Step 1 of v3.4.1 hot-fix plan (project 2026-05-04-v3.3.1-ultracontinue-fixes).
Adds ultracontinue entry to FLAG_SCHEMA covering boolean flags --help,
--cleanup, --confirm, --dry-run with no valued flags. The -h short form
is intentionally not aliased: it appears as positional[0] === '-h' and
the command prose dispatches usage on either condition.
7 new tests in tests/lib/arg-parser.test.mjs verify empty args, --help,
-h positional, --cleanup, --cleanup --confirm, project-dir positional,
and .md positional (parser-level accept; command-level reject).
Pins existing BLOCK rules in the two pre-* executor hooks so a future
silent weakening of BLOCK_RULES surfaces as test failures instead of
slipping through code review.
50 new tests covering both hooks plus allow-list pins (lib/, tests/,
docs/, ls, git, npm) and fail-open on malformed input. Reuses
tests/helpers/hook-helper.mjs child-process spawner.
[skip-docs]
Replaces explicit *.local.md + *.local.json rules with single *.local.*
glob covering the new examples/01-add-verbose-flag/perf-measure.local.sh
and perf-baseline.local.md operator-driven measurement harness for SC1
wall-time gate.
The harness files themselves stay outside git (operator-run only). The
.gitignore generalization is the only tracked change.
[skip-docs]
Adds 6 files in tests/synthetic/ exercising the determinism pipeline at the
SC7 brief floor (Jaccard >= 0.833). Plan fixture pair: 40 step titles each
with 38 shared (Jaccard 0.905). Review fixture pair: 30 finding-IDs each
with 28 shared (Jaccard 0.875). Reuses lib/parsers/jaccard.mjs +
lib/parsers/finding-id.mjs.
The new pair coexists with tests/lib/review-determinism.test.mjs which
holds the older SC4 (0.70) floor against tests/fixtures/ultrareview/.
The lower floor protects pipeline regressions; the higher floor anchors
the speedup brief's determinism aspiration.
[skip-docs]
New hooks/scripts/post-compact-flush.mjs (PostCompact event, CC v2.1.105+):
auto-discovers <cwd>/.claude/projects/*/.session-state.local.json (most
recently modified), validates it via session-state-validator, emits
additionalContext via stdout so the post-compact assistant turn has
Handover 7 resume context loaded immediately.
Read-only — never writes. Always exits 0; never blocks compaction. Uses
only node:fs sync APIs available since Node 12 (no glob dependency).
Companion to the existing pre-compact-flush.mjs:
- PreCompact: refresh progress.json + .session-state.local.json
- PostCompact: re-inject .session-state.local.json into context
Wired in hooks/hooks.json under a new PostCompact matcher block.
Both files staged via /tmp/claude-* and copied into hooks/* via Bash to
respect the llm-security plugin path-guard (which blocks direct Write to
hooks/scripts/*.mjs and hooks*.json).
Test: tests/hooks/post-compact-flush.test.mjs (4 tests) covers no-state,
malformed-state, valid-state, and multi-project mtime selection.
Wire the main-merge-gate lifecycle event into commands/ultraexecute-local.md
Phase 8. Three event variants emitted via lib/stats/event-emit.mjs (S8):
- main-merge-gate fired at the gate boundary
- main-merge-approved fired on operator confirm
- main-merge-declined fired on operator decline (run recorded as partial)
The gate ALWAYS pauses regardless of gates_mode — it is the one always-on
boundary that --gates does not toggle. On decline, --resume re-enters at
the gate, and the wave session branches survive on the remote thanks to
Hard Rule 19's push-before-cleanup. Recovery surface is documented inline.
Pin in tests/lib/main-merge-gate.test.mjs locks the always-on prose, the
event names, and the recovery-surface contract.
Single autonomy-control surface (--gates) added to ultrabrief, ultraresearch,
ultraplan, and ultraexecute. When present, sets gates_mode = true and
re-enables approval pauses at every phase boundary + every wave for
high-stakes runs. When absent (default in auto), the chain runs continuously
to the main-merge gate (which always pauses regardless of --gates — that
boundary is the one always-on safety stop).
ultrabrief: pause after auto-mode confirmation; emit brief-approved event
ultraresearch: pause after each topic completes
ultraplan: pause after Phases 5, 7, 9
ultraexecute: pause after each wave's worktrees finish, before merge-back,
AND before the main-merge gate (MAIN_MERGE_GATE)
All four commands invoke the autonomy-gate state machine via the CLI shim
node lib/util/autonomy-gate.mjs (built in S8). Test pin in
tests/lib/gates-flag-coverage.test.mjs locks the contract.
Also wires the brief-approved stats emission into ultrabrief Phase 5 auto
path (was the SC4 wiring requirement from plan-v2 Step 11).
Bring the launch template (used by /ultraplan-local --decompose) into
contract-parity with the Phase 2.6 wave executor hardenings shipped in the
previous commit:
- GIT_OPTIONAL_LOCKS=0 exported once at the top
- MAX_TURNS / MAX_BUDGET_USD env-overridable (default 50 / 5)
- Absolute SHARED_CONTEXT_FILE built from brief + architecture
- SAFETY_PREAMBLE prepended to every per-session prompt (GH #36071 +
GH #52272 clarifications)
- Per-child --max-turns + --max-budget-usd + --append-system-prompt-file
- push-before-cleanup before merge AND in the cleanup_worktrees trap
- Three new template rules (16, 17, 18, 19) document the contract for
session-decomposer
Pin in tests/lib/doc-consistency.test.mjs locks all required substrings
against future regressions.
Strengthen single-message reinforcement for plan-critic + scope-guardian
parallel dispatch in commands/ultraplan-local.md Phase 9 and mirror in
agents/planning-orchestrator.md Phase 6. Reviewers now write structured JSON
to /tmp/{plan-critic,scope-guardian}-out.json which is merged via the
lib/review/plan-review-dedup.mjs CLI shim from S8.
The merged set lets us revise the plan once for duplicate findings instead
of twice. Source: research/05 R1 + R2.
Pin in tests/lib/doc-consistency.test.mjs locks both files against
single-message + dedup-helper regressions.
Inline STEP_HEADING_REGEX, FORBIDDEN_HEADING_REGEX, the canonical step+manifest
example, and the post-write plan-validator self-check directly into Phase 8 of
commands/ultraplan-local.md. This eliminates the dependency on Opus 4.7
implicitly loading agents/planning-orchestrator.md — the format contract now
travels with the command file itself.
Source: research/04 D5 + plan-v2 Step 7. Pin in tests/lib/doc-consistency.test.mjs
locks the substrings so future edits cannot silently regress the seal.
Pin the contract from plan-v2 Steps 1-3: every agents/*.md must declare
model: (opus|sonnet|haiku) AND (tools: or disallowedTools:). Orchestrators
(planning/research/review) must be opus and include the Agent tool;
non-orchestrators must not include Agent (no recursive swarming).
23 agents in scope; 5 pinning tests.
[skip-docs]
Marketplace-root .gitignore already covers plugins/*/.claude/, but
plugin-local coverage is load-bearing for fork-and-own (forks of just
the plugin won't carry the marketplace .gitignore).
Establish a single governance document at marketplace root and copy
it into each of the 9 plugins so every plugin folder remains 100%
self-contained. Replace the inconsistent provocative blurb across
all READMEs with a uniform fork-and-own paragraph that links to
the local GOVERNANCE.md.
[skip-docs]
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Tiny helper command for ad-hoc multi-session flows that don't run through
/ultraexecute-local. Writes .session-state.local.json so /ultracontinue
can resume in a fresh chat. Required args (next-brief-path, next-label) —
no inline prompt, headless-safe. Validates via session-state-validator
and prints the same 3-line narration that /ultracontinue Phase 3 uses
(SC-8 cross-project consistency).
Step 9 of /ultracontinue v3.3.0. README/CLAUDE updates land in Step 11.
Extends the PreCompact hook with a sibling block that refreshes
.session-state.local.json's updated_at when status is in_progress or
partial. Per-project: runs after the existing progress.json mutation,
inside the same loop iteration.
Design:
- Only refreshes existing state files; creation is the writer's job
(ultraexecute Phase 8 / 2.55 / 4 + future helper command).
- Monotonic guard: only updated_at is touched. project, status,
next_session_brief_path, next_session_label remain owned by the writer.
- Skips status in {completed, failed, stopped} — the latter two are
operator-action-required and silently bumping updated_at would mask
alert state.
- Always exit 0; never blocks compaction.
[skip-docs] rationale: README + CLAUDE.md updates land in Step 11.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Three insertions in commands/ultraexecute-local.md so every session-end
path produces or refreshes .session-state.local.json (Handover 7):
- Phase 2.55 (Check 1, line ~376): write status=stopped on dirty-tree
pre-flight stop before parallel session-spawn
- Phase 4 (line ~773): write status=stopped when entry condition fails
- Phase 8 (line ~1151): canonical convergence — every completed/failed/
stopped/partial run refreshes the state file using atomicWriteJson +
validator verification
Phase 2.3 (validate exit) and Phase 5 (dry-run) intentionally skip the
write — neither path is resumable. Validator errors warn but never block
the run; progress.json remains authoritative.
[skip-docs] rationale: README + CLAUDE.md updates land in Step 11.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Reads .claude/projects/<project>/.session-state.local.json (Handover 7),
narrates a 3-line summary, and immediately begins executing the next
session — no interactive confirmation, headless-safe.
Phases:
- 0: --help (self-documenting per brief NFR)
- 1: resolve project dir (auto-discover via node -e enumeration)
- 2: validate via session-state-validator
- 3: narrate (project / next_session_label / brief path)
- 4: read brief and begin
- 5: stats
[skip-docs] rationale: README + CLAUDE.md updates land in Step 11 (Session
2b) per plan structure. Step 8 (docs:) updates HANDOVER-CONTRACTS.md and
the doc-consistency test pin in the same session.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Three changes in one commit:
1. NEW lib/util/atomic-write.mjs — exports atomicWriteJson(path, obj),
the canonical tmp+rename pattern. Reused by pre-compact-flush.mjs and
(in subsequent steps) by the new session-state writer.
2. NEW tests/lib/atomic-write.test.mjs — 4 unit tests covering
round-trip, no-orphan-tmp, overwrite-atomic, pretty-print formatting.
3. REFACTOR hooks/scripts/pre-compact-flush.mjs — replace the inline
atomicWrite() with the imported atomicWriteJson(). Also fixes a
pre-existing syntax error (leading whitespace + stray --resume token
outside the comment block) that silently broke the hook from v3.1.0
onward — PreCompact runtime is fail-open and swallowed the error.
File reformatted with standard zero-indent JS.
163 → 167 tests, 0 fail.
Step 2 of /ultracontinue v3.3.0 (project 2026-05-01-ultracontinue).
Brief assumed *.local.* covered .session-state.local.json — only *.local.md
existed. Adding *.local.json before any state file can be created.
Step 1 of /ultracontinue v3.3.0 (project 2026-05-01-ultracontinue).
Synthetic plan.md fixture with source_findings: block-style YAML list of 3
40-char hex IDs in frontmatter, plus minimal plan structure (Title +
Implementation Plan + 1 Step + Manifest). 3 tests verify:
1. plan-validator accepts a plan with source_findings (additive optional field)
2. frontmatter parser extracts source_findings as array of strings
3. each ID matches the 40-char lowercase hex format from finding-id.mjs
Closes the SC3(b) gap flagged by adversarial review (scope-guardian Gap 2).
LLM-level behavior (planner emitting source_findings) remains non-testable
without live invocation; this covers the structural contract.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
3 integration tests using the run-A/run-B fixtures:
- Jaccard(A, B) ≥ 0.70 (SC4 brief threshold)
- IDs match 40-char hex shape (lib/parsers/finding-id.mjs format)
- no duplicate IDs within a single run
Tests the Jaccard PIPELINE; real-LLM determinism deferred to v1.1.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
review-run-A.md (5 findings) and review-run-B.md (6 findings, A ⊂ B) form a
known-Jaccard fixture pair: |A ∩ B| = 5, |A ∪ B| = 6, Jaccard = 5/6 = 0.833,
above the SC4 threshold of 0.70. IDs are real 40-char SHA1s computed via
lib/parsers/finding-id.mjs from realistic (file, line, rule_key) triplets.
Both fixtures pass review-validator --strict (frontmatter + body sections +
findings shape). Real-LLM determinism measurement deferred to v1.1.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Modify "all four pipeline commands" → "all five" (adds /ultrareview-local).
Add 3 new pins: Handover 6 section in HANDOVER-CONTRACTS.md,
review-validator CLI shim, rule-catalogue 12-key size invariant.
11/11 doc-consistency tests pass.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Closes the iteration loop: review.md → plan via source_findings audit trail.
Adds versioning row, validator-map entry, full Handover 6 section, and
stability summary row mirroring the shape of Handovers 1-5.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
