feat(core): add post-step request recovery (PR3 phase 1)

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

@@ -7,7 +7,7 @@ DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](ht
 `@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose:
 
 - pi-ai hands tool-call `arguments` around as **parsed objects**; the harness keeps raw JSON strings. The adapter patches replay payloads back to the original raw strings before sending them, and re-stringifies parsed output tool calls at `block-end`.
-- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses).
+- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). Context-overflow detail maps to the same canonical `CONTEXT_WINDOW_EXCEEDED` code as the hand-rolled adapter.
 - pi-ai folds reasoning tokens into `usage.output`; there is no separate reasoning count to map.
 - pi-ai's options omit some DeepSeek/OpenAI-compatible details; the adapter uses its `onPayload` hook to preserve the harness contract (`stop`, scrubbing pi-ai's own per-tool `strict` default — the hand-rolled twin sends no such field — omitted reasoning effort, raw replayed tool arguments).
 

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

@@ -8,7 +8,7 @@
  * @module dsh-llm-pi-ai/convert
  */
 
-import { CallId, LlmError } from '@deepseek-ai/dsh-llm'
+import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmError } from '@deepseek-ai/dsh-llm'
 import type { FinishReason, GenerateOptions, Message, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm'
 import type {
   AssistantMessage,
@@ -165,6 +165,7 @@ export function mapUsage(usage: PiUsage): TokenUsage {
 function classifyPiAiError(message: string): string {
   if (/\b(?:401|403)\b/.test(message)) return 'AUTH'
   if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT'
+  if (isContextWindowExceededError(message)) return CONTEXT_WINDOW_EXCEEDED_CODE
   if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST'
   if (/\b5\d\d\b/.test(message)) return 'SERVER'
   return 'PI_AI_ERROR'

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

@@ -1,5 +1,5 @@
 import { describe, expect, it } from 'vitest'
-import { CallId } from '@deepseek-ai/dsh-llm'
+import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE } 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, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai'
@@ -300,6 +300,18 @@ describe('mapStopReason / mapUsage', () => {
       .toMatchObject({ kind: 'error', code: 'RATE_LIMIT' })
     expect(mapStopReason(assistant({ stopReason: 'error', errorMessage: 'HTTP 500: backend down' })))
       .toMatchObject({ kind: 'error', code: 'SERVER' })
+    expect(mapStopReason(assistant({
+      stopReason: 'error',
+      errorMessage: 'HTTP 400: input exceeds the model context window limit',
+    }))).toMatchObject({ kind: 'error', code: CONTEXT_WINDOW_EXCEEDED_CODE })
+    expect(mapStopReason(assistant({
+      stopReason: 'error',
+      errorMessage: 'HTTP 400: request too large for model context',
+    }))).toMatchObject({ kind: 'error', code: CONTEXT_WINDOW_EXCEEDED_CODE })
+    expect(mapStopReason(assistant({
+      stopReason: 'error',
+      errorMessage: 'HTTP 400: invalid input: temperature exceeds maximum allowed value',
+    }))).toMatchObject({ kind: 'error', code: 'INVALID_REQUEST' })
   })
 
   it('maps cache fields only when nonzero', () => {