Step 19 of v4.1 — extend-in-place per brief Preferences. Three new test
blocks asserting forward-compat:
1. Legacy fixtures (plan-run-A.md, plan-run-B.md) — without profile_used
in frontmatter — still parse cleanly after manifest-yaml.mjs added
OPTIONAL_STRING_KEYS.
2. New fixtures (profile-plan-run-{economy,premium}-*.md) — with
profile_used in frontmatter — parse cleanly with correct profile
value extracted.
3. Real v4.1 plan (.claude/projects/2026-05-08-voyage-v4.1-modellprofiler/plan.md)
validates strict, emits no PLAN_VERSION_MISMATCH warning.
Tests: 475 pass + 2 skipped (Docker not installed).
Step 17 of v4.1 — escalate-handler invoked. Live LLM-budget ($60-120 for
4 plan-runs á /trekplan --profile {economy,premium} on
examples/01-add-verbose-flag/brief.md) was not authorized for the
v4.1-execute-4b session.
Per Step 17 escalate-fallback (and NEXT-SESSION-PROMPT.local.md
fallback-strategy): document economy-Plan as parked, use balanced as
low-threshold profile, defer empirical calibration to v4.2.
Files:
tests/synthetic/profile-plan-run-economy-1.md — 30 steps, parked-synthetic
tests/synthetic/profile-plan-run-economy-2.md — 30 steps, parked-synthetic
tests/synthetic/profile-plan-run-premium-1.md — 40 steps, parked-synthetic
tests/synthetic/profile-plan-run-premium-2.md — 40 steps, parked-synthetic
tests/synthetic/profile-jaccard-calibration.md — threshold 0.55 pinned per
research/02 conservative starting value
Replacement procedure documented in calibration.md "How to replace"
section. Trigger conditions for empirical re-run:
1. Cross-tier smoke-test (Step 18) flips red on a real run
2. v4.2 LLM-budget approval
3. New profile tier added
Step 16 of v4.1 — first test in tests/integration/, establishes the
skip-on-missing-tool pattern voyage will reuse for environment-dependent
integration tests. Two tests:
1. compose config parses and contains expected services
2. compose config pins required image versions
Both skip cleanly when 'docker info' fails (no Docker installed). On a
machine with Docker, both tests run docker compose config and assert the
4 services + 3 version pins are present.
Tests: 468 pass + 2 skipped (Docker not installed in dev env).
Step 14 follow-up — VOYAGE_OTEL_ENDPOINT (not VOYAGE_OTLP_ENDPOINT) per
hooks/scripts/otel-export.mjs and lib/exporters/endpoint-validator.mjs.
Adds VOYAGE_OTEL_ALLOW_PRIVATE=1 for localhost since 127.0.0.1 is
loopback and rejected by default.
Step 13 of v4.1 — adds Stop hook entry pointing to
hooks/scripts/otel-export.mjs (added in Step 12 / commit cced21b).
Mounts the orchestrator on Claude Code's Stop event so OTel/Prometheus
export runs at session-end when VOYAGE_EXPORT_MODE is set.
HIGH-risk-mitigering: tests/hooks/hooks-json-stop-wired.test.mjs
asserter at Stop-key finnes, refererer otel-export.mjs, bruker
\${CLAUDE_PLUGIN_ROOT}-substitusjon, og har type:command.
Tests: 464 → 468 (4 new). All green.
Step 4 av v4.1-execute (Wave 2, Session 2).
Tre innebygde modellprofiler matcher brief profile-assignment matrix:
- economy: alle 6 phase_models = sonnet, parallel 2-3, external_research=false,
iter-cap=1. ~$1-3 per pipeline-sesjon.
- balanced: brief/research/execute/continue=sonnet, plan=opus, review=opus,
parallel 4-6, external_research=false (operator-override deferred
til v4.2 per NEXT-SESSION-PROMPT scope-grenser), iter-cap=2.
~$5-15 per pipeline-sesjon.
- premium: alle 6 phase_models = opus, parallel 6-8, external_research=true,
iter-cap=3. ~$20-60 per pipeline-sesjon (default, samme som v4.0).
Bruker list-of-dicts for phase_models (parser-kompatibel mot
lib/util/frontmatter.mjs:79-105). Verifisert: alle 3 filer parses uten feil
og returnerer array med 6 entries (phase+model per entry).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Step 3 av v4.1-execute (Wave 1, Session 1).
Legg ny eksportert const OPTIONAL_STRING_KEYS = ['profile_used'] parallel
til eksisterende OPTIONAL_KEYS. Utvid parseManifest med ny dispatch-loop
etter OPTIONAL_BOOLEAN_KEYS. Returnerer MANIFEST_OPTIONAL_TYPE hvis
profile_used finnes men ikke er string.
Forskjell fra OPTIONAL_BOOLEAN_KEYS: absence == not-present (NOT defaulted
til false, unlike boolean). Downstream-konsumenter kan dermed skille mellom
unset og empty-string.
Tester (5 nye, baseline 372 → 377):
- OPTIONAL_STRING_KEYS export drift-pin
- profile_used: economy parses successfully (SC #10 forward-compat)
- profile_used: numeric rejected
- absence: field NOT in parsed (string-key semantics)
- profile_used + skip_commit_check + memory_write co-existence
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Step 2 av v4.1-execute (Wave 1, Session 1).
Legg --profile i valued-arrayen for alle 6 voyage-kommandoer (trekbrief,
trekresearch, trekplan, trekexecute, trekreview, trekcontinue). Mønster
identisk med eksisterende --project/--brief valued-handling. Ingen endring
til parseArgs-logikk — utvider kun schema.
Tester (11 nye, baseline 361 → 372):
- 6 happy-path-tests (én per kommando)
- ARG_MISSING_VALUE for --profile uten verdi
- --profile + --quick kombo
- --profile + --gates edge-case (--gates parses inline, ikke i FLAG_SCHEMA)
- --profile + --project kombo
- trekcontinue --profile (validerer at tomt valued[] nå er utvidet)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Slash-command-parseren matcher !`...` selv inne i ```bash markdown-fences,
som gjorde at Phase 8 NEXT-SESSION-PROMPT-template eksekverte ved skill-load
med literale {project_dir}/{next_session_brief_path}/{next_session_label}/
{status}-strenger som argv. Det ga ENOENT på .session-state.local.json.tmp
og blokkerte hele /trekexecute skill-loadet.
Fjern !`...`-wrapperen og merk blokken eksplisitt som runtime-template.
Pattern matcher nå konvensjonen brukt andre steder i samme fil
(linje 202-208) der ```bash brukes for orkestrator-instruksjon uten
auto-eksekvering.
Wave 0 av v4.1-execute — pre-requisite for å låse opp /trekexecute
skill-invokasjon mot .claude/projects/2026-05-08-voyage-v4.1-modellprofiler/
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The ultra-cc-architect plugin was removed from the marketplace; voyage's
architecture-discovery contract still pointed at it by name. Replaced
verbatim references with plugin-agnostic phrasing ("upstream architect
producer") in code comments and user-facing warning messages.
CHANGELOG entries and config-audit v5.0.0 snapshots intentionally
preserved as historical records.
D5 — final session of post-v3.4.1 stabilisering. Repo prepared for the
upcoming voyage-rebrand (v4.0.0 hard cut: ultraplan-local → voyage,
/ultra*-local → /trek*).
Tracked changes:
- README.md: cut #9 jargon — '### Self-verifying plan chain' →
'### Manifest-verified steps' with body rewritten to drop the
'objective completion predicate' jargon.
- package.json: removed 'simulate' script that pointed to
tests/simulator/run-pipeline.mjs (file never existed; D3 was
dropped before that work shipped).
- .claude-plugin/marketplace.json: ultraplan-local description
updated from 'Four-command pipeline' to the current six-command
shape with Handover 6 + multi-session resumption (matches
plugin.json).
- docs/_archive-ultra-suite-brief_2.md: deleted (tracked planning-doc
unrelated to ultraplan-local; 117 lines, no inbound references).
Untracked cleanup (not in commit, gitignored):
- 4 stale plugin-root .local.md (NEXT-SESSION-PROMPT.archived,
PLAN-v2.1-phase3, V3.0-MULTI-SESSION-PLAN, etc.)
- 3 docs/ planning .local.md (ultracontinue-brief, ultracontinue-design-notes,
ultraexecute-v2-observations)
- examples/01-add-verbose-flag/perf-baseline.local.md
- .claude/plans/ultraplan-2026-04-17-logger.md
- 9 closed sub-projects under .claude/projects/ (skill-factory,
ultracontinue, ultrareview-local, ultra-pipeline-speedup,
examples-02-real-cli, post-v3.4.0-roadmap, spor-c-q3-cache,
v3.3.1-ultracontinue-fixes)
Cuts #7 (template-duplisering) + #10 (Two kinds of briefs) reviewed
and judged not needed: README has 38 code-fences vs CLAUDE.md 2 (no
overlap), and 'Two kinds of briefs' is already a direct task-vs-
research-brief explanation, not jargon.
D3 + D4 droppet 2026-05-05 — voyage-rebrand renames all ultra*
references; new test infrastructure built against the old names
would need to be renamed in the same pass. Memory pin:
feedback_cleanup_vs_new_code.md.
Tests: 361 / 0 (unchanged — no test changes).
Stabilisering close-out: complete. Repo is ready for voyage-rebrand.
D2 of post-v3.4.1 stabilisering. Removes 14 plugin-name references from
agents/, commands/, and docs/ tracked files (CLAUDE.md/README.md/SECURITY.md
were ryddet in v3.4.1 commit 52cfc64).
The external architect plugin was moved out of the public marketplace
2026-05-04 due to ToS concerns around future skill sources. References in
prose are now stale or misleading for public users. The architecture/overview.md
filesystem slot remains available for any compatible producer — discovery
is plugin-agnostic via lib/validators/architecture-discovery.mjs (drift-WARN,
never drift-FAIL).
Files:
- agents/planning-orchestrator.md (1 ref generalized)
- commands/ultraplan-local.md (2 refs generalized; missed by prompt inventory)
- docs/HANDOVER-CONTRACTS.md (4 refs generalized; Handover 3 + stability summary)
- docs/architect-bridge-test.md (deleted; was a public-only bridge checklist)
- docs/subagent-delegation-audit.md (5 refs/rows removed; intervention #5 dropped, recommendation adjusted)
CHANGELOG.md retains historical references (20 occurrences) intentionally.
Verification:
- grep tracked non-CHANGELOG md: 0 references remaining
- npm test: 361/361 pass (baseline preserved)
D1 of post-v3.4.1 stabilisering. Path C (cache-warm sentinel + identical-tool
parallel) is closed 2026-05-05 per Q3 experiment NEGATIVE result:
median cache_creation_input_tokens = 163,903 across 3 fork-children at
186K parent context (CC v2.1.128, Sonnet 4.6).
Master-plan thresholds: <= 1,500 POSITIVE / >= 3,500 NEGATIVE — NEGATIVE
solidly. CLAUDE_CODE_FORK_SUBAGENT does not preserve cache prefix across
identical-tool children at our context size.
Path C migration is deferred indefinitely. Reassessment is appropriate
when CC v2.2.xxx ships fork-cache-relevant features. Harness
(scripts/q3-cache-prefix-experiment.mjs) and analyser
(lib/stats/cache-analyzer.mjs) remain available for re-run.
Brief: .claude/projects/2026-05-04-spor-c-q3-cache-prefix-experiment/brief.md
Result: q3-experiment-results.local.md (gitignored)
First foundation lib for v1.12.0 auto-KB-update. Resolves per-OS paths:
- macOS: ~/Library/{Caches,Logs,Application Support}/<app>/
- Linux: XDG_CACHE_HOME / XDG_STATE_HOME with ~/.cache, ~/.local/state fallbacks
- Windows: %LOCALAPPDATA%\<app>\{Cache,Logs,State}
Plus getBackupDir(pluginRoot) → <pluginRoot>/.kb-backup (gitignored).
All four functions auto-mkdir target. Dependency-injection via opts
({platform, homedir, env}) makes the lib pure-testable; 13/13 tests
pass under tmpdir isolation without touching real ~/ paths.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Implements Spor C of post-v3.4.0 roadmap. Zero-dep harness measures
CLAUDE_CODE_FORK_SUBAGENT cache-prefix preservation across 3 fork-children
with identical --allowedTools at 150-250K parent context.
Harness uses --append-system-prompt-file (avoids stdin buffer cap at
>200K bytes) + --exclude-dynamic-system-prompt-sections (prevents
per-child cache-prefix divergence from cwd/env/git-status).
Companion analyser summarizes accumulated ultraexecute-stats.jsonl:
percentile wall_time (p50/p90/max), total events, ISO time range.
Output: JSON via --json <path> CLI shim.
Result file is gitignored (*.local.md). Master-plan thresholds
(<= 1.5K positive / >= 3.5K negative) gate the v3.5.0 Path C decision.
Brief: .claude/projects/2026-05-04-spor-c-q3-cache-prefix-experiment/brief.md
Master-plan: .claude/projects/2026-05-04-post-v3.4.0-roadmap/master-plan.md
Pipeline-walk-through fylt inn etter B3 pipeline-run mot examples/02-real-cli.
Erstatter 'TBD' og '(Placeholder)' med faktisk research-skip + plan-summary
+ execute-summary (4 commits 9587129 → 69c45ad) + 10/10 SC PASS-tabell.
Spor B er ferdig. Neste handling: operatør-bekreftelse + WAIT_FOR_TELEMETRY
før Spor C kan starte. Se plugins/ultraplan-local/NEXT-SESSION-PROMPT.local.md
(stop-prompt, IKKE C1).
Step 4 (final) of plan.md (Spor B B3 pipeline run). Adds 4 new tests
in a contiguous block at the end of tests/tally.test.mjs, mirroring
the existing spawnSync style. All 4 test names contain --regex or -r.
Coverage map:
- SC #1 (long form, exit 0): test 1
- SC #2 (-r short form): test 2
- SC #4 (invalid exits 2 with /^tally: invalid regex/): test 3
- SC #5 (--json includes flags.regex): test 4
Total: 14 tests, all green, 3.16s wall-clock (under 5s cap).
[skip-docs]
Step 3 of plan.md (Spor B B3 pipeline run). Adds one line under
Options: in the HELP template literal so --help users can discover
the new flag. Satisfies SC #8.
[skip-docs]
Step 2 of plan.md (Spor B B3 pipeline run). Wires the --regex/-r flag
into main(): when set, compileRegex(pattern) is used and the count is
text.match(re).length. Invalid regex exits 2 via the existing fail()
helper. JSON output now includes flags.regex so consumers can tell the
mode apart. Baseline tests remain green; -i/--ignore-case has no effect
when --regex is set (out of brief scope).
Verify covered: SC #1 (any position), SC #2 (-r short form), SC #3
(regex semantics differ), SC #4 (invalid exits 2), SC #5 (JSON regex),
SC #6 (byte-identical baseline).
[skip-docs]
Step 1 of plan.md (Spor B B3 pipeline run). Adds the new --regex / -r
flag to parseArgs and a compileRegex(pattern) helper. The flag is
parsed but main() does not yet branch on it (wired in step 2). All
10 baseline tests remain green.
[skip-docs]
Adds the runnable counterpart to examples/01-add-verbose-flag (which is
artifacts-only). The fixture is the measurement target for Spor B's
end-to-end pipeline run (B3) and Spor C's cache-prefix experiment.
Baseline:
- tally.mjs (80 lines, hand-rolled argv parser, zero deps)
- 3 flags: --json, -i/--ignore-case, --lines + --help
- Exit codes: 0 success, 1 file error, 2 invalid argv
- 10 node:test cases, all green (~2.2s wall-clock)
- Deterministic fixtures: sample.txt (foo×7, Foo×1, regex fo+×9) +
poem.txt (--lines vs total distinction)
- REGENERATED.md skeleton (B3 fills the pipeline walk-through)
Brief preconditions verified:
- grep -c 'foo' sample.txt = 4 (>= 1)
- regex /fo+/g count = 9 (> grep count)
- Brief assumptions for B3 SC #1, #3 hold
This is the first runnable example in plugins/ultraplan-local/examples/.
Next: B3 runs /ultraresearch-local + /ultraplan-local + /ultraexecute-local
against the brief to add --regex/-r, then verifies all 10 Success Criteria.
Step 13 of v3.4.1 plan.
- plugin.json description: Five-command -> Six-command (drift fix); also
drops the trailing ultra-cc-architect sentence (SC-6 collateral).
Mentions multi-session resumption as part of the Six-command pipeline.
- plugin.json + package.json version: 3.4.0 -> 3.4.1.
361 tests still green.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
