Add web capability seam: ctx.web, search/fetch providers, web tools

Introduce web access as a first-class capability seam so the model-facing
web tools stay stable while backends change. dsh-web owns ctx.web as a
provider registry with registration-order-independent selection and the
WebError taxonomy; dsh-web-search-exa, dsh-web-search-perplexity, and
dsh-web-fetch-local register capabilities into it; dsh-tool-web is the sole
owner of the model-facing web_search/web_fetch schemas, prompt sections, and
HTML-to-markdown presentation. Search and fetch are deliberately one seam.

Providers ship as namespace plugins that register into ctx.web (like an
LlmAdapter into ctx.llm), not key-owning services, since multiple search
providers cannot each own the key. Tool registration follows product
enablement, not backend availability, so load order/credentials never enter
the model contract; the seam resolves the provider at execution time and
surfaces a structured WebError otherwise.

Moves the RFC to implemented/ amended to match what shipped. Example/app
configs are intentionally not wired yet (RFC migration step 6).
This commit is contained in:
Dudu-0223
2026-06-25 15:04:12 +08:00
parent a4091daa3d
commit d01f5f73b7
50 changed files with 3610 additions and 8 deletions

View File

@@ -24,6 +24,9 @@ For a catalog of the **data structures** this architecture moves around — the
│ @deepseek-ai/dsh-agent-loop (the ONE concrete plugin) │
│ @deepseek-ai/dsh-bash-local (bash impl) │
│ @deepseek-ai/dsh-tool-bash (bash tool schemas) │
│ @deepseek-ai/dsh-web-search-exa (web search impl) │
│ @deepseek-ai/dsh-web-fetch-local (web fetch impl) │
│ @deepseek-ai/dsh-tool-web (web tool schemas) │
│ @deepseek-ai/dsh-session-persistence-jsonl (persistence impl)│
├─────────────────────────────────────────────────────────────┤
│ @deepseek-ai/dsh-agent (vocabulary + registry) │
@@ -33,6 +36,7 @@ For a catalog of the **data structures** this architecture moves around — the
│ @deepseek-ai/dsh-session-persistence (persistence seam) │
│ @deepseek-ai/dsh-llm (abstract model service) │
│ @deepseek-ai/dsh-bash (abstract bash executor) │
│ @deepseek-ai/dsh-web (abstract web access) │
├─────────────────────────────────────────────────────────────┤
│ vendor/: cordis, loader, include, group, timer, hmr, │
│ logger-console, cosmokit, schemastery │
@@ -54,6 +58,7 @@ Dependency rule: **extension** plugins depend on interface packages, never on `d
| `ctx.agentLoop` | `AgentLoop` | dsh-agent-loop | creates `ReactLoopAgent`s and drives their loops |
| `ctx.bash` | `BashExecutor` (abstract) | dsh-bash | bash execution seam: foreground runs + background tasks |
| `ctx.compact` | `CompactService` (abstract) | dsh-compact | compaction seam: decide when history is too large, summarize an older range into a single surface node |
| `ctx.web` | `WebService` | dsh-web | web access seam: search/fetch provider registries, registration-order-independent selection, the `WebError` taxonomy |
All registrations (`registerAdapter`, `section`, `tools`, `register`, …) go through `ctx.effect()` and return disposers, so plugin hot-reload (vendored HMR) and fiber disposal clean up automatically.
@@ -69,6 +74,8 @@ Swappable capabilities are split into **three packages** so each part evolves in
The LLM seam has the same topology folded differently: `dsh-llm` carries the interface (`LlmAdapter`) AND the consumer surface (`ctx.llm.stream()`), with adapters as implementation packages — there the consumer is the loop itself, not a swappable schema surface. Use the full three-package split when the consumer is independently replaceable; keep interface + consumer together when they are one concern. Don't split preemptively: a capability with one conceivable implementation and one consumer stays one package until proven otherwise.
The web capability uses the same three-package split but folds two capabilities onto one seam: `dsh-web` owns the abstract `ctx.web` service, which is a provider REGISTRY (`registerSearchProvider`/`registerFetchProvider`, registration-order-independent selection, the `WebError` taxonomy) rather than a single backend. Providers register capabilities, not tools — `dsh-web-search-exa`, `dsh-web-search-perplexity`, and `dsh-web-fetch-local` each register into `ctx.web` the way an `LlmAdapter` registers into `ctx.llm`, so they are namespace plugins (`inject: ['web']`), not key-owning services. `dsh-tool-web` is the single consumer that owns the model-facing `web_search`/`web_fetch` schemas, prompt sections, and presentation; it reads only the aggregated `ctx.web.searchStatus()`/`fetchStatus()` and executes through `ctx.web.search()`/`fetch()`, so provider selection has one owner. Search and fetch are deliberately one seam (one thing to inject and configure, one selection policy, one abort/error vocabulary) despite sharing no request schema — see the [web capability seam RFC](rfc/implemented/architecture/2026-06-24-web-capability-seam.md).
> **"Capability" — two unrelated meanings.** (1) The *seam pattern* above ("one plugin provides a capability, another needs it") is realized by plain Cordis **services + `inject`**: a provider registers a service (`ctx.bash`, declared in `interface Context`); a consumer declares `inject: ['bash']` and its fiber stays pending until the service exists, tearing down via HMR if it later vanishes. No extra library is needed. (2) `@cordisjs/plugin-capability` is a different axis entirely — a **permission/capability-security** service (named permissions with inheritance/dependency, tested against a session via `ctx.capability.test`). It is a candidate for the deferred permissions/sandbox work (the `tools/execute` veto seam), NOT a mechanism for swapping implementations.
## The vocabulary (dsh-llm)

View File

@@ -59,7 +59,6 @@ Do NOT write one for a mechanical or local choice (a variable name, a one-file r
|---|---|
| [Runtime schemas for the event vocabulary (Zod vs the merge-extensible-map pattern)](proposed/architecture/2026-06-16-typed-event-schemas.md) | 2026-06-16 |
| [Extract a generic long-running tool runtime](proposed/architecture/2026-06-20-generic-long-running-tool-runtime.md) | 2026-06-20 |
| [Web capability seam - provider registry and model-facing web tools](proposed/architecture/2026-06-24-web-capability-seam.md) | 2026-06-24 |
### Process
@@ -120,6 +119,7 @@ Do NOT write one for a mechanical or local choice (a variable name, a one-file r
| [Reorganize packages into a modular hierarchy](implemented/architecture/2026-06-20-package-hierarchy.md) | 2026-06-20 |
| [Branded IDs everywhere they belong](implemented/architecture/2026-06-20-branded-ids.md) | 2026-06-20 |
| [Extract example apps into packages](implemented/architecture/2026-06-20-extract-example-app-packages.md) | 2026-06-20 |
| [Web capability seam — provider registry and model-facing web tools](implemented/architecture/2026-06-24-web-capability-seam.md) | 2026-06-24 |
### Process

View File

@@ -1,6 +1,6 @@
# RFC: Web capability seam - stable tools over multiple providers
Status: proposed
Status: implemented
## Problem
@@ -64,7 +64,7 @@ flowchart LR
`@deepseek-ai/dsh-web` depends only on Cordis and low-level harness support. It declares `ctx.web`, provider interfaces, request/result types, status types, and error codes. It does not import tool, agent, session, LLM, or provider packages.
Provider packages depend on `@deepseek-ai/dsh-web` and Cordis. They own credentials, endpoint config, provider-specific request mapping, provider-specific response parsing, and provider-specific error translation into `WebError`. They issue network requests with the platform-native `fetch` (Node 24), mirroring `@deepseek-ai/dsh-llm-deepseek`'s adapter, NOT a cordis HTTP-client service (`ctx.http`/`@cordisjs/plugin-http`) — even where a Perplexity provider's request is shaped like an OpenAI-compatible chat completion, that wire shape is a provider-private detail and does not make the provider depend on `ctx.llm`.
Provider packages depend on `@deepseek-ai/dsh-web` and Cordis. They own credentials, endpoint config, provider-specific request mapping, provider-specific response parsing, and provider-specific error translation into `WebError`. They issue network requests with the platform-native `fetch` (Node 24), mirroring `@deepseek-ai/dsh-llm-deepseek`'s adapter, NOT a cordis HTTP-client service (`ctx.http`/`@cordisjs/plugin-http`) — even where a Perplexity provider's request is shaped like an OpenAI-compatible chat completion, that wire shape is a provider-private detail and does not make the provider depend on `ctx.llm`. A provider does NOT own the `ctx.web` key (two search providers cannot both own it): like `dsh-llm-deepseek`, each provider package is a function/namespace plugin (`inject: ['web']`) whose `apply` constructs the backend and calls `ctx.web.registerSearchProvider` / `registerFetchProvider`. `@deepseek-ai/dsh-web` is the `export default` service that owns the key.
`@deepseek-ai/dsh-tool-web` depends on `@deepseek-ai/dsh-web`, `@deepseek-ai/dsh-tools`, `@deepseek-ai/dsh-system-prompt`, and Cordis. It never imports concrete provider packages.
@@ -267,11 +267,11 @@ SSRF / private-network protection (blocking private, loopback, link-local, multi
Tool registration in the first version is a minimal stable sync:
1. On plugin startup, read the product/app config that enables or disables web search and web fetch.
2. If web search is enabled, register `web_search` and keep that tool's disposer.
3. If web fetch is enabled, register `web_fetch` and keep that tool's disposer.
1. On plugin startup, read the `dsh-tool-web` `Config` (`search?: boolean`, `fetch?: boolean`, both default `true`) that enables or disables each web tool.
2. If web search is enabled, register `web_search` (its disposer is fiber-scoped via the effect-based registry).
3. If web fetch is enabled, register `web_fetch` (likewise fiber-scoped).
4. Do not dispose either tool merely because `ctx.web.searchStatus()` or `ctx.web.fetchStatus()` is unavailable.
5. Dispose registered tools when the `tool-web` fiber is disposed.
5. Disposing the `tool-web` fiber tears down its registrations automatically.
Provider status changes affect execution results and diagnostics, not whether the model-facing schema exists. If a product wants no web tools at all, it disables `dsh-tool-web` or the individual web tool in config; if it wants web tools but the backend is misconfigured, the model sees a structured tool error at execution time.
@@ -315,7 +315,7 @@ Search provider tests cover request mapping, response parsing into `content` plu
Integration tests should load the real seam, provider, and tool packages together and execute through `ctx.tools.execute()` rather than calling providers directly. If wiring the tools into an ACP-facing example changes editor-visible transcripts, add or update the relevant snapshot scenario in the same change.
At least one test must drive these packages through their REAL cordis Loader/export path, not a hand-built `ctx.plugin({...})` mount, so a broken export shape is caught (see [docs/postmortem/0001](../../../postmortem/0001-acp-default-export-drops-inject.md) and `packages/AGENTS.md` § plugin-export-shape). The two shapes need different guards: `dsh-web` and the provider packages are **services** (`export default` the class) and a stray extra export would surface as a missing service; `dsh-tool-web` is a **namespace plugin** (named `name`/`inject`/`apply`, NO default), and because it has `inject`, a stray `export default apply` makes `unwrapExports` drop the `inject` and the plugin throws `cannot get property … without inject` the moment it loads — so a Loader smoke that boots tool-web over `ctx.web` catches it. Prove the guard bites: add `export default apply` to `tool-web`, watch the smoke go red, revert.
At least one test must drive these packages through their REAL cordis Loader/export path, not a hand-built `ctx.plugin({...})` mount, so a broken export shape is caught (see [docs/postmortem/0001](../../../postmortem/0001-acp-default-export-drops-inject.md) and `packages/AGENTS.md` § plugin-export-shape). The two shapes need different guards: `dsh-web` is a **service** (`export default` the class) and a stray extra export would surface as a missing service; the provider packages and `dsh-tool-web` are **namespace plugins** (named `name`/`inject`/`apply`, NO default), and because each has `inject`, a stray `export default apply` makes `unwrapExports` drop the `inject` and the plugin throws `cannot get property … without inject` the moment it loads — so a Loader smoke that boots tool-web over `ctx.web` catches it (and each provider's registration test mounts it the real way and asserts no default export). Prove the guard bites: add `export default apply` to `tool-web`, watch the smoke go red, revert.
## Migration plan