From 4edd7dfd010ef32aa384f32d545e82f77d7b8f1a Mon Sep 17 00:00:00 2001 From: Daniel JB Clark Date: Sun, 1 Nov 2026 01:46:41 -0400 Subject: [PATCH 1/2] AGENTS: astra was not short; decide 'short' with an acp-dispatch dry-run, never from config --- AGENTS.md | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index bb364ae..79681d2 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -66,9 +66,14 @@ 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 From b47515ec0b156a2353a378dfb75a45aeda84ccac Mon Sep 17 00:00:00 2001 From: Daniel JB Clark Date: Sun, 1 Nov 2026 01:49:37 -0400 Subject: [PATCH 2/2] AGENTS: correction tightened per astra review --- AGENTS.md | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 79681d2..06c544b 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -66,14 +66,23 @@ 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