Merge remote-tracking branch 'origin/master' into worktree/pi-ai-manual-e2e

packages/llm/llm-deepseek/README.md

@@ -4,6 +4,8 @@ DeepSeek chat-completions adapter for the harness LLM seam: hand-rolled `fetch`
 
 A second, library-backed implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai`. This package always owns the `deepseek` provider route; mounting a pi-ai profile with `provider: deepseek` in the same context throws `LlmError('DUPLICATE_ADAPTER')` by design.
 
+The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire serialization, SSE parsing, and chunk translation helpers are not part of that root contract.
+
 ## Config
 
 ```yaml

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

@@ -98,10 +98,10 @@ export class DeepSeekAdapter extends LlmAdapter {
         const parsed = await response.json() as WireError
         if (parsed.error?.message) message = parsed.error.message
       } catch {
-        // Only swallow error-body parsing: status and code are already captured,
-        // so malformed gateway JSON must not mask the actionable HTTP failure.
+        // Only swallow error-body parsing: the stable code and status-line message
+        // are already captured, so malformed gateway JSON must not mask the failure.
       }
-      throw new LlmError(message, code, response.status)
+      throw new LlmError(message, code)
     }
     if (!response.body) {
       throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE')

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

@@ -11,12 +11,9 @@ import type {} from '@deepseek-ai/dsh-llm'
 import { DeepSeekAdapter } from './adapter.ts'
 import type { DeepSeekCatalogModel } from './adapter.ts'
 
-export { DeepSeekAdapter, httpErrorCode } from './adapter.ts'
+export { DeepSeekAdapter } from './adapter.ts'
 export type { DeepSeekAdapterOptions, DeepSeekCatalogModel } from './adapter.ts'
-export { serializeMessages, serializeRequest } from './serialize.ts'
 export type { RequestDefaults } from './serialize.ts'
-export { DONE, parseSse } from './sse.ts'
-export { mapFinishReason, mapUsage, translate } from './translate.ts'
 export type * from './types.ts'
 
 export const name = 'llm-deepseek'

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

@@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
-import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek'
+import { DeepSeekAdapter } from '@deepseek-ai/dsh-llm-deepseek'
+import { httpErrorCode } from '../src/adapter.ts'
 import { assemble } from './assemble.ts'
 
 /** One scripted behavior for the next request the mock server receives. */
@@ -159,7 +160,7 @@ 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, behavior])
+    const server = await mockServer([behavior, behavior])
     const ctx = await harness(server.url)
     await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }))
       .rejects.toThrow(`failed with ${status}`)
@@ -167,11 +168,6 @@ 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 () => {
@@ -241,6 +237,19 @@ describe('DeepSeekAdapter against a mock server', () => {
 })
 
 describe('plugin registration and config', () => {
+  it('keeps wire helpers off the package root', () => {
+    for (const helper of [
+      'httpErrorCode',
+      'serializeMessages',
+      'serializeRequest',
+      'DONE',
+      'parseSse',
+      'mapFinishReason',
+      'mapUsage',
+      'translate',
+    ]) expect(LlmDeepSeek).not.toHaveProperty(helper)
+  })
+
   it('registers the deepseek provider and unregisters on dispose (HMR safety)', async () => {
     const server = await mockServer([])
     const ctx = new Context()

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

@@ -1,7 +1,7 @@
 import { describe, expect, it } from 'vitest'
 import { CallId } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-llm'
-import { serializeMessages, serializeRequest } from '@deepseek-ai/dsh-llm-deepseek'
+import { serializeMessages, serializeRequest } from '../src/serialize.ts'
 
 function request(overrides: Partial<GenerateOptions> = {}): GenerateOptions {
   return { provider: 'deepseek', model: 'deepseek-v4-flash', messages: [], ...overrides }

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

@@ -1,6 +1,6 @@
 import { describe, expect, it } from 'vitest'
 import { LlmError } from '@deepseek-ai/dsh-llm'
-import { DONE, parseSse } from '@deepseek-ai/dsh-llm-deepseek'
+import { DONE, parseSse } from '../src/sse.ts'
 
 /** Build a byte stream from string fragments (fragments = network reads). */
 async function* bytes(...fragments: (string | Uint8Array)[]): AsyncGenerator<Uint8Array> {

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

@@ -1,7 +1,8 @@
 import { describe, expect, it } from 'vitest'
 import { BlockAssembler, LlmError } from '@deepseek-ai/dsh-llm'
 import type { StreamChunk } from '@deepseek-ai/dsh-llm'
-import { DONE, mapFinishReason, mapUsage, translate } from '@deepseek-ai/dsh-llm-deepseek'
+import { DONE } from '../src/sse.ts'
+import { mapFinishReason, mapUsage, translate } from '../src/translate.ts'
 
 async function* feed(...payloads: (string | object)[]): AsyncGenerator<string> {
   for (const payload of payloads) {

packages/llm/llm-pi-ai/README.md

@@ -2,6 +2,8 @@
 
 Generic multi-provider adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai). One plugin instance owns an explicit list of provider profiles; every request selects a profile with `GenerateOptions.provider` and resolves `GenerateOptions.model` dynamically from pi-ai's installed catalog.
 
+The package root exposes the Cordis plugin contract and `PiAiAdapter`; profile resolution, model construction, replay conversion, and stream conversion remain package-internal.
+
 ## Config
 
 Configure credentials and deployment-specific transport settings per provider. Omitting `apiKey` delegates authentication to pi-ai's provider-native ambient discovery. `baseURL` overrides only the endpoint of the selected catalog model, preserving its API family and compatibility metadata, so private proxies such as `https://proxy.example.com:8443` remain supported.
@@ -76,4 +78,4 @@ Unit tests use pi-ai catalog models redirected to local mock servers and cover p
 - **Catalog membership is required** — custom model ids that are absent from the installed pi-ai catalog fail with `UNKNOWN_MODEL`, even when a provider profile supplies a custom endpoint.
 - **`GenerateOptions.stop` is unsupported** — pi-ai's common stream options cannot guarantee stop-sequence behavior across providers, so the adapter rejects the field.
 - **In-history `system` messages use pi-ai's common context conversion** — provider-specific placement follows pi-ai rather than a harness-owned wire override.
-- **`LlmError.status` is unavailable for in-stream failures** — pi-ai error events do not expose a stable HTTP status across providers.
+- **Provider HTTP status is unavailable** — pi-ai error events do not expose a stable HTTP status across providers; failures expose only stable harness error codes.

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

@@ -27,12 +27,8 @@ import { Config, resolveProfiles } from './config.ts'
 
 export { PiAiAdapter } from './adapter.ts'
 export type { PiAiAdapterOptions } from './adapter.ts'
-export { Config, resolveProfiles } from './config.ts'
+export { Config } from './config.ts'
 export type { PiAiProviderProfile } from './config.ts'
-export { toPiContext } from './context.ts'
-export { toPiReplayState } from './replay.ts'
-export type { PiAiReplayState } from './replay.ts'
-export { mapStopReason, mapUsage, toStreamChunks } from './stream.ts'
 
 export const name = 'llm-pi-ai'
 export const inject = ['llm']

packages/llm/llm-pi-ai/tests/adapter.spec.ts

@@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm'
 import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai'
-import { PiAiAdapter, resolveProfiles } from '@deepseek-ai/dsh-llm-pi-ai'
+import { PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai'
+import { resolveProfiles } from '../src/config.ts'
 import { assemble } from './assemble.ts'
 
 interface MockServer {
@@ -180,6 +181,18 @@ describe('PiAiAdapter provider routing', () => {
 })
 
 describe('provider profile lifecycle', () => {
+  it('keeps adapter helpers off the package root', () => {
+    for (const helper of [
+      'resolveProfiles',
+      'toPiContext',
+      'toPiReplayState',
+      'toPiAssistant',
+      'mapStopReason',
+      'mapUsage',
+      'toStreamChunks',
+    ]) expect(LlmPiAi).not.toHaveProperty(helper)
+  })
+
   it('registers every profile atomically and unregisters on dispose', async () => {
     const ctx = new Context()
     await ctx.plugin(LlmService)

packages/llm/llm-pi-ai/tests/convert.spec.ts

@@ -2,7 +2,9 @@ import { describe, expect, it } from 'vitest'
 import { CallId, LlmError } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm'
 import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai'
-import { mapStopReason, mapUsage, toPiContext, toPiReplayState, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai'
+import { toPiContext } from '../src/context.ts'
+import { toPiReplayState } from '../src/replay.ts'
+import { mapStopReason, mapUsage, toStreamChunks } from '../src/stream.ts'
 
 function usage(input = 0, output = 0, cacheRead = 0, cacheWrite = 0): Usage {
   return {

packages/llm/llm/README.md

@@ -45,7 +45,7 @@ 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`; `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.
+- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract.
 
 ### Real adapters
 

packages/llm/llm/src/assembler.ts

@@ -39,12 +39,10 @@ export class BlockAssembler {
   private _replayState: unknown = undefined
 
   /**
-   * Feed one chunk. Returns the completed block when the chunk closes one
-   * (an explicit `block-end`), otherwise undefined.
+   * Feed one chunk into the assembly state.
    * @param chunk - the next raw chunk, in stream order.
-   * @returns the authoritative block from the first `block-end` at its index; undefined for every other chunk.
    */
-  push(chunk: StreamChunk): ContentBlock | undefined {
+  push(chunk: StreamChunk): void {
     switch (chunk.type) {
       case 'block-start': {
         if (!this.partials.has(chunk.index)) {
@@ -78,7 +76,7 @@ export class BlockAssembler {
         // and the final assembled block in agreement.
         if (partial.block) return
         partial.block = chunk.block
-        return chunk.block
+        return
       }
       case 'usage': {
         this._usage = chunk.usage

packages/llm/llm/src/index.ts

@@ -43,12 +43,10 @@ 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;
- * `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).
+ * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy.
  */
 export class LlmError extends HarnessError {
-  constructor(message: string, code: string, public status?: number, options?: ErrorOptions) {
+  constructor(message: string, code: string, options?: ErrorOptions) {
     super(message, code, options)
     this.name = 'LlmError'
   }

packages/llm/llm/tests/assembler.spec.ts

@@ -29,12 +29,12 @@ describe('BlockAssembler', () => {
     expect(assembler.message().role).toBe('assistant')
   })
 
-  it('returns the completed block from push() on block-end', () => {
+  it('records the completed block from block-end', () => {
     const assembler = new BlockAssembler()
-    expect(assembler.push({ type: 'block-start', index: 0, blockType: 'text' })).toBeUndefined()
-    expect(assembler.push({ type: 'text-delta', index: 0, text: 'hi' })).toBeUndefined()
-    const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } })
-    expect(block).toEqual({ type: 'text', text: 'hi' })
+    assembler.push({ type: 'block-start', index: 0, blockType: 'text' })
+    assembler.push({ type: 'text-delta', index: 0, text: 'hi' })
+    assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } })
+    expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }])
   })
 
   it('tolerates deltas without explicit block-start/end', () => {
@@ -57,8 +57,8 @@ describe('BlockAssembler', () => {
     // push a delta first to guarantee the partial exists
     assembler.push({ type: 'text-delta', index: 0, text: 'hi' })
     // block-end's ensure() must find the existing partial (the second branch path)
-    const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } })
-    expect(block).toEqual({ type: 'text', text: 'hi' })
+    assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } })
+    expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }])
   })
 
   it('throws from assemble() when a partial has an unhandled blockType', () => {
@@ -128,7 +128,7 @@ describe('assertNever', () => {
 
   it('BlockAssembler.push rejects chunks outside the closed StreamChunk union', () => {
     const assembler = new BlockAssembler()
-    expect(() => assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk))
+    expect(() => { assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk) })
       .toThrow('unreachable variant in BlockAssembler.push')
   })
 })
@@ -140,26 +140,8 @@ describe('BlockAssembler duplicate-close contract', () => {
       { type: 'block-end', index: 0, block: { type: 'reasoning', text: 'first' } },
       { type: 'block-end', index: 0, block: { type: 'text', text: 'second' } },
     ]
-    const streaming = new BlockAssembler()
-    const closed = []
-    for (const chunk of chunks) {
-      const block = streaming.push(chunk)
-      if (block) closed.push(block)
-    }
-
-    const oneShot = new BlockAssembler()
-    for (const chunk of chunks) oneShot.push(chunk)
-
-    expect(closed).toEqual([{ type: 'reasoning', text: 'first' }])
-    expect(oneShot.blocks()).toEqual([{ type: 'reasoning', text: 'first' }])
-    expect(closed).toEqual(oneShot.blocks())
-  })
-
-  it('push returns undefined for a duplicate block-end (it closed nothing)', () => {
-    const a = new BlockAssembler()
-    expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'x' } }))
-      .toEqual({ type: 'text', text: 'x' })
-    expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'y' } }))
-      .toBeUndefined()
+    const assembler = new BlockAssembler()
+    for (const chunk of chunks) assembler.push(chunk)
+    expect(assembler.blocks()).toEqual([{ type: 'reasoning', text: 'first' }])
   })
 })

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

@@ -255,11 +255,12 @@ describe('LlmService', () => {
 
   it('LlmError extends the shared HarnessError base', async () => {
     const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm')
-    const err = new LlmError('boom', 'AUTH', 401)
+    const cause = new Error('root cause')
+    const err = new LlmError('boom', 'AUTH', { cause })
     expect(err).toBeInstanceOf(HarnessError)
     expect(isHarnessError(err)).toBe(true)
     expect(err.code).toBe('AUTH')
-    expect(err.status).toBe(401)
+    expect(err.cause).toBe(cause)
   })
 
   it('HarnessError carries a code, names itself by subclass, and chains cause', async () => {