confirmation and env-var-driven model selection Autocoder agents now resolve model tiers from env vars → .autocoder.json → built-in defaults (claude-opus-5 / claude-sonnet-5 / claude-haiku-4-5 on Claude Code; gemini-2.5-pro / gemini-2.0-flash on Antigravity). On first run with no model config found, the agent presents the defaults and asks the user to confirm or override before proceeding. The confirmed models are exported as MANAGER_MODEL / WORKER_MODEL / FAST_MODEL and referenced in every Task tool call in the workflow so agents actually use them. Also adds skills/autocoder/references/model-config.md documenting the tier system and how to persist overrides via .autocoder.json. Parallel maintenance: plugins/autocoder/commands/fix.md ↔ .agent/workflows/fix.md Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore: bump autocoder to 4.11.0, marketplace to 3.33.0 Reflects model-config startup confirmation and env-var-driven model selection added in the previous commit. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
#112) Switch fix.md and model-config.md from full API model IDs (claude-opus-5) to platform tier shorthand (opus/sonnet/haiku for Claude Code, pro/flash for Gemini). Agents inherit credentials from the running session — no separate API keys needed. Rename skills/harden → skills/improve to reflect the general improvement and validation loop, not just security hardening. Bump autocoder 4.11.0 → 4.12.0, marketplace 3.33.0 → 3.34.0. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- test_issues_gh_search.sh (11 failures): BASH_ENV=/home/laird/.bashenv prepends ~/bin to PATH on every bash invocation, putting the real gh before the test stub. Fix: pass BASH_ENV="" when invoking the backend. - test_issue_source_lib.sh (1 failure): bash reverts VAR=val assignments on shell-function calls after the function returns, so the previously- exported ISSUE_DIR_PATH from the CLI-dir test step was restored instead of the function's new value. Fix: export explicitly before the call. - test_worker_launch_lib.sh (1 failure): Gemini workers should use the /fix-loop interactive command (matching .agent/workflows/fix-loop.md), not a non-existent gemini-fix-loop.sh shell script. Fix: align worker-launch-lib.sh with the test expectation. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
#96) restart-worker.sh killed the hung worker but never relaunched it, leaving the pane at a bare shell while still printing "✅ Worker restarted". Root cause: callers derive AGENTS_REPO_ROOT as SCRIPT_DIR/../../.., which is only correct for a repo checkout. An installed plugin lives at cache/plugin-marketplace/autocoder/<version>/scripts, so that walk lands on the cache root; appending plugins/autocoder/scripts/claude-worker-loop.sh yields the hybrid path from the report — real in neither the cache nor marketplace layout. Changes: - worker-launch-lib.sh: resolve the loop script from the lib's own directory (WORKER_LAUNCH_LIB_DIR); both ship in the same scripts/ dir. Fail loudly with a non-zero return if it is missing instead of emitting an unusable path. - restart-worker.sh: after sending WORKER_CMD, capture the pane and exit non-zero if it reports "No such file or directory"/"command not found", so a killed-but-not-restarted worker can no longer be reported as success. - test_worker_launch_lib.sh: assert the emitted loop path EXISTS on disk when repo_root does not follow the checkout layout, and that it is not derived from repo_root. Verified red before the fix with exactly the reported path shape. Verification: 17/17 shell unit tests pass; bash -n + py_compile clean. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
CLAUDE.md declares plugins/ <-> .agent/ parity CRITICAL, but nothing
enforced it and the issue layer had drifted badly:
- .agent/scripts/ was missing issues-gh.sh and issue-source-lib.sh
entirely — the Antigravity side had no GitHub backend and no
issue-source resolution.
- .agent/scripts/issue-fns.sh was the pre-dispatcher version: it
inlined the GitHub backend and defined only 6 of the 9 contract
verbs. .agent/workflows/fix.md calls issue_claim, issue_release and
issue_any_claimable, so the Antigravity /fix exited 127 at its
preflight check on every run.
- issues-jira.sh still used POST /rest/api/2/search, removed from Jira
Cloud (HTTP 410, CHANGE-2046) and fixed on the plugins side by #100.
- issues-file.py and issue-config.sh trailed by 438 and 4 lines.
These files are shared infrastructure with no platform-specific content,
so the mirror is now byte-identical to plugins/autocoder/scripts/ (same
blob hashes, same modes) for all seven: issue-fns.sh, issue-config.sh,
issues-file.py, issues-gh.sh, issues-jira.sh, issues-ado.sh and
issue-source-lib.sh.
tests/test_agent_mirror_parity.sh is the guard that stops this
recurring. It asserts presence, byte-identity, that all 9 contract verbs
resolve on BOTH sides, and that `--state blocked` returns JSON rather
than being forwarded to `gh issue list` (which rejects it). It sources
each lib inside a throwaway repo with a poisoned gh on PATH, so a
resolution regression cannot reach the real tracker. Against master it
failed 10 of 19 assertions; it now passes 19/19.
Known remaining gap, left for #88: .agent/scripts/start-parallel-agents.sh
still has no issue-source wiring at all. It now has issue-source-lib.sh
available to wire against.
Verified: all 18 tests/test_*.sh suites pass; bash -n over both script
dirs; py_compile on both issues-file.py copies.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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.
Ports the still-relevant part of the stale #74 onto current
master. #74 itselfbranched before the Jira/ADO backends,
verify-shipped.sh,claimed-issue-numbers.sh,the
harden→improverename andmodel-config.mdlanded, so merging it woulddelete ~4,352 lines of current master. This PR takes only the part that is still
a live defect.
The defect
CLAUDE.mddeclaresplugins/↔.agent/parity CRITICAL, but nothing enforcedit and the issue layer had drifted badly on
master:issues-gh.sh.agent/— no GitHub backend on the Antigravity sideissue-source-lib.sh.agent/— no issue-source resolutionissue-fns.shissues-jira.shissues-file.pyissue-config.shThe missing verbs are the user-visible failure:
.agent/workflows/fix.mdcallsissue_claim,issue_releaseandissue_any_claimable, so the Antigravity/fixexited 127 at its preflight check on every run. The staleissues-jira.shstill usedPOST /rest/api/2/search, which Atlassian removedfrom Jira Cloud (HTTP 410, CHANGE-2046) and which #100 fixed on the plugins side
only.
The fix
These seven files are shared infrastructure with no platform-specific content —
the
.agent/copies were simply older. They are now byte-identical toplugins/autocoder/scripts/(verified by matching git blob hashes and filemodes):
issue-fns.sh,issue-config.sh,issues-file.py,issues-gh.sh,issues-jira.sh,issues-ado.sh,issue-source-lib.sh.The guard
tests/test_agent_mirror_parity.shis what stops this recurring. It asserts:--state blockedreturns JSON rather than being forwarded togh issue list,which rejects it.
Libraries are sourced inside a throwaway repo with a poisoned
ghonPATH, soa resolution regression cannot reach the real tracker; a tripwire assertion fails
the run if anything shells out to the real
gh.Against
masterit fails 10 of 19 assertions. On this branch it passes 19/19.Known remaining gap
.agent/scripts/start-parallel-agents.shstill has no issue-source wiring at all(zero references to
resolve_effective_issue_source,ISSUE_SOURCEorISSUE_DIR_PATH, vs. 9 on the plugins side). That is issue #88 and a separate,larger port — the two scripts differ structurally by ~233 lines. This PR
deliberately leaves it, but now makes
issue-source-lib.shavailable in themirror to wire against.
Verification
tests/test_agent_mirror_parity.sh— 19/19 pass (10 failures onmaster)tests/test_*.shsuites passbash -noverplugins/autocoder/scripts/*.shand.agent/scripts/*.shpy_compileon bothissues-file.pycopiesPython tests were not run —
pytestis not installed in this environment.Closes #71. Supersedes #74, which should be closed as stale.
🤖 Generated with Claude Code