Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
# Cookbook: adding a workspace package
2026-07-14 07:23:53 -07:00
English | [中文 ](adding-a-package.zh.md )
2026-07-14 22:50:20 +08:00
The file-by-file checklist for a new `@deepseek-ai/dsh-<name>` package. This checklist is validated against the bash and adapter packages as templates; if it drifts from them, fix it here.
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
## 1. Create the package
```
2026-06-22 11:36:35 +08:00
packages/< group > /< pkg > /
2026-06-20 23:12:14 +08:00
package.json # copy from packages/core/tools, adjust name/description/deps
2026-06-22 11:36:35 +08:00
tsconfig.json # extends ../../../tsconfig.base.json, rootDir src,
# outDir lib/types, references: ../../../vendor/cosmokit,
# ../../../vendor/cordis (+ ../../../vendor/schemastery if
# you use Config, + ../../< group > /< dep > for each dsh dep)
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
src/index.ts # service default export or plugin (name/inject/apply/Config)
tests/< x > .spec.ts
Add a gated Known Limitations and Deferred Work section to every package README
Every packages/*/* README now carries a canonical '## Known Limitations and
Deferred Work' section: condensed, evidence-backed bullets for consumer-visible
gaps (unimplemented features, platform caveats, MVP cuts) and consciously
postponed work (TODO/FIXME/XXX markers, RFC deferrals still open). The ten
pre-existing ad-hoc variants ('What is NOT here (TODO)', 'Deferred',
'Limitations (MVP)', 'Known limitations (tracked TODOs)', ...) are normalized
into the canonical heading.
A new doc-sync gate, scripts/verify-readme-limitations.ts, enforces the shape:
exactly one limitations-like heading per package README, byte-equal to the
canonical h2, with at least one bullet; near-miss headings fail so variants
cannot creep back. Packages with genuinely nothing to declare (dsh-brand,
dsh-timeout, dsh-subagent-mock, dsh-app-boot) are whitelisted in the script and
must NOT carry the section; whitelist entries are validated against the scanned
package set so a rename fails loud.
Wired into the doc-sync chain (package.json) and the run-gates doc-sync leaf
set; the standing rule lands in packages/AGENTS.md and the adding-a-package
cookbook; decision record in
docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md
(RFC index regenerated).
Also fixes two stale '(deferred)' markers claiming dsh-compact-basic is
unimplemented (the dsh-compact seam README's package table and the seam's
module doc comment).
2026-07-10 01:51:50 +08:00
README.md # service API, events, extension points, design notes,
2026-07-19 17:39:50 +08:00
# + gated Model Experience context blocks or short form
Add a gated Known Limitations and Deferred Work section to every package README
Every packages/*/* README now carries a canonical '## Known Limitations and
Deferred Work' section: condensed, evidence-backed bullets for consumer-visible
gaps (unimplemented features, platform caveats, MVP cuts) and consciously
postponed work (TODO/FIXME/XXX markers, RFC deferrals still open). The ten
pre-existing ad-hoc variants ('What is NOT here (TODO)', 'Deferred',
'Limitations (MVP)', 'Known limitations (tracked TODOs)', ...) are normalized
into the canonical heading.
A new doc-sync gate, scripts/verify-readme-limitations.ts, enforces the shape:
exactly one limitations-like heading per package README, byte-equal to the
canonical h2, with at least one bullet; near-miss headings fail so variants
cannot creep back. Packages with genuinely nothing to declare (dsh-brand,
dsh-timeout, dsh-subagent-mock, dsh-app-boot) are whitelisted in the script and
must NOT carry the section; whitelist entries are validated against the scanned
package set so a rename fails loud.
Wired into the doc-sync chain (package.json) and the run-gates doc-sync leaf
set; the standing rule lands in packages/AGENTS.md and the adding-a-package
cookbook; decision record in
docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md
(RFC index regenerated).
Also fixes two stale '(deferred)' markers claiming dsh-compact-basic is
unimplemented (the dsh-compact seam README's package table and the seam's
module doc comment).
2026-07-10 01:51:50 +08:00
# + the gated "Known Limitations and Deferred Work" section
2026-07-14 00:22:52 +08:00
# (or a whitelist entry in scripts/verify-package-readme-limitations.ts)
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
```
feat(tool-todo): add the model-facing todo_write tool
Add @deepseek-ai/dsh-tool-todo (a new packages/todo/ group): a model-facing
todo_write(todos: [{content, status}]) tool with whole-list-replace semantics.
Each call appends the full list as a todo/write event to the calling agent's
session log; the current list is the most recent such event (last-write-wins).
Single-owner — a non-agent caller is rejected. Beyond the schema's
type/required/enum checks, execute rejects empty/duplicate content and more than
one in_progress task, narrowing the loosely-typed args into a real TodoItem[].
Both UIs render off the existing session/event: the stdio UI prints a glyphed
checklist; the ACP bridge maps the list to a `plan` sessionUpdate (todosToPlan
synthesizes the priority ACP requires; status maps 1:1). Wired into the
coding-agent, acp-agent, and snapshot example configs with a system-prompt nudge.
Tests: unit (schema, validation, append/replace, no-agent rejection, presentCall,
HMR-safety, Loader export-shape guard), full-loop integration through the agent
loop, the ACP todosToPlan mapping + stream-update arm, the stdio render arm, and
a session/load replay that re-emits the plan. New-group TS wiring added to
tsconfig.base/json/build. RFC + a doc-inventory sweep (architecture, packages
README, AGENTS layout, cookbook group list, example READMEs) ship with it.
The todo-plan ACP snapshot scenario is recorded separately (needs an API key).
2026-06-29 10:30:52 +08:00
Choose an existing group when one matches the package's role (`core` , `llm` , `bash` , `compact` , `subagent` , `todo` , `session-persistence` , `ui` , `util` , or `support` ). A new group is allowed, but it is a pure container: no `package.json` , no source files, and packages still sit exactly one level below it.
2026-06-22 11:36:35 +08:00
2026-07-13 17:49:01 +08:00
package.json invariants (enforced by `pnpm run constraints` / `scripts/check-workspace-constraints.ts` ): `private: true` , a `version` matching the root `package.json` , `type: module` , `main: "lib/index.js"` , `types: "lib/types/index.d.ts"` , `exports["."].types: "./lib/types/index.d.ts"` , `exports["."].default: "./lib/index.js"` , `cordis` in BOTH peerDependencies and devDependencies (same range). Mirror every dsh peer dependency in devDependencies. `schemastery` goes in `dependencies` (it is a runtime validator), matching agent-loop. The `files` list is precise: `lib/index.js` , `lib/types/**/*.d.ts` , `lib/types/**/*.d.ts.map` , and `src` ; do not publish `lib/types` JS or JS-map intermediates or stale root declaration files. CLI app packages with a package `bin` include `lib/bin.js` immediately after `lib/index.js` in `files` .
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
2026-06-22 06:11:00 +08:00
In-package relative imports use explicit `.ts` specifiers in source (for example, `export * from './types.ts'` ). The compiler rewrites those to `.js` in emitted JS and leaves explicit `.ts` specifiers in declarations, which standard NodeNext/Node16 TypeScript consumers resolve to the sibling `.d.ts` files.
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
## 2. Register it in the root configs
| File | Change |
|---|---|
2026-06-22 11:36:35 +08:00
| `tsconfig.base.json` | no edit for an existing group; for a new group, add a `./packages/<group>/*/src` candidate to the `@deepseek-ai/dsh-*` wildcard |
2026-07-23 00:06:35 +08:00
| `tsconfig.host.json` (host-side package) or `tsconfig.client.json` (client-side package) | add `{ "path": "./packages/<group>/<pkg>" }` to `references` — exactly one aggregate, never both ([layout ](../development.md#typescript-project-layout )) |
2026-06-20 23:12:14 +08:00
| `knip.json` | only if the package has non-`*.spec.ts` entries (e.g. `*.e2e.ts` → add a per-workspace override like `packages/llm/llm-deepseek` ) |
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
2026-07-23 00:06:35 +08:00
A `packages/client/*` package additionally extends `tsconfig.base.client.json` instead of `tsconfig.base.json` , and a client plugin package declares `dshClient` in package.json, exports `./client` , and calls the shared tsdown preset (`packages/client/tsdown.client.ts` ) — see [packages/client/AGENTS.md ](../../packages/client/AGENTS.md ) for the client-side contract.
2026-06-22 11:36:35 +08:00
Covered automatically by globs or package-manifest discovery — no edits needed: root `package.json` workspaces, `scripts/publint-all.ts` , `tsdown.config.ts` , `vitest.config.ts` , `eslint.config.mjs` , `scripts/check-workspace-constraints.ts` .
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
## 3. Decide the package topology
2026-06-13 18:39:20 +08:00
For a swappable capability, split interface / implementation / consumer into separate packages (see docs/architecture.md § "Capability seams" — the bash trio is the template). A single-purpose plugin stays one package.
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
2026-07-12 02:55:26 +08:00
## 4. Write the package README
2026-07-19 22:50:49 +08:00
Keep package-specific service API, config, events, extension points, and design notes first. The limitations section records durable consumer gaps and non-obvious maintainer constraints owned by this package; ordinary cleanup stays in its source TODO or Agent Note. An indirect Model Experience sentence may name the consumer that surfaces this package's contribution, but it does not restate that consumer's implementation. End a package README with this canonical sequence:
2026-07-12 02:55:26 +08:00
2026-07-13 21:33:23 +08:00
````markdown
2026-07-12 02:55:26 +08:00
## Model Experience
2026-07-13 22:26:33 +08:00
### Request surface and condition
2026-07-19 18:08:42 +08:00
#### What the model sees
2026-07-13 22:26:33 +08:00
2026-07-19 18:08:42 +08:00
An exact data-dependent shape, an anchored generated-catalog link, or an introduction to the verbatim literal below.
2026-07-13 21:33:23 +08:00
2026-07-19 18:08:42 +08:00
##### Verbatim text for this field, when needed
2026-07-13 21:33:23 +08:00
2026-07-13 22:26:33 +08:00
```markdown
2026-07-14 00:22:52 +08:00
Stable system-prompt prose of any length, or another long non-generated literal, copied exactly from source.
2026-07-13 21:33:23 +08:00
```
2026-07-12 02:55:26 +08:00
2026-07-19 18:08:42 +08:00
#### Token effect
Fixed, conditional, retained, replaced, capped, or zero-direct token effect.
#### KV Cache effect
Append-only, prefix-stable, replacing, or independent behavior, including the exact conditions that may invalidate reuse.
2026-07-12 02:55:26 +08:00
## Known Limitations and Deferred Work
2026-07-14 14:37:16 +08:00
- **Consumer-visible gap** — exact boundary, consequence, or maintainer constraint.
2026-07-13 21:33:23 +08:00
````
2026-07-12 02:55:26 +08:00
2026-07-19 18:08:42 +08:00
Fill Model Experience from the implementation. Use one H3 per direct, conditional, capped, lifetime, or auxiliary-model surface, with the three ordered H4 fields shown above and one prose paragraph under each. Quote stable text owned by the package: system-prompt prose goes in a titled H5 plus `markdown` fence under the field that introduces it—normally `What the model sees` —other short literals stay inline with named placeholders, and other long literals use the same nested form. Summarize only data-dependent or provider-owned text. A tool-schema surface links its anchored section in the generated [tool catalog ](../tool-catalog.md ) and states only deltas absent there. Keep prompt and schema surfaces separate when scoping can hide one without the other. In `KV Cache effect` , distinguish append-only growth, a stable repeated prefix, replacement of earlier request tokens, and an independent model request, then name the package-owned changes that can invalidate reuse. “Does not invalidate” means the package preserves an already-reusable prefix; provider cache availability and eviction remain outside the package contract. The [prose standard ](../../.agents/skills/dsh-prose-standard/SKILL.md ) governs completeness and ownership; the verifier enforces the mechanical shape.
2026-07-13 15:47:46 +08:00
2026-07-19 22:50:49 +08:00
A package with no context effect or one consumer-owned path uses the audited `None, as ` or `Indirectly, through ` sentence in [`SENTENCE_MODEL_EXPERIENCE` ](../../scripts/verify-package-readme-model-experience.ts ), followed by a `KV Cache effect` H4 and one non-empty paragraph; a model-agnostic generic package may instead join `NO_MODEL_EXPERIENCE_SECTION` . Do not expand either case into a description of another package's work. The limitations [allowlist ](../../scripts/verify-package-readme-limitations.ts ) is independent. The [Model Experience Agent Note ](../../.agents/notes/implemented/process/2026-07-12-package-model-experience-contract.md ) records the rationale.
2026-07-12 02:55:26 +08:00
## 5. Verify
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
```sh
2026-06-16 14:55:37 +08:00
pnpm install # registers the workspace
2026-07-12 02:55:26 +08:00
pnpm run doc-sync
2026-06-16 14:55:37 +08:00
pnpm run constraints & & pnpm run typecheck & & pnpm run lint
pnpm run test:coverage # 100% per-file over src (types.ts exempt)
2026-06-22 11:36:35 +08:00
pnpm run build & & pnpm run hygiene
Add examples/coding-agent and the docs cookbook
The first real agent wiring: DeepSeek V4 + the bash tool suite + stdio
chat + JSONL persistence, runnable via yarn demo:coding (reads the
gitignored repo-root .env through process.loadEnvFile).
- examples/coding-agent: cordis.yml wiring both real plugin families
(llm-deepseek with !!js env secrets; bash-local + tool-bash), a
bash-only coding system prompt, a max-steps-guard plugin (bounds
runaway turns via the agent/turn-continuation waterfall — abort()
from step-end is a no-op by then), and a stdio UI with dimmed
reasoning and exit-on-idle for piped stdin.
- e2e (yarn test:e2e, key-gated): full-loop.e2e.ts runs a real model
against the real bash tool; coding-task.e2e.ts is the swebench-style
smoke — the model fixes a buggy add.js in a temp dir and the test
re-runs node add.test.js itself rather than trusting the agent.
- docs/cookbook: adding-a-package (the verified checklist),
adding-a-tool (execute() contract, background pattern, seams),
adding-an-llm-adapter (protocol obligations, mock-server testing,
e2e policy). AGENTS.md layout/commands/secrets sections updated;
architecture.md points at both examples and the cookbook.
- vitest.e2e.config.ts: serialize test files + retry twice — parallel
e2e files trip the shared internal key's concurrency quota.
- fix: the !js YAML tag spelling in docs/JSDoc is actually !!js
(js-yaml resolves custom tags under tag:yaml.org,2002:js).
2026-06-13 00:47:32 +08:00
```
fix(docs): address Codex review round 2 — repoint every remaining moved-policy citation
The definitive sweep (audit every AGENTS.md mention in packages/, docs/,
examples/, scripts/) found thirteen more citations of relocated policy
and two citations of rules that never existed as quoted:
- with-key policy comments (web deepseek/perplexity e2e headers) ->
docs/testing.md; real-impl-over-mock comments (acp harness, load,
stream-update specs) -> docs/testing.md; defensive-pattern quotes
(acp index.ts x3, stream-update) -> docs/defensive-patterns.md.
- md-tier repoints: real-api-e2e RFC, tool-schema-catalog RFC,
postmortem 0001 guardrail row, adding-a-package cookbook,
drop-bash-output-spill-files RFC, acp-subagent-backend RFC phrasing.
- Two false attributions dropped in favor of self-contained reasoning:
tool-todo's 'don't validate scenarios that can't happen' and the
bash-stdin-env RFC's 'Don't add features beyond what the task
requires' (neither rule ever existed under those names).
- Citations of the two 'not golden truth' doctrines stay: those bullets
survive verbatim in the root conventions.
Note: packages/support/ui-stdio readline TTY spec flakes under full
coverage on a heavily loaded box (passes standalone and passed the
same tree's coverage run minutes earlier); untouched by this stack.
2026-07-04 15:43:51 +08:00
Test expectations: every registry/registration needs an HMR-safety test (register from a child fiber, dispose it, assert cleanup). Excessive tests are welcome — see [docs/testing.md ](../testing.md ).