Pine/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases 1 Wiki Activity

refactor: prune unused web seam fields

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-14 04:17:38 +08:00
parent a0359bc4a9
commit 3ab35de64f
34 changed files with 228 additions and 344 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/web/web-fetch-local/README.md
+2 -3
View File
@@ -8,7 +8,7 @@ This is an **implementation** package: it registers a provider into `ctx.web`, i
The provider owns **safe resource retrieval**: URL validation, HTTP transport, redirect policy, a resource-backstop timeout, abort propagation, byte caps, charset decoding, content-type classification, and binary rejection. `@deepseek-ai/dsh-tool-web` owns **presentation** (HTML→markdown, truncation formatting). A non-2xx HTTP response is a *result* (status code + decoded body), not an error; `WebError` is reserved for failures to safely retrieve or represent the resource.
The provider's `timeoutMs`/`maxTimeoutMs` is a **resource backstop** for direct `ctx.web.fetch()` callers and misconfigured deployments — it is NOT the model-facing tool-call budget. The tool-call budget for `web_fetch` is deployment policy owned by [`@deepseek-ai/dsh-timeout-policy`](../../timeout/timeout-policy/README.md), which arms a per-call deadline on `exec.signal`. A shipped web-tool deployment sets the provider backstop **above** the `tool-timeout` budget, so the tool-call policy normally wins for model calls (returning `TOOL_TIMEOUT`); when the outer deadline signal reaches this provider first, it classifies as `WEB_ABORTED` and the outer wrapper replaces the result with `TOOL_TIMEOUT`. The provider's own `WEB_FETCH_TIMEOUT` only fires for a direct seam caller whose own budget elapsed.
The provider's configured `timeoutMs` is a **resource backstop** for direct `ctx.web.fetch()` callers and misconfigured deployments — it is NOT the model-facing tool-call budget. The tool-call budget for `web_fetch` is deployment policy owned by [`@deepseek-ai/dsh-timeout-policy`](../../timeout/timeout-policy/README.md), which arms a per-call deadline on `exec.signal`. A shipped web-tool deployment sets the provider backstop **above** the `tool-timeout` budget, so the tool-call policy normally wins for model calls (returning `TOOL_TIMEOUT`); when the outer deadline signal reaches this provider first, it classifies as `WEB_ABORTED` and the outer wrapper replaces the result with `TOOL_TIMEOUT`. The provider's own `WEB_FETCH_TIMEOUT` fires when its configured backstop elapses.
## Transport hygiene
@@ -26,8 +26,7 @@ The provider's `timeoutMs`/`maxTimeoutMs` is a **resource backstop** for direct
| `maxUrlLength` | `2048` | Maximum accepted request URL length. |
| `maxResponseBytes` | `5_000_000` | Maximum response body size in bytes. |
| `maxBodyChars` | `100_000` | Maximum decoded body length in characters. |
| `timeoutMs` | `30_000` | Default fetch timeout — a resource backstop for direct `ctx.web.fetch()` callers, not the model-facing tool-call budget (that is `dsh-timeout-policy`). |
| `maxTimeoutMs` | `120_000` | Upper bound for a per-request timeout override (direct callers). |
| `timeoutMs` | `30_000` | Fetch timeout — a resource backstop for direct `ctx.web.fetch()` callers, not the model-facing tool-call budget (that is `dsh-timeout-policy`). |
| `maxRedirects` | `5` | Maximum same-origin redirect hops (`0` follows none). |
| `userAgent` | `deepseek-harness/…` | `User-Agent` header. |
packages/web/web-fetch-local/src/index.ts
-5
View File
@@ -40,8 +40,6 @@ export interface Config {
maxBodyChars?: number
/** Default fetch timeout in milliseconds. */
timeoutMs?: number
/** Upper bound for a per-request timeout override. */
maxTimeoutMs?: number
/** Maximum number of same-origin redirect hops to follow. */
maxRedirects?: number
/** `User-Agent` header sent on every request. */
@@ -53,7 +51,6 @@ export const Config: z<Config> = z.object({
maxResponseBytes: z.number().default(5_000_000),
maxBodyChars: z.number().default(100_000),
timeoutMs: z.number().default(30_000),
maxTimeoutMs: z.number().default(120_000),
maxRedirects: z.number().default(5),
userAgent: z.string().default(DEFAULT_USER_AGENT),
})
@@ -83,14 +80,12 @@ export function apply(ctx: Context, config: Config): void {
assertPositiveFinite('maxResponseBytes', resolved.maxResponseBytes)
assertPositiveFinite('maxBodyChars', resolved.maxBodyChars)
assertPositiveFinite('timeoutMs', resolved.timeoutMs)
assertPositiveFinite('maxTimeoutMs', resolved.maxTimeoutMs)
assertNonNegativeInteger('maxRedirects', resolved.maxRedirects)
const limits: LocalFetchLimits = {
maxUrlLength: resolved.maxUrlLength,
maxResponseBytes: resolved.maxResponseBytes,
maxBodyChars: resolved.maxBodyChars,
timeoutMs: resolved.timeoutMs,
maxTimeoutMs: resolved.maxTimeoutMs,
maxRedirects: resolved.maxRedirects,
userAgent: resolved.userAgent,
}
packages/web/web-fetch-local/src/provider.ts
+7 -11
View File
@@ -20,8 +20,8 @@
*/
import { WebError } from '@deepseek-ai/dsh-web'
import type { WebFetchBody, WebFetchProvider, WebFetchRequest, WebFetchResult, WebProviderStatus } from '@deepseek-ai/dsh-web'
import { clampTimeout, deadline, timeoutOf } from '@deepseek-ai/dsh-timeout'
import type { WebFetchBody, WebFetchProvider, WebFetchRequest, WebFetchResult } from '@deepseek-ai/dsh-web'
import { deadline, timeoutOf } from '@deepseek-ai/dsh-timeout'
import { classifyContentType, decoderForCharset, isSameOrigin, parseCharset, validateFetchUrl } from './policy.ts'
/** Resolved provider limits (the plugin's schemastery Config supplies defaults). */
@@ -34,8 +34,6 @@ export interface LocalFetchLimits {
maxBodyChars: number
/** Default fetch timeout in milliseconds. */
timeoutMs: number
/** Upper bound for a per-request timeout override. */
maxTimeoutMs: number
/** Maximum number of (same-origin) redirect hops to follow. */
maxRedirects: number
/** `User-Agent` header sent on every request. */
@@ -52,20 +50,19 @@ export class LocalFetchProvider implements WebFetchProvider {
constructor(private readonly limits: LocalFetchLimits) {}
/** No credentials to check — an anonymous public fetcher is always usable. */
status(): WebProviderStatus {
return { available: true }
available(): boolean {
return true
}
async fetch(request: WebFetchRequest, exec?: { readonly signal?: AbortSignal }): Promise<WebFetchResult> {
if (exec?.signal?.aborted) throw new WebError('web fetch aborted', 'WEB_ABORTED')
const timeoutMs = clampTimeout(request.timeoutMs, this.limits.timeoutMs, this.limits.maxTimeoutMs)
async fetch(request: WebFetchRequest, signal?: AbortSignal): Promise<WebFetchResult> {
if (signal?.aborted) throw new WebError('web fetch aborted', 'WEB_ABORTED')
// One deadline signal fuses the caller's abort with our own timeout, so the
// network request and the streaming read both stop on either. The timeout
// abort carries a TimeoutReason we recover afterward to classify the cause
// (translateAbortOrNetwork), instead of hand-rolling a controller + timer +
// reason-recovery dance.
using d = deadline(exec?.signal, timeoutMs, 'WEB_FETCH_TIMEOUT')
using d = deadline(signal, this.limits.timeoutMs, 'WEB_FETCH_TIMEOUT')
return await this.followAndRead(request.url, d.signal)
}
@@ -161,7 +158,6 @@ export class LocalFetchProvider implements WebFetchProvider {
const body: WebFetchBody = kind === 'html' ? { kind: 'html', content } : { kind: 'text', content }
return {
providerId: this.id,
url: finalUrl.toString(),
statusCode: response.status,
body,
packages/web/web-fetch-local/tests/fetch-local.spec.ts
+5 -11
View File
@@ -12,7 +12,6 @@ const limits: LocalFetchLimits = {
maxResponseBytes: 5_000_000,
maxBodyChars: 100_000,
timeoutMs: 5_000,
maxTimeoutMs: 10_000,
maxRedirects: 5,
userAgent: 'test-agent/1.0',
}
@@ -82,7 +81,7 @@ describe('LocalFetchProvider success', () => {
it('fetches a text body', async () => {
handler = (_req, res) => { res.writeHead(200, { 'content-type': 'text/plain' }); res.end('hello world') }
const result = await provider().fetch({ url: base })
expect(result.providerId).toBe(LOCAL_FETCH_PROVIDER_ID)
expect(provider().available()).toBe(true)
expect(result.statusCode).toBe(200)
expect(result.body).toEqual({ kind: 'text', content: 'hello world' })
expect(result.truncated).toBe(false)
@@ -287,14 +286,14 @@ describe('LocalFetchProvider invalid URLs and abort', () => {
it('honors a pre-aborted signal', async () => {
const controller = new AbortController()
controller.abort()
await expect(provider().fetch({ url: base }, { signal: controller.signal }))
await expect(provider().fetch({ url: base }, controller.signal))
.rejects.toThrow(expect.objectContaining({ code: 'WEB_ABORTED' }))
})
it('aborts an in-flight fetch via the signal', async () => {
handler = (_req, _res) => { /* never responds */ }
const controller = new AbortController()
const promise = provider().fetch({ url: base }, { signal: controller.signal })
const promise = provider().fetch({ url: base }, controller.signal)
controller.abort()
await expect(promise).rejects.toThrow(expect.objectContaining({ code: 'WEB_ABORTED' }))
})
@@ -325,11 +324,6 @@ describe('LocalFetchProvider invalid URLs and abort', () => {
.rejects.toThrow(expect.objectContaining({ code: 'WEB_PROVIDER_ERROR' }))
})
it('caps the per-request timeout at maxTimeoutMs', async () => {
handler = (_req, res) => { res.writeHead(200, { 'content-type': 'text/plain' }); res.end('ok') }
const result = await provider({ maxTimeoutMs: 10_000 }).fetch({ url: base, timeoutMs: 999_999 })
expect(result.statusCode).toBe(200)
})
})
describe('LocalFetchProvider body cancellation on error paths', () => {
@@ -378,7 +372,7 @@ describe('web-fetch-local plugin registration', () => {
await ctx.plugin(WebService, { fetchProvider: LOCAL_FETCH_PROVIDER_ID })
const fiber = await ctx.plugin(fetchPlugin, {})
await expect(ctx.web.fetch({ url: `${base}/` }))
.resolves.toMatchObject({ providerId: LOCAL_FETCH_PROVIDER_ID, statusCode: 200 })
.resolves.toMatchObject({ statusCode: 200 })
await fiber.dispose()
await expect(ctx.web.fetch({ url: `${base}/` }))
.rejects.toThrow(expect.objectContaining({ code: 'WEB_PROVIDER_CONFIGURED_MISSING' }))
@@ -421,7 +415,7 @@ describe('web-fetch-local plugin registration', () => {
await ctx.plugin(WebService, { fetchProvider: LOCAL_FETCH_PROVIDER_ID })
const fiber = await ctx.plugin(fetchPlugin, { maxRedirects: 0 })
await expect(ctx.web.fetch({ url: `${base}/` }))
.resolves.toMatchObject({ providerId: LOCAL_FETCH_PROVIDER_ID, statusCode: 200 })
.resolves.toMatchObject({ statusCode: 200 })
await fiber.dispose()
})
})