Expose audited hardcoded tunables as plugin config

The audit swept every packages/*/* plugin for the new AGENTS.md
convention (no hardcoded tunables in plugins) and exposes each finding
as a defaulted, validated Config field. Defaults are the previously
hardcoded values throughout, so no deployment or golden changes.

- tool-fs (had NO Config): readLimit, readMaxLineLength, readMaxBytes,
  readStreamMinSize. The caps thread through ReadToolCaps/ReadWindow —
  read-render already documented that the consumer applies the caps, so
  they become explicit per-request fields.
- tool-web: searchMaxResults (WEB_SEARCH_MAX_RESULTS stays as the
  schemastery default). Also fixes the stale GREP_LIMIT references in
  search.ts and the web-capability-seam RFC (no such constant exists).
- bash-local: graceMs (SIGTERM->SIGKILL escalation grace). The
  RunInternals.graceMs test seam is gone: graceMs is now a required
  SpawnSpec field filled from config, so tests exercise the real
  config path and the defaults live in exactly one place.
- subagent-acp: disposeEofGraceMs / disposeGraceMs. The AcpRunSpec
  fields become required for the same one-defaulting-layer reason.
- session-persistence-sqlite: journalMode ('wal' default; the
  rollback-journal modes serve filesystems where WAL's shared-memory
  files do not work, e.g. network mounts).
- hooks-claude + hooks-codex: stderrSummaryMaxChars for the persisted
  hook/result stderr summary. The duplicated summarize() helpers merge
  into hook-protocol's summarizeStderr(stderr, maxChars), beside the
  HookResultRecord field it feeds, with the bound parameterized the
  same way runHook's defaultTimeoutMs already is.
- compact-basic: charsPerToken for the token estimator (default 4, the
  English-text heuristic; CJK-heavy deployments need ~1-2 or compaction
  fires far too late). Also corrects the BasicCompactService class doc,
  which claimed defaults the required-field config never had.
- fs-local: deletes the dead STREAM_MIN_SIZE constant and the dead
  FsIoInternals.streamMinSize seam — the read-routing bound lives in
  the consumer (tool-fs), where it is now config. This is item 1 of
  the proposed prune-write-only-fs-surface RFC, annotated accordingly.

Every new field gets range validation (following the existing
assertPositiveFinite pattern), a README row, and tests covering the
configured behavior, the schema default, and load-time rejection.
This commit is contained in:
Tianyi Cui
2026-07-04 17:37:23 +08:00
parent bee8132a7f
commit 774d460889
45 changed files with 592 additions and 171 deletions

View File

@@ -17,6 +17,7 @@ Each tool is registered independently; a product that wants only one disables th
|---|---|---|
| `search` | `true` | Register `web_search`. |
| `fetch` | `true` | Register `web_fetch`. |
| `searchMaxResults` | `8` | Upper bound on sources returned by one `web_search` call (the seam truncates a longer provider list and flags it). |
```yaml
- id: tool-web

View File

@@ -20,7 +20,7 @@
import type { Context } from 'cordis'
import z from 'schemastery'
import type {} from '@deepseek-ai/dsh-web'
import { applyWebSearchTool } from './search.ts'
import { applyWebSearchTool, WEB_SEARCH_MAX_RESULTS } from './search.ts'
import { applyWebFetchTool } from './fetch.ts'
export { WEB_SEARCH_MAX_RESULTS, applyWebSearchTool, formatSearchOutput, parseSearchArgs, presentSearchCall } from './search.ts'
@@ -38,13 +38,26 @@ export interface Config {
search?: boolean
/** Register `web_fetch`. Defaults to true. */
fetch?: boolean
/** Upper bound on sources returned by one `web_search` call. */
searchMaxResults?: number
}
export const Config: z<Config> = z.object({
search: z.boolean().default(true),
fetch: z.boolean().default(true),
searchMaxResults: z.number().default(WEB_SEARCH_MAX_RESULTS),
})
/** The shape after schemastery applies its defaults to every field. */
type ResolvedConfig = Required<Config>
/** The result cap must be a positive integer (it bounds a provider's source list). */
function assertPositiveInteger(name: string, value: number): void {
if (!Number.isInteger(value) || value < 1) {
throw new Error(`tool-web: ${name} must be a positive integer`)
}
}
/**
* Register the enabled web tools. `search`/`fetch` default to true; a product
* that wants only one disables the other in config. The tools' disposers are
@@ -52,6 +65,9 @@ export const Config: z<Config> = z.object({
* teardown is needed.
*/
export function apply(ctx: Context, config: Config): void {
if (config.search !== false) applyWebSearchTool(ctx)
if (config.fetch !== false) applyWebFetchTool(ctx)
// schemastery (Config) has already filled every defaulted field.
const resolved = config as ResolvedConfig
assertPositiveInteger('searchMaxResults', resolved.searchMaxResults)
if (resolved.search) applyWebSearchTool(ctx, resolved.searchMaxResults)
if (resolved.fetch) applyWebFetchTool(ctx)
}

View File

@@ -13,10 +13,10 @@ import type { WebSearchResult } from '@deepseek-ai/dsh-web'
import type {} from '@deepseek-ai/dsh-system-prompt'
/**
* Default upper bound on returned sources. Owned by the consumer (not the
* provider or model), mirroring `dsh-tool-fs`'s `READ_LIMIT`/`GREP_LIMIT`. The
* model just asks a question; the product controls how much context returns.
* The default `8` aligns with OpenCode's Exa default.
* Default upper bound on returned sources (the `searchMaxResults` config).
* Owned by the consumer (not the provider or model), mirroring `dsh-tool-fs`'s
* `READ_LIMIT`. The model just asks a question; the product controls how much
* context returns. The default `8` aligns with OpenCode's Exa default.
*/
export const WEB_SEARCH_MAX_RESULTS = 8
@@ -67,8 +67,8 @@ export function presentSearchCall(args: { query: string }): GenericCallView {
return { card: 'generic', title: args.query, kind: 'search', rawInput: args.query }
}
/** Register the `web_search` tool and its system-prompt guidance. */
export function applyWebSearchTool(ctx: Context): void {
/** Register the `web_search` tool and its system-prompt guidance. `maxResults` is the deployment's source cap. */
export function applyWebSearchTool(ctx: Context, maxResults: number): void {
ctx.systemPrompt.section({
name: 'tool:web_search',
order: 110,
@@ -84,7 +84,7 @@ export function applyWebSearchTool(ctx: Context): void {
async execute(args, exec): Promise<ContentBlock[]> {
const input = parseSearchArgs(args)
const result = await ctx.web.search(
{ query: input.query, maxResults: WEB_SEARCH_MAX_RESULTS },
{ query: input.query, maxResults },
exec.signal ? { signal: exec.signal } : undefined,
)
return [{ type: 'text', text: formatSearchOutput(result) }]

View File

@@ -15,6 +15,7 @@ import {
presentFetchCall,
renderBody,
htmlToMarkdown,
WEB_SEARCH_MAX_RESULTS,
} from '@deepseek-ai/dsh-tool-web'
const available: WebProviderStatus = { available: true }
@@ -279,3 +280,48 @@ describe('tool-web execution through the real registry', () => {
await fiber.dispose()
})
})
describe('searchMaxResults is plugin config', () => {
it('forwards the default cap to the seam when unconfigured', async () => {
const seen: { maxResults?: number | undefined } = {}
const provider: WebSearchProvider = {
id: 'stub-search',
status: () => available,
search: (request) => { seen.maxResults = request.maxResults; return Promise.resolve({ providerId: 'stub-search', query: 'q', sources: [], truncated: false }) },
}
const { fiber, call } = await mountTools({ webConfig: { searchProvider: 'stub-search' }, search: provider })
await call('web_search', { query: 'q' })
expect(seen.maxResults).toBe(WEB_SEARCH_MAX_RESULTS)
await fiber.dispose()
})
it('forwards a configured cap to the seam, which enforces it', async () => {
const sources = Array.from({ length: 5 }, (_, i) => ({ url: `https://s${i}.test` }))
const provider: WebSearchProvider = {
id: 'stub-search',
status: () => available,
search: request => Promise.resolve({ providerId: 'stub-search', query: request.query, sources, truncated: false }),
}
const { fiber, call } = await mountTools({ config: { searchMaxResults: 2 }, webConfig: { searchProvider: 'stub-search' }, search: provider })
const out = await call('web_search', { query: 'q' })
expect(out.isError).toBe(false)
const body = out.content.map(b => b.text).join('')
expect(body).toContain('https://s1.test')
expect(body).not.toContain('https://s2.test')
expect(body).toContain('Showing the first 2 sources.')
await fiber.dispose()
})
it.each([
['zero', 0],
['negative', -3],
['fractional', 1.5],
])('rejects a %s searchMaxResults at load', async (_label, value) => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(WebService, {})
await expect(ctx.plugin(ToolWeb, { searchMaxResults: value }))
.rejects.toThrow(/tool-web: searchMaxResults must be a positive integer/)
})
})