|
|
@@ -8,7 +8,7 @@ English | [中文](2026-09-12-ralph-off-in-shipped-defaults.zh.md)
|
|
|
|
|
|
The `ralph` tool runs a fixed foreground loop of fresh, unseeded child agents and returns when a worker reports completion or a concrete blocker. Its own model-facing description restricts it to runs the direct human explicitly asked for, and its README records that completion is a worker self-declaration with no independent evaluator and that the loop has no background collection, resume checkpoint, or scheduler.
|
|
|
|
|
|
-That tool shipped enabled in `packages/bundle/base/cordis.patch.yml` and in three of the four shipped agent presets. A default session therefore carried a tool whose own description told the model not to reach for it, and the default profile's catalog advertised a capability the Harness does not yet stand behind.
|
|
|
+That tool shipped enabled in `packages/bundle/base/cordis.patch.yml` and in three of the four shipped agent presets. A default session therefore carried a tool whose own description told the model not to reach for it, and the default profile's catalog advertised a capability the Harness does not yet stand behind. The [shipped tool roster](../feature/2026-07-31-even-out-shipped-tool-rosters.md) decision assembled that base roster and lists each later narrowing; this is one more entry in that list.
|
|
|
|
|
|
## Decision
|
|
|
|
|
|
@@ -16,7 +16,7 @@ That tool shipped enabled in `packages/bundle/base/cordis.patch.yml` and in thre
|
|
|
|
|
|
The `ptc` preset also declares `workflow-worker-thread` disabled. That preset kept the engine for `ralph` alone after it dropped the general `workflow` tool, so disabling `ralph` left the engine with no consumer in that composition.
|
|
|
|
|
|
-Each disabled row carries its restore recipe in a local comment. An overlay row re-enables the capability for a base-backed profile from `$DSH_HOME/cordis.patch.yml` or a `--patch` file. Preset files take no patches (`packages/preset/agent-presets/README.md`), so a Web session that wants `ralph` duplicates the preset into `$DSH_HOME/.agent-presets` and drops `disabled`; in `ptc` that means the tool row and the engine row together, because `tool-ralph` injects `ctx.workflowEngine`.
|
|
|
+Each disabled row carries its restore recipe in a local comment. An overlay row re-enables the capability for a base-backed profile from `$DSH_HOME/cordis.patch.yml` or a `--patch` file. Preset files take no patches (`packages/preset/agent-presets/README.md`), so a Web session that wants `ralph` duplicates the preset under a **new id** into `$DSH_HOME/.agent-presets` and drops `disabled`; a copy reusing the shipped id is shadowed by the shipped root, which wins duplicate ids (`packages/preset/agent-presets/src/index.ts`), and `copy()` refuses an id any root already supplies. In `ptc` the duplicate drops `disabled` from the tool row and the engine row together, because `tool-ralph` injects `ctx.workflowEngine`.
|
|
|
|
|
|
`packages/bundle/web-app/cordis.patch.yml` keeps its own `tool-ralph` disable even though `base` now ships the row off. `validatePresetPlaneSeparation` in `scripts/verify-cordis-config.ts` collects declared row ids without regard to `disabled`, so deleting that row would return `tool-ralph` to the Web host plane and collide with the same id in every preset.
|
|
|
|
|
|
@@ -44,6 +44,6 @@ A default Web, headless, sdk, acp, or custom base-backed session no longer offer
|
|
|
|
|
|
## Verification
|
|
|
|
|
|
-`packages/preset/agent-presets/tests/shipped-root.spec.ts` pins that every preset carrying `tool-ralph` disables it, that `ptc` disables `workflow-worker-thread`, and that `standard` and `cordis` keep the engine enabled for their `workflow` tool. `apps/cli/tests/web-agent-presets.e2e.ts` and `apps/web/tests/shipped-composition.e2e.ts` pin the exact default and PTC tool catalogs, so a row that stops contributing is a test failure rather than a silently shorter list. `scripts/verify-cordis-config.ts` continues to pass its plane-separation check against the disabled rows.
|
|
|
+`packages/preset/agent-presets/tests/shipped-root.spec.ts` pins that every preset carrying `tool-ralph` disables it, that the `minimal` roster carries no such row, that `ptc` disables `workflow-worker-thread`, and that `standard` and `cordis` keep the engine enabled for their `workflow` tool. `apps/cli/tests/web-agent-presets.e2e.ts` and `apps/web/tests/shipped-composition.e2e.ts` pin the exact default and PTC tool catalogs, so a row that stops contributing is a test failure rather than a silently shorter list. `scripts/verify-cordis-config.ts` continues to pass its plane-separation check against the disabled rows.
|
|
|
|
|
|
-Every affected recorded-session sidecar was refreshed with `pnpm run test:snapshot:refresh`, and `pnpm run test:snapshot` replays the corpus. `snapshots/session/ralph-loop` passes under its own composition patch, which is the evidence that the demotion removed the row from the defaults without removing coverage of the tool.
|
|
|
+Most affected recorded-session sidecars were regenerated with `DSH_SNAPSHOT=refresh pnpm run test:snapshot`, and `pnpm run test:snapshot` replays the corpus. Six sidecars were curated by hand instead, because no local run produces them. Four belong to `pwsh-tool-turn` and `persistent-pwsh-tool-turn`, which this host skips for a missing `pwsh`; their removed text is byte-identical to what the refresh removed elsewhere. The remaining two are `snapshots/web/schedule-catalog`, which no executing test writes or reads: `schedule-after.e2e.ts` reads only that directory's `catalog.expected.md` and `session.v3.jsonl`, and `assertFixtureInventory` checks only that the four files exist, so the `header.pin: true` in its `snapshot.yml` is not enforced. `snapshots/session/ralph-loop` passes under its own composition patch, which is the evidence that the demotion removed the row from the defaults without removing coverage of the tool.
|
Tianyi Cui