From 8ad396116ebdb181016b77d360ae58f352112a92 Mon Sep 17 00:00:00 2001 From: claude Date: Sat, 25 Jul 2026 17:02:35 +0200 Subject: [PATCH] fix(fieldtest): probe tier runs on the frontmatter opus model The owner reviewed the recorded design-review dissent on the probe tier's sonnet override and agreed with it: field evidence is a rule-2 judgement role, and the probe cut lacks the deterministic measurement + verify gate the issue-#30 override rests on. The probe tier keeps its scope economy (1-2 examples on the single delta axis, capped report) and drops the model override; agent-template rule 2 loses the conditioned exception. refs #35 --- docs/agent-template.md | 14 ++++---------- fieldtest/SKILL.md | 22 ++++++++++------------ 2 files changed, 14 insertions(+), 22 deletions(-) diff --git a/docs/agent-template.md b/docs/agent-template.md index 7de8273..4e0ea2a 100644 --- a/docs/agent-template.md +++ b/docs/agent-template.md @@ -136,16 +136,10 @@ Assignment rule, in priority order: gating a cycle (adversarial lenses, plan recon, field/bench evidence, the in-loop quality review) — run `opus`. Opus is the documented strength for code review, debugging, and deep - reasoning. One conditioned exception (issue #35): the - per-cycle fieldtest's **probe tier** — the cycle's - user-visible delta is a single narrow axis — is dispatched by - the `fieldtest` skill with an explicit `model: sonnet` - dispatch override; the one-axis scope bounds the judgement - surface and the orchestrator triages every finding anyway. - The frontmatter keeps the opus default, which the milestone - fieldtest always runs. (The direct agent-dispatch surface has - no per-dispatch *effort* override, so the frontmatter effort - applies unchanged on a probe.) + reasoning. This rule covers the fieldtest's probe tier too: + a probe narrows *scope*, never the model (a sonnet probe + override was ratified and same-day retracted on review + grounds — issue #35). 3. **Mechanical scope** — tightly-scoped execution of a pre-made plan, recon, extraction, compliance-diffing run `sonnet` (near-opus coding quality at lower latency and cost). diff --git a/fieldtest/SKILL.md b/fieldtest/SKILL.md index 7b34d5a..8aed89c 100644 --- a/fieldtest/SKILL.md +++ b/fieldtest/SKILL.md @@ -86,18 +86,16 @@ probe merely right-sizes the dispatch when the surface delta is one axis. A multi-axis cycle takes the full tier — when in doubt, full. -**Probe dispatch mechanics.** A probe dispatch passes an -explicit `model: sonnet` override on the agent dispatch — the -dispatch-level model override takes precedence over the agent's -opus frontmatter; the conditioned exception is documented in -`../docs/agent-template.md` § model, rule 2. (The direct -agent-dispatch surface has no per-dispatch effort override, so -the frontmatter effort applies unchanged; the probe's economy -comes from the model tier and the one-axis scope.) The -judgement surface a probe covers is one axis, and the -orchestrator triages every finding anyway. The **milestone -fieldtest always runs full tier on the frontmatter model** — its -carrier takes no `tier` field. +**Both tiers run on the agent's frontmatter model.** A probe +dispatch changes scope, not model: its economy comes from the +one-axis cut and the capped report, while finding classification +stays on the opus judgement tier. (A `model: sonnet` probe +override was ratified and same-day retracted on review grounds — +field evidence is a judgement role per +`../docs/agent-template.md` § model rule 2, and the probe cut +lacks the deterministic gate the issue-#30 override rests on; +recorded on issue #35.) The **milestone fieldtest always runs +full tier** — its carrier takes no `tier` field. ## When to Use / Skipping