mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge branch 'worktree/schedule-conversational-after' into worktree/schedule-explicit-at
# Conflicts: # packages/client/runtime/README.i18n.yaml # packages/client/runtime/README.md # packages/client/runtime/README.zh.md
This commit is contained in:
Tianyi Cui
@@ -24,7 +24,7 @@
|
||||
|
||||
Two planes decide where an edit belongs. The HOST composition holds the registries and anything shared across sessions — persistence, the sandbox and approval stack, the model route, the subagent registry and its backends. An AGENT PRESET holds what one session contributes to those registries: its tools, its persona, its prompt sections. A row that publishes a service belongs in the host composition, or inside an `isolate` realm if the preset genuinely owns that service and nothing outside one agent reads it.
|
||||
|
||||
Presets you author live under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/`, one directory per preset. NEVER edit or delete the shipped preset install (the `agent-presets` directory beside the deployment's own config): it belongs to the deployment, an upgrade overwrites it, and corrupting the `cordis` preset would disable this very mode. To change what a shipped preset does, copy its composition into a new preset directory and edit the copy.
|
||||
Presets you author live one directory per preset under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/`; the roster reports each preset's real path, so take the one you edit from there. NEVER edit or delete the shipped preset install (the `agent-presets` directory beside the deployment's own config): it belongs to the deployment, an upgrade overwrites it, and corrupting the `cordis` preset would disable this very mode. To change what a shipped preset does, copy its composition into a new preset directory and edit the copy.
|
||||
|
||||
Load the `editing-cordis-compositions` skill before writing or changing a composition.
|
||||
|
||||
|
||||
@@ -1,12 +1,18 @@
|
||||
---
|
||||
name: editing-cordis-compositions
|
||||
description: Use when creating or changing a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, or diagnosing a row that mounted but contributed nothing.
|
||||
description: Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.
|
||||
---
|
||||
|
||||
# Editing Cordis compositions
|
||||
|
||||
Every capability in this harness is a plugin row in a `cordis.yml`. There is no separate configuration language: changing what an agent can do means changing which rows are composed for it.
|
||||
|
||||
## Off-limits
|
||||
|
||||
**Never edit, delete, or overwrite a preset that ships with the deployment** — the `agent-presets` directory beside the deployment's own config, which supplies `standard`, `code`, `minimal`, and `cordis`. Never escalate the sandbox to reach it, even when a change there looks quicker. An upgrade overwrites that install, and corrupting `cordis` disables preset authoring itself. Reading a shipped composition is the intended way to start; writing to one is not, and neither is editing the host composition to work around a preset limitation.
|
||||
|
||||
To change what a shipped preset does, copy it and edit the copy. Locally authored presets under the user root are yours to create, edit, and delete.
|
||||
|
||||
## Decide the plane first
|
||||
|
||||
Two planes, and the choice is not about how "agent-related" something feels — it is about whether the thing must be shared.
|
||||
@@ -17,16 +23,105 @@ Two planes, and the choice is not about how "agent-related" something feels —
|
||||
|
||||
**A service with a consumer outside the agent plane cannot move into a preset.** `subagents` is the worked example: the registry answers cross-session queries for the host api-proxy, so a per-session copy both starves that host row — it waits forever for a service nothing provides — and collides on the second session, since a provider name registers once. The preset contributes the delegation *tools*; the registry and its backends stay host-side.
|
||||
|
||||
A preset is a directory holding one `agent.cordis.yml`, optionally beside a `preset.yml` carrying display metadata — `name` and `description` (and, for shipped presets, a roster `order`). Write the metadata too: a preset without it shows up in every picker as its bare directory name. The shipped presets live beside the deployment's composition; locally authored ones live under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<name>/`.
|
||||
A preset is a directory holding one `agent.cordis.yml`, optionally beside a `preset.yml` carrying display metadata — `name` and `description` (and, for shipped presets, a roster `order`). Write the metadata too: a preset without it shows up in every picker as its bare directory name.
|
||||
|
||||
Locally authored presets live one directory per preset under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/`, and the shipped set sits beside the deployment's own config. Use those when the user asks where to look. Both roots are configuration rather than fixed locations, though, and no call reports them — `authorable` says only whether a writable one exists — so take the path you actually read or edit from `list()` or `resolve()`, which is also where `copy()` reports what it just created.
|
||||
|
||||
## The roster service
|
||||
|
||||
`ctx.agentPresets` owns discovery, authoring, and mounting. You reach it by mounting a temporary plugin that injects it and registers a tool for yourself — `cordis_mount` returns only the mount acknowledgement, so a registered tool is how a service answer gets back to you, and it becomes callable on your next step.
|
||||
|
||||
Read `cordis_inspect what:"api" name:"agentPresets"` for the current signatures before writing the code. The four calls this skill relies on:
|
||||
|
||||
- `list()` — every preset with its `id`, `trust` (`system` for the shipped set, `user` for authored ones), and the absolute `path` of its composition file. This is how you locate any composition without knowing the install layout; the directory is that path's parent.
|
||||
- `read(id)` — one preset's composition text, without a file tool or a path.
|
||||
- `copy(from, id, name?)` — the only authoring write (see below).
|
||||
- `standingKeyFor(id)` — mount-validate one preset (see below).
|
||||
|
||||
```js
|
||||
return {
|
||||
name: 'preset-tools',
|
||||
inject: ['agentPresets', 'tools'],
|
||||
apply(ctx) {
|
||||
harness.registerTool(ctx, harness.defineTool({
|
||||
name: 'preset_check',
|
||||
description: 'Mount-validate one preset by id.',
|
||||
parameters: { id: { type: 'string', required: true } },
|
||||
output: { schema: { type: 'string' }, render(_a, v) { return [{ type: 'text', text: v }] } },
|
||||
async execute(args) {
|
||||
try {
|
||||
await ctx.agentPresets.standingKeyFor(args.id)
|
||||
return 'mounted OK'
|
||||
} catch (error) {
|
||||
return error.message
|
||||
}
|
||||
},
|
||||
}))
|
||||
},
|
||||
}
|
||||
```
|
||||
|
||||
Unmount the plugin with `cordis_unmount` when you are done; it is a probe, not a capability to leave behind.
|
||||
|
||||
## Authoring a preset
|
||||
|
||||
1. **Start from a copy.** Read a shipped composition close to what you want (the `standard` preset is the full coding agent) and copy its whole directory into `${DSH_HOME:-$HOME/.dsh}/.agent-presets/<id>/` — the id must be lowercase letters, digits, and hyphens, because it becomes the directory name. A composition written from scratch usually forgets a group realm or a consumer row; a copy starts loadable.
|
||||
2. **Expect the file sandbox.** The preset root lies outside the session workspace, so under the default `workspace-write` policy the first write is denied. Retry that exact command once with `sandbox_permissions` escalation and a short justification — the user sees and approves it. Batch your writes (one heredoc per file) rather than escalating many small commands.
|
||||
3. **Rewrite `preset.yml`**: give the copy its own `name` and `description`, and drop any `order` the source declared — that field sorts the shipped roster.
|
||||
4. **Edit `agent.cordis.yml`** row by row, keeping the plane rule and realm rule above.
|
||||
1. **Start from a copy.** `copy(from, id, name)` copies a whole preset directory into the user root — composition, metadata, skill directories, assets. It validates the id against `[a-z0-9][a-z0-9-]*` (it becomes the directory name, so no leading hyphen), refuses an id any root already supplies, rolls a failed copy back, and rewrites the copy's `preset.yml` to keep the source's description while dropping its name and roster `order`. Prefer it over a shell copy: it needs no sandbox escalation, it lands the copy in whichever root this deployment made writable, and the copy is exactly as loadable as its source. `resolve(id)` then names the file it created — that path, not a guessed one, is what the following edits target. `standard` is the full coding agent and the usual source.
|
||||
2. **Expect the file sandbox on every edit after the copy.** The user preset root lies outside the session workspace, so under the default `workspace-write` policy the first write there is denied. Only writes are: reading any composition by absolute path needs no escalation. Retry that exact command once with `sandbox_permissions` escalation and a short justification — the user sees and approves it. Batch your writes (one heredoc per file) rather than escalating many small commands. `copy()` itself runs host-side and needs none of this; the edits do.
|
||||
3. **Write the copy's `description`** in `preset.yml`, and its `name` if you passed none to `copy()`.
|
||||
4. **Edit `agent.cordis.yml`** row by row, keeping the plane rule and the realm rule.
|
||||
5. **Mount-validate the result**, then hand off to the user for a real session — both under *Verifying a change*.
|
||||
|
||||
### Native product subagents
|
||||
A composition written from scratch usually forgets a group realm or a consumer row; a copy starts loadable.
|
||||
|
||||
## The rule that catches people
|
||||
|
||||
**A row that publishes a service may not sit loose in a preset.** Registering a service without an isolate realm puts it in the process-global realm, so the second session mounting that preset collides with the first. The mount rejects it rather than letting the collision surface later.
|
||||
|
||||
Whether a row publishes a service is not visible from its name, and package READMEs are absent from an installed deployment. Read it off the live runtime instead: `cordis_inspect what:"services"` lists every service with the fiber that owns it, so a service attributed to a fiber other than the row you are adding is one that row consumes rather than provides. For a row not in your current composition, mount-validate and read the rejection — it names the offending service.
|
||||
|
||||
When a preset genuinely owns a service, wrap the provider **and every consumer that reaches it** in one group carrying an `isolate` realm. The shipped `standard` composition does this for `workflows`, which nothing outside an agent reads — its `delegation` group, with the delegation tools omitted here:
|
||||
|
||||
```yaml
|
||||
- id: delegation
|
||||
name: cordis:group
|
||||
group: true
|
||||
isolate:
|
||||
workflows: true
|
||||
config:
|
||||
- id: workflow-workerthread
|
||||
name: '@deepseek-ai/dsh-workflow-workerthread'
|
||||
config:
|
||||
provider: spawn
|
||||
- id: tool-workflow
|
||||
name: '@deepseek-ai/dsh-tool-workflow'
|
||||
```
|
||||
|
||||
`true` means a realm private to each mounting session. A string label instead joins subtrees into one shared realm; `provide()` still throws on the second registration under that symbol, so a label does not pool instances and is not what a preset needs.
|
||||
|
||||
A consumer left outside the group resolves the host's registry, which the preset did not populate, and then contributes nothing. Mount-validation catches that as a row that never activated.
|
||||
|
||||
Realms are for services a preset owns, not for every group. A host capability the preset only consumes must stay outside a realm, or the row cannot resolve it: `tool-bash`, `tool-tasks`, and `tool-goal` publish nothing and sit loose in `standard`, which explains in comments which host instance each one resolves and why a realm would break it. Wrapping a consumer row in a realm of its own is the same error as leaving one outside its provider's realm.
|
||||
|
||||
## Verifying a change
|
||||
|
||||
**`standingKeyFor(id)` is the check.** It composes the preset's plugin subtree for real — the same mount a session start performs, minus the agent — and rejects the four ways a composition fails:
|
||||
|
||||
- a row whose package does not resolve (`Cannot find package …`);
|
||||
- a row whose config is invalid (`invalid config: $.<field> missing required value`);
|
||||
- a row that never activated (`N row(s) did not activate: <id>: waiting for <service>`);
|
||||
- a service published into the root realm, which arrives as one of two messages. A name the host does not supply lands in the root realm and the mount audit rejects it: `row(s) published process-global service(s) [<name>]; a preset service must sit behind an isolate realm or move to the host composition` — this is the shape a preset's own forgotten realm takes. A name the host already supplies collides before the audit: `service "<name>" has been registered at <Owner>`. Both name the offending service.
|
||||
|
||||
It returns normally when the composition mounts. Run it as the final check on a finished edit rather than after every line: a successful mount installs a standing generation that lives until the process exits, while a failed one disposes its subtree and leaves nothing behind.
|
||||
|
||||
**Do not treat the roster's `broken` field as validation.** `list()` reports `broken` from a shape check — the file parses in the loader's YAML dialect and holds named rows — which every failure above passes. It catches a damaged file, not an unusable composition.
|
||||
|
||||
`cordis_inspect` reports THIS session's composition, so it confirms what a row does in the runtime you are already in, never what your new preset will do.
|
||||
|
||||
After a clean mount-validation, ask the user to start a session on the new preset and confirm the tool list; the preset decides tool schemas and prompt sections, and only a real session shows the agent that composition produces.
|
||||
|
||||
`cordis_mount` evaluates JavaScript against the live runtime and disappears on restart. It is for probing, not for shipping a capability: a capability belongs in a composition file.
|
||||
|
||||
## Native product subagents
|
||||
|
||||
Codex and Claude Code providers already live in the host composition. A preset chooses either product by contributing the same ordinary delegation-tool row used for spawn and fork; never move a product provider into the preset and never add a product-specific settings field.
|
||||
|
||||
@@ -54,43 +149,6 @@ Copy these disabled templates from a shipped full preset and remove `disabled` o
|
||||
|
||||
The two rows are independent. Leaving both disabled preserves the copied preset, enabling one exposes only that product tool, and enabling both exposes both. The host must provide `codex` or `claude` on `PATH`; the preset does not install, authenticate, select a model for, or probe either product.
|
||||
|
||||
The shipped preset directories are off-limits: never edit or delete them, and never escalate the sandbox to reach them, even when a change there looks quicker — an upgrade overwrites the install, and corrupting the `cordis` preset disables preset authoring itself. Locally authored presets under the user root are yours to create, edit, and delete.
|
||||
|
||||
## The rule that catches people
|
||||
|
||||
**A row that publishes a service may not sit loose in a preset.** Registering a service without an isolate realm puts it in the process-global realm, so the second session mounting that preset collides with the first. The mount rejects it rather than letting the collision surface later.
|
||||
|
||||
Whether a row publishes a service is not visible from its name. `tool-bash` reads like a tool but provides `bashEnv`. Check the package's README, or mount the preset and read the rejection — it names the offending service.
|
||||
|
||||
When a preset genuinely owns a service, wrap the provider **and every consumer that reaches it** in one group carrying an `isolate` realm:
|
||||
|
||||
```yaml
|
||||
- id: tasks
|
||||
name: cordis:group
|
||||
group: true
|
||||
isolate:
|
||||
tasks: true
|
||||
config:
|
||||
- id: tasks-local
|
||||
name: '@deepseek-ai/dsh-tasks-local'
|
||||
- id: tool-tasks
|
||||
name: '@deepseek-ai/dsh-tool-tasks'
|
||||
```
|
||||
|
||||
`true` means a realm private to each mounting session. A string label instead pools one instance across every subtree naming that label — use it only for something genuinely expensive to duplicate.
|
||||
|
||||
A consumer left outside the group resolves the host's registry, which the preset did not populate, and then contributes nothing. That is the quietest failure here: the mount succeeds and a tool is simply missing.
|
||||
|
||||
Host capabilities exposed through registries need no realm: the host `tools` and `skills` registries are layered per scope, so rows like `skill-local` and `tool-skill` sit loose in the preset and their registrations file into this preset's layer automatically — the agent's catalog merges them with whatever the deployment registered globally.
|
||||
|
||||
## Verifying a change
|
||||
|
||||
Read the live runtime with `cordis_inspect` — it reports the services, the plugin fibers, and the registered tools as they actually are, which is the only reliable check that a row did what its name suggests. Note it shows THIS session's composition: a preset you just wrote is not mounted anywhere until a session starts on it.
|
||||
|
||||
To check a preset you authored, re-read the files and validate these fields: the top level is a YAML list, every row is a map with a `name`, every group carries its own list, and service-publishing rows sit behind an `isolate` realm. The settings page's preset roster validates the same fields and marks an unloadable preset broken in red — point the user there, and ask them to start a session on the new preset to confirm the tool list; you cannot start one yourself.
|
||||
|
||||
`cordis_mount` evaluates JavaScript against the live runtime and disappears on restart. It is for probing, not for shipping a capability: a capability belongs in a composition file.
|
||||
|
||||
## What not to move into a preset
|
||||
|
||||
`agent-loop` registers the one agent factory and throws on a second. The registries own the per-session layering and cannot themselves be per-session. Session persistence must stay host-side or the session list fragments. The sandbox, approval, and permission rows are a deliberate boundary: a preset is exactly as privileged as the plugins it names, so letting one relax its own confinement would defeat the confinement.
|
||||
|
||||
Reference in New Issue
Block a user