Kjell Tore Guttormsen
2a35d067d9
The four profiles, the resolver, the profile validator and docs/profiles.md go; /trekbrief Phase 3.5 and the brief's phase_signals checks go (an older brief's key is ignored); MANIFEST_PROFILE_DRIFT and profile_used go. Every Profile, Composition rule, Sequencing gate and High-effort section leaves the commands. Decision 209: /trekresearch runs the full swarm with contrarian-researcher as wave 2 every run; /trekreview and the coordinator run all four passes with no high-effort normalization. Voyage agents are spawned with no model (their own model: opus applies); the two built-in spawns pass model "opus". --profile stays in the parser as a retired flag that swallows its value. §Model & effort moves to docs/architecture.md; the sequencing-gate eval case goes. Files removed: 44 (43 from the R3 list + tests/commands/trekreview.test.mjs, whose every test pinned removed text). Files edited: 43. Tests: 2467 (2466 pass / 0 fail / 1 skipped) before, 2309 (2309 pass / 0 fail / 0 skipped) after. Durable check: all three groups green, none pending. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
4.4 KiB
Voyage — Autonomy gates, observability
Imported from CLAUDE.md via pointer.
Autonomy mode (--gates, v3.4.0)
All four pipeline commands accept --gates [true|false|closed|open]. A bare --gates, --gates true or --gates closed turns gating on; --gates false, --gates open or no flag (the default) leaves it off. The next token is the flag's value only when it is one of those four; any other token stays the command's own argument, so /trekplan --gates --project <dir> and /trekexecute --gates plan.md are a bare --gates. Each command maps the value once through lib/util/autonomy-gate.mjs; a shim that fails falls back to the same mapping in prose, and the run goes on. With gating on, /trekbrief pauses before its auto chain, /trekresearch after each topic, and /trekplan after exploration, synthesis and adversarial review. /trekexecute accepts the flag and pauses on nothing: its one stop is the merge into main, which always asks (below).
Under the hood: lib/util/autonomy-gate.mjs is the --gates flag parser. It prints {"ok":true,"gates":true} when --gates is bare, true or closed, {"ok":true,"gates":false} for false, open or no flag, and a usage error (exit 1) for anything else. The module is pure data with no I/O. The main-merge gate is the final autonomy boundary before HEAD lands on main.
The main-merge gate is a lock, and the guard asks the one question (operator decision 2026-10-08). The gate opens only when the run is completed and the review's verdict gate (lib/review/verdict-gate.mjs, K7) exits 0; BLOCK (1) and "could not decide" (2) keep it closed. When it opens, /trekexecute runs the merge into main itself and pre-bash-executor answers "ask" before it runs, in auto mode too, so that question is the only one. In the permission mode where Claude Code shows no prompts, the guard refuses the merge instead, and every other call it would ask about (push, tag or publish, destructive git), since no one can be asked (operator decisions 2026-10-09). The executor no longer asks "ready to merge?" first, and --gates no longer adds a pause before the wave merge-back: the guard asks there as well, once per session, because the push and the merge go in one call. Before this, one merge cost two questions in three places: the --gates pause before the wave merge-back, the gate's own question after the waves were merged, and the gate's question on the single-session path followed by the guard's at the merge itself.
Path A/B/C decision (v3.4.0; Path C closed 2026-05-05)
Three architectural options were considered for the speedup work:
- Path A — cache-first (drop
--allowedToolsper child to recover cross-phase cache sharing): REJECTED. Inverts the security model; plugin hooks don't fire reliably inclaude -p(research/06 GH #36071). - Path B — sequential
--no-ffparallel waves with manifest-driven failure recovery: CHOSEN. Ships in v3.4.0. Phase 2.6 of/trekexecuteruns the wave executor with hardenings for plugin-in-monorepo + gitignored-state topology. - Path C — hybrid (cache-warm sentinel + identical-tool parallel): CLOSED 2026-05-05. Q3 experiment measured 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. Result is solidly NEGATIVE —CLAUDE_CODE_FORK_SUBAGENTdoes 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.
Status (6.0.0):
/trekexecuteno longer starts wave children. Phase 2.6 prepares one wave at a time and hands each session over as an order the user runs in a session they open (CHANGELOG, 6.0.0). The Q3 harness was removed in 6.0.0 because it started the binary; its result above stands, and the script remains in git history before that tag.
A revived Path C (post-v2.2.xxx) would require: (1) re-architecting tool-list to be identical across all wave children, (2) cache-telemetry analysis confirming the new fork-cache behaviour holds, (3) prompt-level deny re-enablement to compensate for tool scoping rollback.
Observability
Claude Code's own OpenTelemetry (CLAUDE_CODE_ENABLE_TELEMETRY) gives tool durations, tokens and cost per agent and skill: see Monitoring usage (read 2026-11-07, Claude Code 2.1.319).