feat(llm): interrogate a draft provider endpoint for its models

Once a pi-ai route became a declaration rather than a catalog lookup,
adding an OpenAI-compatible gateway meant knowing its model ids up
front. Most such endpoints publish that list at `GET /models`, but no
seam operation could ask: every one is keyed by a registered provider
route, and the provider being added has no route, no stored profile,
and no stored credential — the endpoint and key are values in a form.

Interrogation is therefore keyed by settings namespace, which a
configuration surface already holds from the configurable-provider
directory. `registerModelDiscovery` offers it per namespace,
`discoverModels` asks, and the request carries the draft itself. The
reply is candidates, not a catalog: every field but the id is optional
because most listings disclose nothing else, and adopting one is a
settings write like any other. Nothing here reads or writes settings or
credentials, so `settings.yaml` still decides what a route serves.

`llm.discoverModels` carries the same draft over the wire. Its apiKey is
the third and last payload a secret may ride, and it is never stored,
logged, or echoed; every refusal folds into `model-discovery-failed`,
naming the endpoint asked but never the credential offered.

The pi-ai side is a plain GET for OpenAI-compatible protocols only —
their listing shape is the one gateways, self-hosted servers, and the
official endpoints agree on. Others say so, sending the user to
hand-entry rather than reporting a guessed shape as an empty provider.
The reply is read under a four-megabyte ceiling held on the bytes
actually received, because the endpoint is a URL the user typed.

packages/llm/llm-pi-ai/src/discovery.ts

@@ -0,0 +1,207 @@
+/**
+ * One-shot interrogation of a provider endpoint's model listing, serving the
+ * configuration surface's "fetch available models" action.
+ *
+ * This is deliberately *not* a catalog refresh. Nothing here is stored: the
+ * request carries a draft the user is still editing — an endpoint and a
+ * credential neither of which may exist in `settings.yaml` yet — and the reply
+ * is candidate metadata the surface offers for adoption. `settings.yaml`
+ * remains the only thing that decides what a route serves.
+ *
+ * Only OpenAI-compatible protocols are interrogated. Their listing is the one
+ * shape a gateway, a self-hosted server, and the official endpoints all agree
+ * on, which is the case this action exists for; every other protocol reports
+ * that it cannot be interrogated so the surface falls back to hand-entry
+ * rather than guessing a response shape.
+ *
+ * @module dsh-llm-pi-ai/discovery
+ */
+
+import { LlmError } from '@deepseek-ai/dsh-llm'
+import type { LlmDiscoveredModel, LlmModelDiscoveryRequest } from '@deepseek-ai/dsh-llm'
+import { attributionHeaders } from '@deepseek-ai/dsh-llm'
+
+/**
+ * Protocols whose model listing this module can read. Every entry speaks
+ * OpenAI's `GET /models` shape; pi-ai's other protocols are absent because a
+ * wrong guess at their response shape would be reported as an empty provider
+ * rather than as the gap it is.
+ */
+const LISTABLE_PROTOCOLS: ReadonlySet<string> = new Set([
+  'azure-openai-responses',
+  'openai-codex-responses',
+  'openai-completions',
+  'openai-responses',
+])
+
+/**
+ * Endpoint replies larger than this are refused. The endpoint is whatever URL
+ * the user typed, so the ceiling holds on the bytes actually read rather than
+ * on the length the server claims — the same two-stage shape `dsh-web-fetch`
+ * uses for its own caller-supplied URLs, except that a truncated model listing
+ * is not parseable, so overflow rejects instead of truncating.
+ */
+const MAX_RESPONSE_BYTES = 4 * 1024 * 1024
+
+/** One entry of an OpenAI-compatible `GET /models` reply. */
+interface ListingEntry {
+  id?: unknown
+  /** Common gateway extensions; absent from the official listings. */
+  name?: unknown
+  display_name?: unknown
+  context_window?: unknown
+  context_length?: unknown
+  max_tokens?: unknown
+  max_output_tokens?: unknown
+}
+
+/** A positive integer field of a listing entry, or `undefined` when absent or unusable. */
+function capacity(...candidates: readonly unknown[]): number | undefined {
+  for (const candidate of candidates) {
+    if (typeof candidate === 'number' && Number.isInteger(candidate) && candidate > 0) return candidate
+  }
+  return undefined
+}
+
+/** A non-empty string field of a listing entry, or `undefined`. */
+function label(...candidates: readonly unknown[]): string | undefined {
+  for (const candidate of candidates) {
+    if (typeof candidate === 'string' && candidate.length > 0) return candidate
+  }
+  return undefined
+}
+
+/**
+ * Join the endpoint base with the listing path. The base is treated as a
+ * prefix rather than a URL to resolve against, so a deployment path such as
+ * `https://gateway.example/openai/v1` keeps its segments instead of losing
+ * them to `URL` resolution.
+ */
+function listingUrl(baseURL: string): string {
+  return `${baseURL.replace(/\/+$/, '')}/models`
+}
+
+/**
+ * Read a reply body, refusing one that outgrows the ceiling. A declared length
+ * is checked first so an honest server is turned away without transferring
+ * anything; the accumulated total is what actually enforces the bound, because
+ * a server that under-declares (or streams) tells us nothing up front.
+ */
+async function readBounded(response: Response, url: string): Promise<string> {
+  const oversized = (): LlmError =>
+    new LlmError(`${url} answered with more than ${MAX_RESPONSE_BYTES} bytes`, 'DISCOVERY_FAILED')
+  const declared = Number(response.headers.get('content-length') ?? Number.NaN)
+  if (Number.isFinite(declared) && declared > MAX_RESPONSE_BYTES) {
+    await response.body?.cancel()
+    throw oversized()
+  }
+  /* v8 ignore next -- fetch always exposes a body stream on a 2xx Response; the null guard is defensive. */
+  if (response.body === null) return ''
+  const reader = response.body.getReader()
+  const chunks: Uint8Array[] = []
+  let total = 0
+  try {
+    for (;;) {
+      const { done, value } = await reader.read()
+      if (done) break
+      total += value.byteLength
+      if (total > MAX_RESPONSE_BYTES) throw oversized()
+      chunks.push(value)
+    }
+  } finally {
+    /* v8 ignore next 4 -- cancel() after a completed or abandoned read settles without rejecting; unobserved best-effort cleanup. */
+    await reader.cancel().catch(() => {
+      // Cancel after a drained read, or after this function walked away from
+      // an oversized one, is cleanup; the reply is already decided either way.
+    })
+  }
+  const body = new Uint8Array(total)
+  let offset = 0
+  for (const chunk of chunks) {
+    body.set(chunk, offset)
+    offset += chunk.byteLength
+  }
+  return new TextDecoder().decode(body)
+}
+
+/**
+ * Read one OpenAI-compatible listing reply. Entries without a usable id are
+ * skipped rather than failing the whole interrogation: a single malformed row
+ * should not deny the user the rest of a working endpoint's catalog.
+ */
+function readListing(body: unknown): LlmDiscoveredModel[] {
+  const data = (body as { data?: unknown } | null)?.data
+  if (!Array.isArray(data)) {
+    throw new LlmError(
+      'the endpoint\'s model listing has no "data" array; enter this provider\'s models by hand',
+      'DISCOVERY_FAILED',
+    )
+  }
+  const models: LlmDiscoveredModel[] = []
+  for (const raw of data) {
+    const entry = raw as ListingEntry | null
+    const id = label(entry?.id)
+    if (id === undefined) continue
+    const name = label(entry?.name, entry?.display_name)
+    const contextWindow = capacity(entry?.context_window, entry?.context_length)
+    const maxTokens = capacity(entry?.max_output_tokens, entry?.max_tokens)
+    models.push({
+      id,
+      ...name === undefined ? {} : { name },
+      ...contextWindow === undefined ? {} : { contextWindow },
+      ...maxTokens === undefined ? {} : { maxTokens },
+    })
+  }
+  return models
+}
+
+/**
+ * Interrogate one draft provider endpoint for the models it advertises.
+ * @param request - the endpoint, protocol, and one-shot credential to use.
+ * @returns the advertised models in endpoint order.
+ * @throws LlmError when the protocol has no readable listing, the endpoint
+ *   refuses or fails the request, or the reply is not a model listing.
+ */
+export async function discoverModels(
+  request: LlmModelDiscoveryRequest,
+): Promise<readonly LlmDiscoveredModel[]> {
+  const api = request.api ?? 'openai-completions'
+  if (!LISTABLE_PROTOCOLS.has(api)) {
+    throw new LlmError(
+      `pi-ai protocol "${api}" has no model listing this build can read; enter this provider's models by hand`,
+      'DISCOVERY_UNSUPPORTED',
+    )
+  }
+  const url = listingUrl(request.baseURL)
+  let response: Response
+  try {
+    response = await fetch(url, {
+      method: 'GET',
+      headers: {
+        accept: 'application/json',
+        ...request.apiKey === undefined ? {} : { authorization: `Bearer ${request.apiKey}` },
+        ...attributionHeaders(),
+      },
+      ...request.signal === undefined ? {} : { signal: request.signal },
+    })
+  } catch (error: unknown) {
+    if (request.signal?.aborted) {
+      throw new LlmError('model discovery aborted by caller', 'ABORTED', { cause: error })
+    }
+    throw new LlmError(`could not reach ${url}`, 'DISCOVERY_FAILED', { cause: error })
+  }
+  if (!response.ok) {
+    throw new LlmError(
+      `${url} answered ${response.status}${response.status === 401 || response.status === 403 ? '; check the API key' : ''}`,
+      'DISCOVERY_FAILED',
+    )
+  }
+  const text = await readBounded(response, url)
+  let body: unknown
+  try {
+    body = JSON.parse(text)
+  } catch (error: unknown) {
+    throw new LlmError(`${url} did not answer with JSON`, 'DISCOVERY_FAILED', { cause: error })
+  }
+  return readListing(body)
+}

packages/llm/llm-pi-ai/src/index.ts

@@ -50,6 +50,7 @@ import { PiAiAdapter } from './adapter.ts'
 import { catalogProviderIds } from './catalog.ts'
 import { assertServiceable, Config, resolveProfiles } from './config.ts'
 import type { ResolvedPiAiProviderProfile } from './config.ts'
+import { discoverModels } from './discovery.ts'
 
 export { PiAiAdapter } from './adapter.ts'
 export type { PiAiAdapterOptions } from './adapter.ts'
@@ -176,6 +177,10 @@ export function apply(ctx: Context, config: Config): void {
     directoryFacts = entries
   }
   ensureDirectory()
+  // Interrogating an endpoint is a configuration-time action over a draft, so
+  // it is offered for the whole namespace rather than per route: the provider
+  // a surface is adding does not exist yet.
+  ctx.llm.registerModelDiscovery(NS, discoverModels)
   // Route effects bind to this apply fiber via the stable `ctx` reference,
   // even when a swap runs inside the scoped settings callback below. A bare
   // mount (zero routes) is the dormant posture: nothing registers until a