kevchess15/deepseek-harness
1
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
deepseek-harness/packages/web/README.md

55 lines
2.8 KiB
Markdown
Raw Permalink Normal View History

docs: rebuild the documentation skill and standards (#2983)
2026-08-25 23:47:20 +08:00
---
description: "Package map for the web access capability family: the search/fetch service, its provider backends, and the model-facing tools that consume them."
kind: "package-group"
---
# web/ — web access capability family
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).
2026-06-25 15:04:12 +08:00
docs: translate remaining READMEs
2026-07-26 05:03:53 +08:00
English | [中文](README.zh.md)
docs: rebuild the documentation skill and standards (#2983)
2026-08-25 23:47:20 +08:00
## Summary
The `web/` group gives the harness web access — searching the web and fetching URLs — through one provider-neutral service (`ctx.web`) and the backends and tools that use it. A deployment mounts one or more backends — Exa, Perplexity, or DeepSeek for search, anonymous HTTP(S) for fetch — and the service picks a usable provider per operation, so the model-facing tools stay stable while backends come and go. Six packages split the family: the `web/` service that owns provider selection and errors, three search backends, one fetch backend, and `tool-web/`, which exposes `web_search` and `web_fetch` to the model. The group owns web access only: no browsing or extraction, no per-URL policy, and each backend keeps its own resource caps. Search and fetch deliberately share one service so selection, cancellation, errors, and configuration have a single owner.
## Table of Contents
- [Packages](#packages)
- [Related documentation](#related-documentation)
- [Dev Note](#dev-note)
-----
<a id="packages"></a>
## Packages
Six packages play the web roles; the subsystem reference owns the exhaustive vocabulary and contracts.
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).
2026-06-25 15:04:12 +08:00
| Package | Role | ctx key |
|---|---|---|
docs: rebuild the documentation skill and standards (#2983)
2026-08-25 23:47:20 +08:00
| [`web/`](web/README.md) | Search/fetch service: search and fetch URLs through interchangeable backends, one selection and error policy | `ctx.web` |
| [`web-search-exa/`](web-search-exa/README.md) | Searches the web through Exa | registers on `ctx.web` |
| [`web-search-perplexity/`](web-search-perplexity/README.md) | Searches the web through Perplexity | registers on `ctx.web` |
| [`web-search-deepseek/`](web-search-deepseek/README.md) | Searches the web through DeepSeek native search | registers on `ctx.web` |
| [`web-fetch-http/`](web-fetch-http/README.md) | Fetches public HTTP(S) pages anonymously | registers on `ctx.web` |
| [`tool-web/`](tool-web/README.md) | Exposes `web_search` and `web_fetch` to the model | registers on `ctx.tools` |
-----
<a id="related-documentation"></a>
## Related documentation
Start with the subsystem reference for the shared vocabulary, then the design decision behind the single provider-selection service.
- [Web subsystem](../../docs/subsystems/web.md) — the search/fetch requests and results, provider availability, `WebError`, and public-address enforcement.
- [Web capability seam decision](../../.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md) — why search and fetch share one provider-selection service.
<a id="dev-note"></a>
## Dev Note
<details>
<summary>Working context for maintainers — click to expand</summary>
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).
2026-06-25 15:04:12 +08:00
docs: rebuild the documentation skill and standards (#2983)
2026-08-25 23:47:20 +08:00
None.
docs: anchor each subsystem page to its package group; make group READMEs thin tables core.md read as a type grab-bag: LLM wire vocabulary up front, the agent/loop story buried, and no correspondence to packages/core. It now opens on the packages/core control spine — the package-by-package loop map with a Page column into session/system-prompt/tools/scope — and keeps only what the spine group declares plus the repo-wide patterns: the Agent handle with its delivery/cancellation/interception contracts, the SessionEvent envelope, branded ids, the …Map pattern. The conversation vocabulary (Message/ContentBlock, the model request, adapters — 17 type-equiv blocks) moves to llm-streaming.md, which now declares packages/llm end-to-end; the duplicate ContentBlockMap paste near its seam section folds into the moved section, and the manifest, LINK_MAP, README table rows, website label (Core data structures → Core), and inbound anchors follow. Every packages/<group>/README pair is now a thin front door in one shape: a why-first intro (bash's seam-pattern-first paragraph rewritten as 'shell execution for the agent'), the package table, and a closing pointer to the owning docs/subsystems page — the bash-style table stays the load-bearing middle. Load-bearing trailing paragraphs relocate rather than vanish: the fs no-timeout rationale becomes a filesystem.md section (both languages), session's four sectioned tables merge into one 12-row table, examples' legacy-bin H2 collapses to a pointer at jsonrpc-demo's README, and design rationale that already lives in an Agent Note or subsystem page is now linked instead of restated. All 40 pair records re-recorded.
2026-08-02 05:54:15 +08:00
docs: rebuild the documentation skill and standards (#2983)
2026-08-25 23:47:20 +08:00
</details>
Reference in a new issue Copy permalink