feat(trekresearch): add Phase 4.5 dimension discovery and amend Independence rule

This commit is contained in:
Kjell Tore Guttormsen 2026-08-09 14:58:48 +02:00
commit d9cba9c6ea
3 changed files with 121 additions and 5 deletions

View file

@ -7,12 +7,20 @@ tools: ["Read", "Glob", "Grep", "Write", "Edit", "Bash"]
---
<!-- Phase mapping: orchestrator → command
Corrected in v5.10: every row below was off by one, and the old last row
pointed at a ninth command phase that does not exist — the command ends
at Phase 8.
Orchestrator Phase 1 = Command Phase 4 (Agent group selection)
Orchestrator Phase 2 = Command Phase 5 (Parallel research)
Orchestrator Phase 3 = Command Phase 6 (Targeted follow-ups)
Orchestrator Phase 4 = Command Phase 7 (Triangulation)
Orchestrator Phase 5 = Command Phase 8 (Synthesis + write brief)
Orchestrator Phase 6 = Command Phase 9 (Completion)
Orchestrator Phase 2 = Command Phase 4 (Parallel research — same
command phase; the orchestrator
splits selection from launch)
(no orchestrator phase)= Command Phase 4.5 (Dimension discovery,
high effort only — v5.10)
Orchestrator Phase 3 = Command Phase 5 (Targeted follow-ups; bounded
conversation loop at high effort)
Orchestrator Phase 4 = Command Phase 6 (Triangulation)
Orchestrator Phase 5 = Command Phase 7 (Synthesis + write brief)
Orchestrator Phase 6 = Command Phase 8 (Present and track / completion)
As of v2.4.0, /trekresearch runs these phases inline in main
context instead of spawning this agent. Keep this file as the canonical
reference for what those phases do. -->

View file

@ -391,6 +391,34 @@ other agents — the value of Gemini is independence.
small = halved, medium/large = default
- convention-scanner: medium+ codebases only (50+ files)
## Phase 4.5 — Dimension discovery
**Skip this phase entirely unless `phase_signal_result.effort == 'high'`.**
Phase 4 retrieves more than the interview knew to ask for. This phase mines
that surplus: findings that were **retrieved but unintegrated** — material an
agent surfaced that no interview dimension claims.
1. **Mine.** Walk the Phase-4 agent results and collect findings that map to
no existing dimension.
2. **Rerank.** Order candidates by relevance to the research question **and**
dissimilarity to the dimensions already on the list. A candidate that
restates an existing dimension is not a discovery.
3. **Augment under the existing ceiling.** Append candidates to the dimension
list only while the **whole** list (interview + discovered) stays at or
below `maxDimensions: 8` (`settings.json:16`). The ceiling is **not**
raised here, so the documented 38 dimension range stays true and the
README prose about it stays untouched. If the interview already produced 8
dimensions, this phase discovers nothing and says so.
4. **Record the baseline.** Keep the interview-derived count as
`dimensions_baseline` so the discovered delta is machine-readable against
the final `dimensions` (Phase 8 stats).
Every outbound query generated from a discovered dimension passes
`query-privacy-gate.mjs` before it leaves the machine — see the per-turn
protocol in Phase 5. That gate is the compensating control for the
Independence crossing this phase makes (see Hard rules → Independence).
## Phase 5 — Targeted follow-ups
Review all agent results. Identify knowledge gaps — dimensions where findings
@ -727,6 +755,16 @@ Low effort: inline research only, no agent swarm (existing
- **Sources required:** Every claim must cite a source. No unsourced findings.
- **Independence:** Do not pre-bias external agents with local findings or vice versa.
Triangulate AFTER independent research.
**Amended (v5.10) for Phase 4.5:** dimension discovery deliberately crosses this
rule. Its candidate dimensions are mined from the Phase-4 result set, which
contains output from the five local codebase agents, so a discovered dimension
can carry local context into an external query. The crossing is bounded to
Phase 4.5 and the Phase 5 loop it feeds, it never applies to the initial
external swarm (which stays blind to local findings), and the compensating
control is `query-privacy-gate.mjs`: every outbound query is inspected before
it leaves the machine, with a hard-block tier for secret-shaped strings that no
operator flag can override. Triangulation still happens AFTER independent
research.
- **Graceful degradation:** If MCP tools are unavailable (Tavily, Gemini, MS Learn),
proceed with available tools and note limitations in brief metadata.
- **Cost:** Model resolution at Agent-spawn sites is a three-layer fallback:

View file

@ -166,6 +166,76 @@ test('trekresearch — High-effort behavior keeps the standard/low effort senten
);
});
// --- Step 8: Phase 4.5 dimension discovery + Independence amendment ---
const ORCHESTRATOR_FILE = join(ROOT, 'agents', 'research-orchestrator.md');
function readOrchestrator() { return readFileSync(ORCHESTRATOR_FILE, 'utf8'); }
test('trekresearch — Phase 4.5 exists between Phase 4 and Phase 5 with the effort skip-guard', () => {
const text = read();
const p45 = text.indexOf('## Phase 4.5 —');
assert.ok(p45 >= 0, 'Phase 4.5 heading missing');
const p4 = text.indexOf('## Phase 4 —');
const p5 = text.indexOf('## Phase 5 —');
assert.ok(p4 >= 0 && p5 > p45 && p45 > p4, 'Phase 4.5 must sit between Phase 4 and Phase 5');
const slice = text.slice(p45, p5);
assert.match(
slice,
/\*\*Skip this phase entirely unless `phase_signal_result\.effort == 'high'`\.\*\*/,
'Phase 4.5 must carry the bolded skip-guard in the Phase 3.5 form',
);
assert.match(slice, /query-privacy-gate\.mjs/,
'Phase 4.5 must name the privacy gate as its compensating control');
assert.match(slice, /maxDimensions: 8|maxDimensions` *: *8/,
'Phase 4.5 must augment under the existing maxDimensions ceiling, not raise it');
});
test('trekresearch — Independence hard rule carries an explicit Phase 4.5 amendment', () => {
const text = read();
const rulesIdx = text.indexOf('## Hard rules');
assert.ok(rulesIdx >= 0, 'Hard rules section missing');
const rules = text.slice(rulesIdx);
const indIdx = rules.indexOf('**Independence:**');
assert.ok(indIdx >= 0, 'Independence hard rule missing');
// Bound the rule at the next bullet so the amendment must live inside it.
const nextBullet = rules.indexOf('\n- **', indIdx);
const independence = nextBullet > indIdx ? rules.slice(indIdx, nextBullet) : rules.slice(indIdx);
assert.match(independence, /Amend(ed|ment)/i,
'Independence must be explicitly amended, not silently contradicted');
assert.match(independence, /Phase 4\.5/, 'the amendment must name Phase 4.5 as the crossing');
assert.match(independence, /query-privacy-gate\.mjs/,
'the amendment must name the compensating control');
});
test('trekresearch — orchestrator phase map is correct, has no Phase 9, and carries Phase 4.5', () => {
const doc = readOrchestrator();
const start = doc.indexOf('<!-- Phase mapping');
assert.ok(start >= 0, 'phase mapping comment missing');
const end = doc.indexOf('-->', start);
assert.ok(end > start, 'phase mapping comment not terminated');
const map = doc.slice(start, end);
assert.doesNotMatch(map, /Command Phase 9/,
'the command ends at Phase 8 — a Command Phase 9 row is a fiction');
// Six orchestrator rows, each pointing at the phase the command actually has.
const expected = [
[1, '4'],
[2, '4'],
[3, '5'],
[4, '6'],
[5, '7'],
[6, '8'],
];
for (const [orch, cmd] of expected) {
const re = new RegExp(`Orchestrator Phase ${orch}\\s+= Command Phase ${cmd.replace('.', '\\.')}\\b`);
assert.match(map, re, `map row for Orchestrator Phase ${orch} must point at Command Phase ${cmd}`);
}
assert.match(map, /Command Phase 4\.5/, 'the map must carry the new Phase 4.5 row');
});
// --- v5.1.1 runtime SC4 + SC7 ---
test('trekresearch — SC4: low-effort fixture → resolver returns {effort: low, model: sonnet}', () => {