Commit graph

771 commits

Author SHA1 Message Date
efe981f7bc
refactor(cleanup): simplify pass on the R-a diff
engine-compare imports the coordinator's title limit and trim instead
of a copy whose reason went with Arm B; the autonomy gate exports one
parser and its test runs in-process with two CLI runs; one import
scanner in lib-imports; the fenced-section walker shared from
tests/helpers/md-section.mjs instead of six copies; plan-gate hash
in-process; living-paths scans once; routing drops the orchestrator
filter whose files are gone; small leftovers removed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 13:31:30 +01:00
029e83117c
test(r8): move the live tests the move map missed
33 more tests of live behaviour from the deleted round files, each in
the test file named after its source and seen failing under a mutation
of that source (log in the project folder). Two stay dropped: one pinned
the removed gate states, one the old Phase 1.5 file comparison. The two
trekexecute.md sentences that still said /trekcontinue compares the two
prompt files now say it uses the project-folder file (line count kept).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 13:11:25 +01:00
8295601965
chore(cleanup): remove the June trials, orchestrator docs, dormant agent, caller-less code and the fix-round chain
R4-R7 of the cleanup list (decision 188): the June trial docs and
fixtures, the three orchestrator reference docs, the dormant
synthesis-agent, code with no caller (project-discovery, bash-normalize,
fidelity-diff, test-census, the next-session prompt validator, arm B and
the --workflow flag) and the fix-round chain. Living docs repointed; the
reasons for in-session orchestration and the all-opus pin are now written
in docs/architecture.md and docs/profiles.md.

New tests/lib/living-paths.test.mjs: living tracked text names only
plugin paths that exist (seen red with 22 dead pointers before this
commit). docs/T1-cc26-delegated-orchestration.md and
lib/review/gold-scorer.mjs stay until R-b: the frozen end-state registry
names them.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 12:51:54 +01:00
308b149e70
refactor(gates): the autonomy gate is the --gates flag parser
lib/util/autonomy-gate.mjs keeps only gatesValue + parseGatesArgs and the
CLI ({"ok":true,"gates":true|false}; exact usage error on a bad value;
the old --state/--event arguments are a usage error). The four commands
run 'autonomy-gate.mjs --gates [value]' and read gates. Prose (README,
operations, architecture, sdlc-playbook-gap) and the S24, gates-flag
and [#1] tests follow (R9).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 10:37:03 +01:00
651be3468b
test(r8): move the live tests out of the round files
R8 of cleanup R-a (plan .claude/projects/2026-11-07-cleanup-r-a, appendix A).
The live tests of the round files move into the test named after their
source; each moved test was seen red under a mutation of its source.
New: tests/lib/lib-imports.test.mjs, tests/lib/timing.test.mjs (from
timing-under-load). The [#1] --gates rule and shim-line pins move into
tests/lib/autonomy-gate.test.mjs.

Removed: the round test files (retterunde, retterunde-prose-pins,
trial-mechanical-fixes, trial2-fixes, trial2-minor, trial2-minor-prose-pins,
fix-round-4-5a-prose, fix-round-4-5b2-b-prose, timing-under-load), the 8 R8
e2e scripts, and seven round test files on the R-a removal list that pinned
them (fix-round-4-5b-prose, fix-round-4-5b-part-2/3/4-scripts,
fix-round-4-5b-part-4-prose, fix-round-4-5b2-b/c-scripts). The diff-mode e2e
pin (test 24) and the red-script round-wrapper cases go too.

tests/synthetic/plan-run-C.md becomes tests/fixtures/plan-run-c.md,
regenerated from buildPlan({ version: '1.9' }). The red judge, reporter and
judge test headers now name the shared red script.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 10:19:49 +01:00
fa0d4f036c
docs(changelog): known issues from part B's review, rounds 1 and 2
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 12:08:40 +01:00
80bb3a33d8
merge: trekexecute review-gate-4-5b2 part B and part C 2026-11-04 12:03:15 +01:00
9edc998fac
refactor: simplify pass (trekexecute)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 11:29:46 +01:00
6c8f7377bb
test(red-proof): fix round 4.5b2 part C red proof and changelog
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 11:17:19 +01:00
ff3e20919e
fix(hooks): a command with several merges says its run evidence is not shown
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 10:54:56 +01:00
29b1fba9fb
fix(hooks): no run evidence for a merged name git reads as a tag or another ref
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 10:38:39 +01:00
5b9cbeba28
fix(review): the evidence writer takes a verdict only for the branch head
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 10:27:19 +01:00
d4daa9d787
fix(review): the instruction set holds nested rules files and a link's own name
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 10:16:34 +01:00
d81bd39754
fix(review): an answer after a stopped prepare no longer locks the rounds
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 10:05:04 +01:00
fc252f8d56
fix(review): the verdict gate refuses duplicate finding ids
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 09:40:25 +01:00
f1f5ab5528
refactor: simplify pass (trekexecute)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 12:48:04 +01:00
d38846f61d
test(red-proof): fix round 4.5b2 part B red proof and regression run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 12:27:24 +01:00
3cb3958238
fix(review): a dropped engine finding keeps the gate not measured, round 1 included
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 11:57:30 +01:00
a09e6c96a1
fix(review): scope_sha_start is bound to the fork point from main
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 11:23:21 +01:00
57e7eba0a0
fix(review): R6 checks every parent of a commit after the review
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 11:07:08 +01:00
03c9f527a3
docs(changelog): review gate 4.5b2 part B, its door and known issues 2026-11-02 21:42:38 +01:00
ec5b6483ec
feat(hooks): the merge question says how the run was tested and how it is undone 2026-11-02 21:23:24 +01:00
fcba232ccd
feat(review): the code-correctness reviewer checks the repo's tracked instruction files 2026-11-02 20:47:15 +01:00
349a4fc789
feat(review): the standard path puts back engine findings the coordinator dropped 2026-11-02 20:12:46 +01:00
8d399fddfb
feat(review): a REVIEW.md policy caps and skips MINOR findings only 2026-11-02 19:43:54 +01:00
9e7e8d1516
feat(trekexecute): every MAJOR answered before merge, fixed runs the fix loop 2026-11-02 18:44:42 +01:00
635003e8aa
feat(review): review rounds carry findings until resolved, one cap of three 2026-11-02 17:44:23 +01:00
1464605e35
feat(review): pre-existing findings marked from git and re-derived by the gate 2026-11-02 16:37:24 +01:00
ce7dbc27a9
feat(review): a WARN opens the lock only when every counting MAJOR is answered 2026-11-02 15:45:37 +01:00
ce64851a0d
fix(review): an append of review answers to the approval log keeps the review current 2026-11-02 15:01:58 +01:00
5709957e10
feat(review): review_version 1.2 with answers, pre-existing, rounds and policy fields 2026-11-02 14:22:35 +01:00
ed67526987
feat(review): two CLAUDE.md rule keys at MINOR, the catalogue counts 17 2026-11-02 13:53:24 +01:00
96fba75996
merge: trekexecute guard-4-5b2-part-a 2026-11-02 11:32:04 +01:00
5c3f7ee296
docs(changelog): fix round 4.5b2 part A, the review's findings as known issues
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 11:24:56 +01:00
cc277c476c
refactor: simplify pass (trekexecute)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 10:58:35 +01:00
63fd33daaf
test(red-proof): fix round 4.5b2 part A red proof and regression run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 10:34:40 +01:00
023ccc32af
docs(changelog): fix round 4.5b2 part A, the part 4 bullets brought in line, two findings and the minor ones as known issues
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 10:20:59 +01:00
ebec492f6a
fix(hooks): the args-heredoc guard blocks a heredoc operator a second shell would read, with a bypass corpus
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 09:57:28 +01:00
7ab4100489
fix(hooks): the args-heredoc guard judges a split delimiter as written out, also inside a string
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 08:52:12 +01:00
1731e41629
fix(hooks): the args-heredoc guard reads the quotes before an escaped run, not the whole command
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 13:04:09 +01:00
e2d6beccb7
merge: trekexecute fix-round-4-5b-part-4 2026-10-31 18:58:13 +01:00
9b80e6c14c
refactor: simplify pass (trekexecute)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 17:25:10 +01:00
1f5b42556e
test(red-proof): fix round 4.5b part 4 red proof and regression run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 17:08:57 +01:00
8b9b9439cf
docs(changelog): fix round 4.5b part 4, the review's other findings as known issues, and the TOK claim without never
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 16:57:48 +01:00
9f7ba6503f
fix(hooks): the args-heredoc guard lets through a heredoc operator the shell reads as text
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 16:42:30 +01:00
12bca8b953
fix(hooks): the args-heredoc guard checks a delimiter split by a backslash-newline, and its catch branch is tested
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 16:25:53 +01:00
591f3c4793
merge: trekexecute fix-round-4-5b-part-3 2026-10-29 08:32:02 +01:00
7cb038cce3
refactor: simplify pass (trekexecute)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 00:18:29 +01:00
051331a5ef
test(red-proof): fix round 4.5b part 3 red proof and regression run
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 00:04:36 +01:00
31af4fa774
docs(changelog): fix round 4.5b part 3 and the review's other two findings as known issues
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 23:54:24 +01:00