feat(analyze): prime analyst engine — --analyzer prime posts the span projection to an OpenAI-compatible bridge

[drewstone]

What

traces analyze --analyzer prime: any captured session can now be analyzed by the prime-RLM arm. Registered at the external-engine seam (ExternalAnalyzer), deliberately not the agentic dspy seam — prime here is a one-shot model call with no REPL/tools, and registering it as an agentic engine would misrepresent its execution model (seam map with file:line in the commit).

The engine posts the span projection to an OpenAI-compatible bridge (cli-bridge prime backend), using the proven protocol: short-strings finding contract, one bounded repair turn (malformed reply forwarded, trajectory never), per-attribute-cap re-render for oversized projections, findings decoded with exact-key + span-URI grounding against the artifact. Additive only — default analyze behavior byte-identical.

Includes a review fix: the per-finding span_ids cap is now enforced on the deduplicated list (was 2× the documented contract pre-dedup; found by the adversarial verifier).

Proof

• 15/15 new engine tests (fake bridge; happy/null/repair/fail/HTTP/transport/oversized/rejected-rows paths).
• Full suite 640/640 (baseline main was 625/625 — +15, zero regressions); typecheck + DTS build clean.
• Docs: analyzer section extended with prerequisites (running cli-bridge prime backend), example command, and a cross-link: the scored prime-vs-dspy comparison lives in agent-eval's analyst benchmark.

Named follow-up

A registryBenchmarkRunner adapter wrapping this engine for scored benchmark runs belongs in agent-eval, not here.

[tangletools]

✅ Auto-approved drewstone PR — 4ac1ff1f

This PR was opened by the trusted drewstone account.
The full PR reviewer audit still runs separately and will publish findings if it detects issues.

_{tangletools · auto-approval · reason: drewstone_author · 2026-08-08T03:43:07Z}

[tangletools]

⚪ Value Audit — audit-incomplete

Verdict	audit-incomplete
Concerns	1 (1 low)
Heuristic	0.0s
Duplication	0.1s
Interrogation	90.0s (2 bridge agents)
Total	90.1s

💰 Value — error

value agent produced no parseable value-audit JSON.

• Model: opencode/deepseek/deepseek-v4-pro
• Bridge attempts: 3
• Bridge error: opencode/kimi-for-coding/k2p7: Bridge returned 503: {"error":{"message":"cli-bridge admission timed out after 30000ms","type":"admission_rejected","reason":"queue_timeout","admission":{"active":20,"queued":2,"maxActive":20,"maxQueue":48}}}; opencode/zai-coding-plan/glm-5.2: Bridge returned 503: {"error":{"message":"cli-bridge admission timed out after 30000ms","type":"admission_rejected","reason":

🎯 Usefulness — error

usefulness agent produced no parseable value-audit JSON.

• Model: opencode/deepseek/deepseek-v4-pro
• Bridge attempts: 3
• Bridge error: opencode/zai-coding-plan/glm-5.2: Bridge returned 503: {"error":{"message":"cli-bridge admission timed out after 30000ms","type":"admission_rejected","reason":"queue_timeout","admission":{"active":20,"queued":2,"maxActive":20,"maxQueue":48}}}; opencode/kimi-for-coding/k2p7: Bridge returned 503: {"error":{"message":"cli-bridge admission timed out after 30000ms","type":"admission_rejected","reason":

🔎 Heuristic Signals

🟡 Cruft: console debug added examples/external-engines.ts

+console.log(

---

What this audit checks

It judges the change on its merits — not whether it was tasked out in an issue. Unticketed, fast-moving work is fine; the question is whether the change is good and whether a better or existing approach should be used instead.

Pass	What it asks
Heuristic	Vague title? Whitespace-only or cruft-bearing diff? (content signals only)
Duplication	Do added function/class names already exist elsewhere in the repo?
Value Audit	What does it do? What goal does it achieve? Is it good? Better architecture or already-exists?
Usefulness Audit	Does it integrate and fit? Will it hold up in real use and actually get used?

Findings are concerns, not blocks — the human reviewer decides what to do with them.

_{value-audit · 20260808T034628Z}