open/voyage
1
0
Fork 0
Code Issues Releases 2 Activity

docs(voyage): S15 — cost-claim truth-pass + premium default-profile pins

Browse source 
Resolve the S14 default-profile contradiction. Investigation overturned
the audit addendum's guess ("code is the bug → balanced"): commit 40d8742
(2026-05-13, "pin all sub-agents to Opus permanently (operator request)")
plus VOYAGE_PROFILE=premium in ~/.zshenv establish premium as the deliberate
default. Operator confirmed in-session: premium is the shipped default; fix
the stale docs, not the code. No code or behaviour changed (lib/ untouched).

Docs (default-name → premium, consistent across resolver + all three docs):
- README + docs/profiles.md + docs/operations.md: 3 lookup-order sites and
  3 profile tables now mark `premium` as the default.
- premium table row corrected to all-opus (matches premium.yaml — a third
  inconsistency the audit missed; README/profiles.md showed opus/sonnet/...).

Cost narrative made honest (premium = all-Opus reality):
- §Cost profile rewritten: uniform model per phase, no orchestrator-vs-swarm
  split; cheaper via --profile balanced/economy.
- Removed false "Sonnet exploration/review swarm" claims (README 195/223/266
  model-neutral; 804 parenthetical; the "Switch the planning model" note).
- profiles.md custom-profile prose corrected: built-in wins over same-named
  custom (findProfilePath), dropping the bogus "balanced is the locked default".

Pins (TDD red→green, doc-consistency.test.mjs):
- default-profile name invariant (resolveProfile ↔ README/profiles/operations)
- profile tables ↔ each built-in yaml phase_models (structural, catches drift)
- cost-claim regression guard (no resurrected Sonnet-swarm phrasing)

S16/S18 surface untouched: counts (23 agents, 9/10 dims, 5/6 dims), versions,
framing gates unchanged. Full suite 686 (684 pass / 2 skip / 0 fail).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
This commit is contained in:
Kjell Tore Guttormsen 2026-06-18 21:06:36 +02:00
commit 7a5749ddcc
4 changed files with 108 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

24
README.md
View file

@ -192,7 +192,7 @@ If you say "stop" or "enough" during Phase 4, the current review findings are su
Deep, multi-phase research that combines local codebase analysis with external knowledge. Uses specialized agent swarms to investigate multiple dimensions in parallel, then triangulates findings.
A parallel swarm of up to 5 local + 4 external Sonnet agents investigates 3–8 research dimensions, with optional Gemini Deep Research as an independent second opinion. Findings are triangulated (local vs. external, confidence per dimension, contradictions flagged) and synthesized into a structured research brief.
A parallel swarm of up to 5 local + 4 external agents investigates 3–8 research dimensions, with optional Gemini Deep Research as an independent second opinion. Findings are triangulated (local vs. external, confidence per dimension, contradictions flagged) and synthesized into a structured research brief.
Output:
- With `--project <dir>`: `{dir}/research/{NN}-{slug}.md` (auto-incremented index)
@ -220,7 +220,7 @@ Research uses up to 5 local agents (architecture-mapper, dependency-tracer, task
Produces an implementation plan detailed enough for autonomous execution. **v2.0 breaking change:** requires `--brief` or `--project`. There is no longer an interview inside `/trekplan` — use `/trekbrief` first.
After `brief-reviewer` validates the input brief, 6–8 Sonnet exploration agents analyze the codebase in parallel and merge findings into a synthesis. Optional research briefs (`--research`, or auto-discovered in `{project_dir}/research/`) enrich the plan; `architecture/overview.md` priors are loaded if an opt-in upstream architect plugin (not bundled) produced one. Opus then writes the plan with per-step YAML manifests, which `plan-critic` (9 dimensions) and `scope-guardian` adversarially review before handoff.
After `brief-reviewer` validates the input brief, 6–8 exploration agents analyze the codebase in parallel and merge findings into a synthesis. Optional research briefs (`--research`, or auto-discovered in `{project_dir}/research/`) enrich the plan; `architecture/overview.md` priors are loaded if an opt-in upstream architect plugin (not bundled) produced one. Opus then writes the plan with per-step YAML manifests, which `plan-critic` (9 dimensions) and `scope-guardian` adversarially review before handoff.
Output:
- With `--project <dir>`: `{dir}/plan.md`
@ -263,7 +263,7 @@ Every implementation step includes:
- **Checkpoint:** — git commit after success
- **Manifest:** — the objective completion predicate (Hard Rule 17)
Exploration uses 6–8 Sonnet agents in parallel (architecture-mapper, dependency-tracer, task-finder, test-strategist, git-historian, risk-assessor, plus convention-scanner on medium+ codebases and research-scout when unfamiliar tech is detected). Adversarial review then runs `brief-reviewer`, `plan-critic` (9 dimensions, no-placeholder enforcement, manifest audit), and `scope-guardian` (creep + gap detection). Per-agent details in [`agents/`](agents/).
Exploration uses 6–8 agents in parallel (architecture-mapper, dependency-tracer, task-finder, test-strategist, git-historian, risk-assessor, plus convention-scanner on medium+ codebases and research-scout when unfamiliar tech is detected). Adversarial review then runs `brief-reviewer`, `plan-critic` (9 dimensions, no-placeholder enforcement, manifest audit), and `scope-guardian` (creep + gap detection). Per-agent details in [`agents/`](agents/).
---
@ -755,16 +755,16 @@ Three built-in model profiles plus operator-defined `<custom>.yaml` (drop in `li
| Profile | Brief | Research | Plan | Execute | Review | Continue | Use case |
|---------|-------|----------|------|---------|--------|----------|----------|
| `economy` | sonnet | sonnet | sonnet | sonnet | sonnet | sonnet | Lowest cost; high-confidence small-scope tasks |
| `balanced` (default) | sonnet | sonnet | opus | sonnet | opus | sonnet | Default — opus where reasoning depth pays off |
| `premium` | opus | sonnet | opus | sonnet | opus | sonnet | Critical-path planning + review when budget allows |
| `economy` | sonnet | sonnet | sonnet | sonnet | sonnet | sonnet | Lowest cost; high-confidence small-scope tasks (opt-in via `--profile economy`) |
| `balanced` | sonnet | sonnet | opus | sonnet | opus | sonnet | Mixed — opus where reasoning depth pays off (opt-in via `--profile balanced`) |
| `premium` (default) | opus | opus | opus | opus | opus | opus | Maximum quality — Opus on every phase (default since the 2026-05-13 operator decision) |
Lookup order:
1. Explicit `--profile <name>` flag passed to the command
2. Plan-file frontmatter `profile:` (when resuming via `/trekexecute --resume` or `/trekcontinue`)
3. `VOYAGE_PROFILE` environment variable
4. Default `balanced`
4. Default `premium`
See [`docs/profiles.md`](docs/profiles.md) for the decision tree, custom-profile authoring, and cost estimation disclaimer (the per-profile cost numbers are *anslag*, not contractual SLAs).
@ -782,7 +782,7 @@ Default JSONL stats stream (`${CLAUDE_PLUGIN_DATA}/trek*-stats.jsonl`) is unchan
## Cost profile
Opus runs the orchestrators (one per command) and the executor (one per plan session). Sonnet runs the exploration and review swarms (5–10 agents per command, with effort/turn limits). The pipeline front-loads cheap Sonnet work so Opus only does synthesis and execution. Typical total: comparable to a long single Claude Code session — the per-command cost is published in `${CLAUDE_PLUGIN_DATA}/trek*-stats.jsonl` if you want exact numbers.
The default `premium` profile runs **Opus on every phase** — the orchestrator (one per command), the exploration and review swarms (5–10 sub-agents per command, all `model: opus`-pinned in `agents/*.md`), and the executor (one per plan session). The model is **uniform per phase**: there is no "Opus orchestrates, Sonnet runs the swarms" split — a phase resolves to one model and both the orchestrator and its sub-agents use it. For cheaper runs, opt into `--profile balanced` (Sonnet on brief/research/execute/continue, Opus on plan + review) or `--profile economy` (Sonnet everywhere). Per-command cost is published in `${CLAUDE_PLUGIN_DATA}/trek*-stats.jsonl` if you want exact numbers.
The `opus` alias resolves to **Opus 4.8** (default reasoning effort `high`) and `sonnet` to Sonnet 4.6. Note two distinct effort axes that share the word "effort": brief `phase_signals.effort` (low/standard/high) tunes *orchestration shape* — how many agents and passes run — while native `effort:` on selected agents (retrieval at `medium`, adversarial-reasoning at `high`) tunes the *per-spawn reasoning budget*. See [`docs/profiles.md`](docs/profiles.md) § Model & effort axes.
@ -801,7 +801,7 @@ Top-level layout:
```
trekplan/
├── agents/ 23 specialized agents (sonnet for exploration + review, opus for orchestration)
├── agents/ 23 specialized agents (all `model: opus`-pinned; per-phase model set by `--profile`)
├── commands/ 6 slash commands (trekbrief, trekresearch, trekplan, trekexecute, trekreview, trekcontinue) + trekplan-end-session helper
├── templates/ Frontmatter templates for brief, research, plan, session, launch
├── hooks/ 5 hooks (pre-bash, pre-write, session-title, post-bash-stats, pre-compact-flush)
@ -844,7 +844,7 @@ synthesis.
The default for `/trekbrief`, `/trekresearch`,
`/trekplan`, and `/trekexecute` is `opus` (deep
reasoning). To run on Sonnet for cost or latency, search-and-replace
the frontmatter in three files:
the frontmatter in these four command files:
```bash
sed -i.bak 's/^model: opus$/model: sonnet/' \
@ -854,7 +854,9 @@ sed -i.bak 's/^model: opus$/model: sonnet/' \
commands/trekexecute.md
```
The exploration agents stay on Sonnet — only the orchestrator is bumped.
This flips only the four command orchestrators. The exploration and review
sub-agents in `agents/*.md` are separately `opus`-pinned — flip those too, or
just run `--profile economy`, to put the whole pipeline on Sonnet.
### Disable external research