Commit graph

12 commits

Author SHA1 Message Date
512ae322bd fix(ultraplan-local): Bug 3 producers — frontmatter writes + ESM/CJS fix
Step 7 of v3.4.1 plan.

ultraplan-end-session-local Phase 3:
- Replace require()-of-ESM-module shim with node --input-type=module + import.
- Convert Phase 1 project enumeration to ESM as well so the file is uniformly
  ESM (grep -c 'require(' commands/ultraplan-end-session-local.md → 0).
- Combined ESM block writes both .session-state.local.json (atomicWriteJson)
  and sibling NEXT-SESSION-PROMPT.local.md (writeFileSync) so producers
  succeed or fail together.
- Sibling markdown gets frontmatter: produced_by, produced_at, project.

ultraexecute-local Phases 8 / 2.55 / 4:
- Each phase that writes .session-state.local.json now also writes a sibling
  NEXT-SESSION-PROMPT.local.md with frontmatter (produced_by:
  ultraexecute-local, produced_at: ISO-8601, status). Phase 8 includes the
  full ESM block; 2.55 / 4 reference the combined pattern.
- This is the producer side of the Bug 3 contract; consumer-side wire-up
  (Phase 1.5 consistency check in /ultracontinue) lands in Step 8.

Tests: 346 green (no new tests this step — coverage comes via Step 8
integration test).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-04 17:37:21 +02:00
b837274b77 feat(ultraplan-local): emit main-merge-gate stats event from Phase 8
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.
2026-05-04 07:55:41 +02:00
34f62043f9 feat(ultraplan-local): add --gates autonomy-control flag to all four pipeline commands
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).
2026-05-04 07:54:30 +02:00
41a0c913fa feat(ultraplan-local): harden Phase 2.6 wave executor (11 sub-changes for plugin-in-monorepo + gitignored-state topology)
Phase 2.6 + Hard Rules + Phase 2.4 hardenings against the topology that
blocked S6 / S7 self-execution:

Phase 2.6 (multi-session orchestration):
  - NEW Step 2a-pre: build absolute SHARED_CONTEXT_FILE (brief + architecture)
    once per wave; introduce ULTRAEXECUTE_MAX_TURNS / ULTRAEXECUTE_MAX_BUDGET_USD
    overrides for long runs.
  - Step 2a: prefix every git worktree command with GIT_OPTIONAL_LOCKS=0
    (research/02 R2; GH #47721).
  - NEW Step 2a': copy gitignored project artifacts (brief.md, plan.md,
    research/) into each freshly-created worktree using PROJECT_SOURCE +
    PROJECT_REL so plugin-in-monorepo + gitignored-state topology works
    (brief Constraint 2).
  - Step 2b: prepend two safety preambles to every per-session prompt:
      (a) defense-in-depth headless-mode warning citing GH #36071
      (b) malware-reminder conditional clarification per GH #52272
    Honor `cwd:` field from Execution Strategy via SESSION_CWD; default
    is worktree root (backward-compatible). Add per-child --max-turns,
    --max-budget-usd, --append-system-prompt-file (research/06 R3+R4).
  - Step 2e: push branch BEFORE merge (research/02 R3 — converts
    unrecoverable branch loss into recoverable remote state).
  - Step 2f: prefix all worktree-remove / branch -d / worktree prune with
    GIT_OPTIONAL_LOCKS=0.
  - Step 4 cleanup: same GIT_OPTIONAL_LOCKS=0 treatment.

Hard Rules:
  - Hard Rule 15: extend exception to permit ~/.claude/projects/*/memory/
    writes when manifest declares memory_write: true (brief Constraint 3
    Option A — narrow opt-in for memory file edits).
  - Hard Rule 19 (new): push-before-cleanup formalized as a rule.

Phase 2.4: advisory hooks-fire precheck for CC version >= v2.1.117
  (research/04 D4 + R5; research/06 R1).

Test: tests/hooks/worktree-guard.test.mjs (6 tests) verifies the
pre-bash-executor and pre-write-executor hooks accept routine worktree
cleanup (Hard Rule 12) while still blocking the dangerous patterns
introduced by parallel orchestration.
2026-05-04 07:49:45 +02:00
Kjell Tore Guttormsen
e4a11daa68 feat(ultraplan-local): write session-state from ultraexecute session-end paths [skip-docs]
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>
2026-05-01 20:50:28 +02:00
Kjell Tore Guttormsen
1a65d8e4d5 feat(graceful-handoff): 2.0 — migrate to skills/ with disable-model-invocation [skip-docs]
Step 1 of v2.0 plan. Hard cut from commands/ to skills/ per Anthropic
recommendation for new plugins. Frontmatter sets disable-model-invocation:
true and pins model: claude-sonnet-4-6. Docs (README, CLAUDE.md, root
README) deferred to Step 9 per plan.
2026-05-01 05:45:26 +02:00
Kjell Tore Guttormsen
2bc405e14a feat(ultraplan-local)!: v2.0.0 — brief-driven four-command pipeline
Extract interview from /ultraplan-local into new /ultrabrief-local command.
/ultraplan-local now requires --brief or --project (breaking). All pipeline
artifacts land in one project directory: .claude/projects/{date}-{slug}/
with brief.md, research/, plan.md, sessions/, progress.json.

Breaking changes:
- /ultraplan-local requires --brief <path> or --project <dir>
- /ultraplan-local --spec removed (convert specs to briefs per MIGRATION.md)
- Interview phase moved to /ultrabrief-local
- spec-reviewer renamed to brief-reviewer with 5th dimension (Research Plan validity)

Added:
- /ultrabrief-local command (interactive interview → brief.md with research plan)
- templates/ultrabrief-template.md (task brief format with intent + research plan)
- brief-reviewer agent (5-dimension brief quality review)
- --project <dir> flag on /ultraresearch-local, /ultraplan-local, /ultraexecute-local
- MIGRATION.md (v1 → v2 upgrade guide)

Changed:
- planning-orchestrator accepts Brief file: input (was Spec file:)
- planning-orchestrator Phase 1b uses brief-reviewer
- README + CLAUDE.md rewritten for four-command pipeline and task/research brief terminology
- CHANGELOG.md [2.0.0] entry with rationale
- Marketplace root README + CLAUDE.md updated to v2.0.0

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-18 07:22:08 +02:00
Kjell Tore Guttormsen
9ecd66929c feat(ultraplan-local): v1.8.0 — close Opus 4.7 schema-drift gap
Opus 4.7 reads agent instructions more literally than 4.6. The v1.7
planning-orchestrator described the Step+Manifest schema via prose +
procedural rules, which 4.6 inferred correctly but 4.7 sometimes
rendered as narrative "Fase N" prose — producing plans ultraexecute
Phase 2 rejected. First observed 2026-04-17 during llm-security v6.2.0
planning.

v1.8.0 closes the gap:

- planning-orchestrator Phase 5 embeds a literal copyable Step+Manifest
  example (JWT middleware) replacing "read the template" prose
- Explicit forbidden-format clause: ## Fase N, ### Phase N, ### Stage N,
  and any non-"### Step N:" heading are denied
- Phase 5.5 schema self-check: grep-verify canonical Step count matches
  Manifest count and narrative heading count is zero, before handing to
  plan-critic
- ultraexecute-local --validate mode: schema-only check that parses
  steps + manifests, reports READY/FAIL with actionable error hints,
  no security scan, no execution. Fast sanity check between
  /ultraplan-local and full execution.

Static verification: 17/17 PASS.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-17 18:01:14 +02:00
Kjell Tore Guttormsen
d1befac35a feat(ultraplan-local): v1.7.0 — self-verifying plan chain
Wave 1 of a 6-session parallel build revealed three failure modes:
(1) hallucinated completion (status=completed after 2/5 steps, last
tool call was an arbitrary file review), (2) fail-late bash (3/6
sessions had push blocked inside sub-agent sandbox after all work
was done), (3) no objective verification (plans were prose).

v1.7 closes all three by making the plan an executable contract.

Per-step YAML manifest (expected_paths, commit_message_pattern,
bash_syntax_check, forbidden_paths, must_contain) is the objective
completion predicate. Plan-critic dimension 10 (Manifest quality)
is a hard gate. Session decomposer propagates manifests verbatim
and emits an obligatory Step 0 pre-flight (git push --dry-run,
exit 77 sentinel) in every session spec.

ultraexecute-local gets Phase 7.5 (independent manifest audit from
git log + filesystem, ignoring agent bookkeeping) and Phase 7.6
(bounded recovery dispatch, recovery_depth ≤ 2). Hard Rule 17
forbids marking a step passed without manifest verification. Hard
Rule 18 forbids ending on an arbitrary tool call before reporting.

Division of labor is made explicit:
- /ultraresearch-local gathers context (no build decisions)
- /ultraplan-local produces an executable contract (manifests,
  plan-critic gate)
- /ultraexecute-local executes disciplined (does NOT compensate
  for weak plans — escalates)

Code complete. Docs partial (Arbeidsdeling table + manifest section
added to plugin + marketplace READMEs). Verification tests
(10-sequence) pending — see REMEMBER.md.

Backward compat: v1.6 plans without plan_version marker get
legacy mode with synthesized manifests and legacy_plan: true in
progress file. Plan-critic emits advisory, not block.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-12 07:38:16 +02:00
Kjell Tore Guttormsen
aa21e59ac2 feat(ultraplan-local): defense-in-depth security hardening for executor
Four-layer security model for ultraexecute-local and headless sessions:

Layer 1 — Plugin hooks: pre-bash-executor.mjs (13 BLOCK + 8 WARN rules
with bash evasion normalization) and pre-write-executor.mjs (8 path guard
rules blocking .git/hooks, .claude/settings, shell configs, .env, SSH/AWS).

Layer 2 — Prompt-level security rules: denylist in ultraexecute-local.md
Sub-step D and session-spec-template.md Security Constraints section.
These are the only rules that work in headless child sessions.

Layer 3 — Pre-execution plan validation: new Phase 2.4 scans all Verify
and Checkpoint commands against denylist before execution begins.

Layer 4 — Replace --dangerously-skip-permissions with scoped
--allowedTools "Read,Write,Edit,Bash,Glob,Grep" --permission-mode
bypassPermissions in ultraexecute-local.md, headless-launch-template.md,
and session-decomposer.md. Blocks Agent, MCP, WebSearch in child sessions.

Also adds Hard Rules 14-16: verify command security check, no writing
outside repository root, no writing to security-sensitive paths.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 18:33:15 +02:00
Kjell Tore Guttormsen
5dd7e8447c fix(ultraplan-local): CRITICAL — worktree isolation for parallel sessions
Phase 2.6 previously launched parallel claude -p sessions in the same
working directory, causing git race conditions and repository corruption.

Changes:
- Add Phase 2.55 (pre-flight safety checks): clean tree, plan file
  tracking, scope fence overlap validation, stale worktree cleanup
- Rewrite Phase 2.6 with git worktree isolation: each parallel session
  gets its own worktree and branch, merged back sequentially
- Add merge conflict detection and abort (no silent data loss)
- Add unconditional worktree cleanup (even on failure)
- Add hard rules 11-13 (worktree mandatory, cleanup, sequential merge)
- Session-scoped progress file naming for --session mode
- Update headless launch template with worktree support and cleanup trap
- Bump version to 1.5.0

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-07 22:12:53 +02:00
Kjell Tore Guttormsen
f93d6abdae feat: initial open marketplace with llm-security, config-audit, ultraplan-local 2026-04-06 18:47:49 +02:00