fix: retain LLM HTTP status metadata

packages/llm/llm-deepseek/src/adapter.ts

@@ -76,7 +76,7 @@ export class DeepSeekAdapter extends LlmAdapter {
         // Only swallow error-body parsing: status and code are already captured,
         // so malformed gateway JSON must not mask the actionable HTTP failure.
       }
-      throw new LlmError(message, code)
+      throw new LlmError(message, code, response.status)
     }
     if (!response.body) {
       throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE')

packages/llm/llm-deepseek/tests/adapter.spec.ts

@@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => {
       status,
       body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }),
     }
-    const server = await mockServer([behavior, behavior])
+    const server = await mockServer([behavior, behavior, behavior])
     const ctx = await harness(server.url)
     await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }))
       .rejects.toThrow(`failed with ${status}`)
@@ -166,6 +166,11 @@ describe('DeepSeekAdapter against a mock server', () => {
       assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })
         .catch((error: unknown) => (error as LlmError).code),
     ).resolves.toBe(code)
+    // The numeric HTTP status is carried on the error for explicit handling.
+    await expect(
+      assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })
+        .catch((error: unknown) => (error as LlmError).status),
+    ).resolves.toBe(status)
   })
 
   it('keeps the status-line message for JSON error bodies without a message', async () => {

packages/llm/llm/README.md

@@ -42,7 +42,7 @@ Every product adapter sends application identity on provider HTTP requests. `att
 - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`.
 - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history.
 - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams.
-- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract.
+- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response.
 
 ### Real adapters
 

packages/llm/llm/src/index.ts

@@ -42,10 +42,12 @@ declare module 'cordis' {
 
 /**
  * Typed error for LLM-related failures. Extends {@link HarnessError}, so the
- * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy.
+ * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy;
+ * `status` carries the HTTP status when the error originated from a non-2xx
+ * provider response (absent for protocol/usage errors that have no HTTP status).
  */
 export class LlmError extends HarnessError {
-  constructor(message: string, code: string, options?: ErrorOptions) {
+  constructor(message: string, code: string, public status?: number, options?: ErrorOptions) {
     super(message, code, options)
     this.name = 'LlmError'
   }

packages/llm/llm/tests/service.spec.ts

@@ -79,12 +79,11 @@ describe('LlmService', () => {
 
   it('LlmError extends the shared HarnessError base', async () => {
     const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm')
-    const cause = new Error('root cause')
-    const err = new LlmError('boom', 'AUTH', { cause })
+    const err = new LlmError('boom', 'AUTH', 401)
     expect(err).toBeInstanceOf(HarnessError)
     expect(isHarnessError(err)).toBe(true)
     expect(err.code).toBe('AUTH')
-    expect(err.cause).toBe(cause)
+    expect(err.status).toBe(401)
   })
 
   it('HarnessError carries a code, names itself by subclass, and chains cause', async () => {

packages/support/llm-replay/src/index.ts

@@ -20,7 +20,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm'
  */
 export type ReplayEntry =
   | { kind: 'chunks'; chunks: StreamChunk[] }
-  | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string }
+  | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number }
   | { kind: 'hang' }
 
 /** Resolved plugin configuration. */
@@ -221,7 +221,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined)
         if (signal?.aborted) throw new Error('aborted')
         yield chunk
       }
-      throw new LlmError(entry.message, entry.code)
+      throw new LlmError(entry.message, entry.code, entry.status)
     case 'hang':
       // Replay a stream that stalls until cancelled (mirrors MockAdapter): one
       // chunk, then wait for abort and surface it as the consumer expects.

packages/support/llm-replay/tests/llm-replay.spec.ts

@@ -175,7 +175,7 @@ describe('loadReplayScript', () => {
   it('uses the sidecar override when present, ignoring the JSONL', () => {
     writeFileSync(file, sessionJsonl([]), 'utf8')
     const overrideFile = join(dir, 'replay.override.json')
-    const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }]
+    const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }]
     writeFileSync(overrideFile, JSON.stringify(override), 'utf8')
     expect(loadReplayScript({ file, overrideFile })).toEqual(override)
   })
@@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => {
     expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second)
   })
 
-  it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => {
+  it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => {
     writeFileSync(file, sessionJsonl([]), 'utf8')
     const overrideFile = join(dir, 'replay.override.json')
     const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }]
     writeFileSync(overrideFile, JSON.stringify([
-      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' },
+      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 },
     ]), 'utf8')
     const ctx = new Context()
     await ctx.plugin(LlmService)
@@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
     const seen: StreamChunk[] = []
     await expect((async () => {
       for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c)
-    })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' })
+    })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 })
     expect(seen).toEqual(partial)
   })
 
@@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => {
     const overrideFile = join(dir, 'replay.override.json')
     const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }]
     writeFileSync(overrideFile, JSON.stringify([
-      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' },
+      { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 },
     ]), 'utf8')
     const ctx = new Context()
     await ctx.plugin(LlmService)