docs(changelog): ceiling rule and deploy row
This commit is contained in:
1 parent
ef13713f09
commit
887cf89004
1 file changed
+2
-1
+2
-1
@@ -22,7 +22,8 @@ Format follows [Keep a Changelog](https://keepachangelog.com/) and this project
|
|||||||
- model-router `verbose: true` logs transitions only: one line when main changes model or effort (`model-router: main: fable/high → fable/xhigh (plan: route tool)`), one hand-off line per dispatch and one per later effort move of an agent, each with its cause; the per-step, "answered by", spawn, route-tool and skill-path lines are gone. An agent answering on a model other than the planned one is said once. A non-boolean `verbose` falls back to `false`, said once.
|
- model-router `verbose: true` logs transitions only: one line when main changes model or effort (`model-router: main: fable/high → fable/xhigh (plan: route tool)`), one hand-off line per dispatch and one per later effort move of an agent, each with its cause; the per-step, "answered by", spawn, route-tool and skill-path lines are gone. An agent answering on a model other than the planned one is said once. A non-boolean `verbose` falls back to `false`, said once.
|
||||||
- `verifier` and `security-auditor` run on a new `audit` phase (best/xhigh: Fable, Opus when Fable is down). Their frontmatter floor is `model: opus` (the verifier was `sonnet`): a fable floor would spawn the gates on a dead model during a credit outage. `judge` (big/xhigh, opus) keeps plan-challenger, analyzer and plugin-advisor. The `about` lines of `judge` and `verify` no longer claim audits or security review. The census `lib/tests/effort-routing.test.sh` floors a best-tier agent row on the tier's second alias (opus).
|
- `verifier` and `security-auditor` run on a new `audit` phase (best/xhigh: Fable, Opus when Fable is down). Their frontmatter floor is `model: opus` (the verifier was `sonnet`): a fable floor would spawn the gates on a dead model during a credit outage. `judge` (big/xhigh, opus) keeps plan-challenger, analyzer and plugin-advisor. The `about` lines of `judge` and `verify` no longer claim audits or security review. The census `lib/tests/effort-routing.test.sh` floors a best-tier agent row on the tier's second alias (opus).
|
||||||
- `settings.json` session model `claude-fable-5-1[1m]` → `opus`: sessions start on Opus, and Fable is reached through the best-tier rows.
|
- `settings.json` session model `claude-fable-5-1[1m]` → `opus`: sessions start on Opus, and Fable is reached through the best-tier rows.
|
||||||
- `/deploy` runs on the `verify` row (sonnet/xhigh, was `apply` sonnet/low) by a first-use decision.
|
- Doctrine ceiling: the main loop on Fable writes no code past the `/hotfix` scope and hands larger work to `/feat` or `/bugfix` (Sub-agents rule in `CLAUDE.global.md`). README and the plan-challenge citers (`lib/challenge-plan.md`, `agents/plan-challenger.md`) now say the main loop runs on the `opus` session model and reaches Fable through best-tier rows.
|
||||||
|
- `/deploy` runs on the `verify` row (sonnet/xhigh, was `apply` sonnet/low). The row ships as such, its `changed` entry is dropped from `routing.json`, and the frontmatter floor follows (`effort: xhigh`).
|
||||||
- `lib/model-gate.md` calls the model-router `route` tool and takes its answer as the witness; with the mod off the gate stops and names `/route on`. The `model:` / `effort:` frontmatter of agents and skills is now the off-state floor, census-locked equal to the rows (`lib/tests/effort-routing.test.sh`; a row changed through the first-use dialog passes with a `WARN floor drift` line while its frontmatter still holds the shipped value). `analyzer` effort goes from high to xhigh. Built-in judgment dispatches carry an explicit `effort=`.
|
- `lib/model-gate.md` calls the model-router `route` tool and takes its answer as the witness; with the mod off the gate stops and names `/route on`. The `model:` / `effort:` frontmatter of agents and skills is now the off-state floor, census-locked equal to the rows (`lib/tests/effort-routing.test.sh`; a row changed through the first-use dialog passes with a `WARN floor drift` line while its frontmatter still holds the shipped value). `analyzer` effort goes from high to xhigh. Built-in judgment dispatches carry an explicit `effort=`.
|
||||||
- `settings.json` denies every write form of the human-only `gitflow.*` keys (18 entries): any `git … config` spelling, section remove/rename, `git -c`, the git config env overrides, and Edit/Write of `.git/config`, `.gitconfig` and `~/.config/git/config`. Side effect: Claude can no longer read `gitflow.autopush` through `git config` either; hooks and `lib/gitflow.sh` still read it. The `hard_deny` rule on routing around a guardrail now names PreToolUse hook refusals.
|
- `settings.json` denies every write form of the human-only `gitflow.*` keys (18 entries): any `git … config` spelling, section remove/rename, `git -c`, the git config env overrides, and Edit/Write of `.git/config`, `.gitconfig` and `~/.config/git/config`. Side effect: Claude can no longer read `gitflow.autopush` through `git config` either; hooks and `lib/gitflow.sh` still read it. The `hard_deny` rule on routing around a guardrail now names PreToolUse hook refusals.
|
||||||
- `gitflow start` and `finish` warn on stderr when a base is behind origin and cannot fast-forward, instead of a silent `git pull --ff-only || true` (T18l, T18n).
|
- `gitflow start` and `finish` warn on stderr when a base is behind origin and cannot fast-forward, instead of a silent `git pull --ff-only || true` (T18l, T18n).
|
||||||
|
|||||||
Reference in new issue
Block a user