From abe6184effe74bdf0a81889f4a18be0d4ec5afe8 Mon Sep 17 00:00:00 2001 From: Daniel JB Clark Date: Sun, 1 Nov 2026 01:46:37 -0400 Subject: [PATCH 1/2] AGENTS + spec: astra was not short; decide 'short' with an acp-dispatch dry-run, never from config --- AGENTS.md | 11 ++++++++--- .../schema-v4-reconciliation-2026-10-31.md | 6 ++++-- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index d008160..4ea658f 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -59,9 +59,14 @@ overridden. Never use `route-override`, `--est-pct`, `--min-headroom 0` or wont-fit, inflight, headroom or preflight), when `aiuse --available --json` lists it `usable_now: false`, or, for Argon, when `acp-run agy` fails on quota. Short means move to the next model in the order, never force it. - Say in the PR body which model was short and why. As of 2026-10-31 astra - is short: Codex has 45% left, below the 60% `codex:frontier` estimate - floor, so Fable takes the first seat. + Say in the PR body which model was short and why. **Decide "short" by + running it, never from config:** `acp-dispatch ... --dry-run` with the + real `-C` prints `would refuse` when the pool is short. The + `codex:frontier` estimate comes from measured history (about 2% of the + weekly window per astra review, 2026-11-01); its 60% default applies only + with fewer than three measured slices. On 2026-10-31 a lead read that + default from the config, called astra short at 45%, and sent every review + to Fable or Argon, though astra was available. - Design rulings (a `schema_version` bump, the privilege or enforcement scope on a host, a deploy plan, the unit-writer or consent-diff design) get two independent frontier reviews, astra and Fable. Argon stands in diff --git a/docs/architecture/schema-v4-reconciliation-2026-10-31.md b/docs/architecture/schema-v4-reconciliation-2026-10-31.md index 4dd947b..339085c 100644 --- a/docs/architecture/schema-v4-reconciliation-2026-10-31.md +++ b/docs/architecture/schema-v4-reconciliation-2026-10-31.md @@ -5,8 +5,10 @@ It supersedes its three inputs, which stay frozen as written: [the Opus 5.5 draft](schema-v4-opinion-opus-draft.md), the [Fable 5.1 review](schema-v4-opinion-fable.md) and the [Gemini 4 Argon review](schema-v4-opinion-argon.md). Argon took the seat that the -standing rule gives to astra, because astra was short (Codex had 45% left, below the -60% `codex:frontier` estimate floor). The standing rule is in `AGENTS.md` on PR +standing rule gives to astra. The lead believed astra was short, inferring it from the +60% `codex:frontier` default in the config. That was wrong: the dispatch estimate comes +from measured history, and a dry-run on 2026-11-01 admitted astra at 41%. Both +reviews are still cross-model. The standing rule is in `AGENTS.md` on PR https://github.com/frdminc/tendcf/pull/24 and was reviewed there. Where an input is wrong, §8 says so; the inputs are not corrected in place. This document was itself reviewed by Fable 5.1 (approve with changes); those changes are applied. From 32e5b3f53dc20e487d2a42fe7aca55079fc877ab Mon Sep 17 00:00:00 2001 From: Daniel JB Clark Date: Sun, 1 Nov 2026 01:49:33 -0400 Subject: [PATCH 2/2] AGENTS + spec: correction tightened per astra review (dry-run limits, per-window fallback, no availability claim) --- AGENTS.md | 25 +++++++++++++------ .../schema-v4-reconciliation-2026-10-31.md | 8 +++--- 2 files changed, 21 insertions(+), 12 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 4ea658f..ddefc0a 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -59,14 +59,23 @@ overridden. Never use `route-override`, `--est-pct`, `--min-headroom 0` or wont-fit, inflight, headroom or preflight), when `aiuse --available --json` lists it `usable_now: false`, or, for Argon, when `acp-run agy` fails on quota. Short means move to the next model in the order, never force it. - Say in the PR body which model was short and why. **Decide "short" by - running it, never from config:** `acp-dispatch ... --dry-run` with the - real `-C` prints `would refuse` when the pool is short. The - `codex:frontier` estimate comes from measured history (about 2% of the - weekly window per astra review, 2026-11-01); its 60% default applies only - with fewer than three measured slices. On 2026-10-31 a lead read that - default from the config, called astra short at 45%, and sent every review - to Fable or Argon, though astra was available. + Say in the PR body which model was short and why. **Check the actual + dispatch, never infer availability from the config alone.** Run the + intended command with `--dry-run`, preserving its model, kind, effort, + brief, `-C` and output/task directory. Inspect `would refuse: class=...` + (or `would_refuse_class` with `--json`), not just the exit status: + dry-run returns 0 for predicted headroom, fit and concurrency refusals. + It skips preflight, so no predicted refusal is not proof of availability; + the real dispatch must still pass its checks. The `codex:frontier` + estimate uses comparable measured history: on 2026-11-01 the selected + machine-wide history for astra at high effort held 14 matching records, + and the scalar and weekly-window estimates were both 2 percentage points + (upper median). The configured 60% fallback floor applies when the + selected history has fewer than three measurements for the scalar or the + relevant quota window; three measurements overall do not release every + window's floor. On 2026-10-31 a lead treated the configured 60% fallback + as a permanent minimum and declared astra short at 45% remaining. That + comparison alone did not establish that astra was short. - Design rulings (a `schema_version` bump, the privilege or enforcement scope on a host, a deploy plan, the unit-writer or consent-diff design) get two independent frontier reviews, astra and Fable. Argon stands in diff --git a/docs/architecture/schema-v4-reconciliation-2026-10-31.md b/docs/architecture/schema-v4-reconciliation-2026-10-31.md index 339085c..ee06981 100644 --- a/docs/architecture/schema-v4-reconciliation-2026-10-31.md +++ b/docs/architecture/schema-v4-reconciliation-2026-10-31.md @@ -5,10 +5,10 @@ It supersedes its three inputs, which stay frozen as written: [the Opus 5.5 draft](schema-v4-opinion-opus-draft.md), the [Fable 5.1 review](schema-v4-opinion-fable.md) and the [Gemini 4 Argon review](schema-v4-opinion-argon.md). Argon took the seat that the -standing rule gives to astra. The lead believed astra was short, inferring it from the -60% `codex:frontier` default in the config. That was wrong: the dispatch estimate comes -from measured history, and a dry-run on 2026-11-01 admitted astra at 41%. Both -reviews are still cross-model. The standing rule is in `AGENTS.md` on PR +standing rule gives to astra. The lead called astra short by comparing Codex's 45% +remaining with the 60% `codex:frontier` fallback in the config. That comparison did not +establish it: the dispatch estimate uses measured history, and an astra review dispatched +on 2026-11-01 at 41% was admitted. Both reviews are still cross-model. The standing rule is in `AGENTS.md` on PR https://github.com/frdminc/tendcf/pull/24 and was reviewed there. Where an input is wrong, §8 says so; the inputs are not corrected in place. This document was itself reviewed by Fable 5.1 (approve with changes); those changes are applied.