Merge remote-tracking branch 'origin/master' into worktree/routed-model-compaction-policy

# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md
#	.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	examples/headless-agent/tests/harness.ts
#	examples/repl-agent/cordis.yml
#	packages/compact/compact-basic/README.md
#	packages/compact/compact-basic/src/index.ts
#	packages/compact/compact-basic/tests/compact-basic.spec.ts
#	packages/compact/compact-basic/tests/loader-composition.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/llm/README.md
#	packages/llm/llm-deepseek/src/adapter.ts
#	packages/llm/llm-pi-ai/src/adapter.ts
#	packages/llm/llm/README.md
#	packages/llm/llm/src/index.ts
#	scripts/gen-cordis-catalog.ts
#	website/zh-CN/api/harness/events.md
#	website/zh-CN/api/harness/llm.md
#	website/zh-CN/api/harness/token-meter.md
#	website/zh-CN/guide/config.md

packages/compact/compact-basic/tests/compact-basic.spec.ts

@@ -11,9 +11,16 @@ import {
 } from '@deepseek-ai/dsh-compact-basic/src/config.ts'
 import type { CompactionResult } from '@deepseek-ai/dsh-compact'
 import LlmService, { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, LlmAdapter } from '@deepseek-ai/dsh-llm'
-import type { ContentBlock, GenerateOptions, LlmModelContext, StreamChunk } from '@deepseek-ai/dsh-llm'
+import type {
+  ContentBlock,
+  GenerateOptions,
+  LlmFailure,
+  LlmModelContext,
+  StreamChunk,
+} from '@deepseek-ai/dsh-llm'
 import { Session, SessionId } from '@deepseek-ai/dsh-session'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 
 const SIGNAL = new AbortController().signal
@@ -132,6 +139,43 @@ function toolConversation(): Session {
   return session
 }
 
+/** One closed routed tool step followed by an open turn for rewrite events. */
+function oversizedToolResult(chars = 3_000, withCompactablePrompt = false): Session {
+  const session = new Session(SessionId(`oversized-tool-${chars}`))
+  const callId = CallId('oversized')
+  session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+  if (withCompactablePrompt) {
+    session.append('user/message', {
+      content: [{ type: 'text', text: 'older history '.repeat(200) }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+  }
+  session.append('step/start', { turn: 1, step: 1 })
+  session.append('request/header', {
+    header: { config: { provider: MODEL, model: MODEL } },
+    reason: 'initial',
+  })
+  session.append('assistant/message', {
+    turn: 1,
+    step: 1,
+    content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }],
+    provenance: { provider: MODEL, model: MODEL },
+  }, { surfaceOp: 'append' })
+  session.append('tool/call', { turn: 1, step: 1, callId, name: 'bash', arguments: '{}' })
+  session.append('tool/result', {
+    turn: 1,
+    step: 1,
+    callId,
+    content: [{ type: 'text', text: 'X'.repeat(chars) }],
+    isError: false,
+    meta: { presentation: 'preserved' },
+  }, { surfaceOp: 'append' })
+  session.append('step/end', { turn: 1, step: 1 })
+  session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
+  session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } })
+  return session
+}
+
 class TestCompactService extends BasicCompactService {
   summary: ContentBlock[] = [{ type: 'text', text: 'small checkpoint' }]
   summaryProvider = 'summary-provider'
@@ -579,6 +623,78 @@ describe('pressure measurement and retention', () => {
   })
 })
 
+describe('optional model-free tool-result pruning', () => {
+  const pruneConfig = { thresholdChars: 100, headChars: 20, tailChars: 10 }
+
+  it('does not prune a below-pressure session opportunistically', async () => {
+    const ctx = createContext(10_000)
+    const prune = new ToolResultPruneService(ctx, pruneConfig)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.8,
+      retainTokens: 100,
+    })
+    const session = oversizedToolResult()
+    const pruneSession = vi.spyOn(prune, 'pruneSession')
+
+    expect(await compactIfNeeded(compact, session)).toBeNull()
+    expect(pruneSession).not.toHaveBeenCalled()
+    expect(compact.calls).toHaveLength(0)
+    expect(session.surface.replaceGeneration).toBe(0)
+  })
+
+  it('skips LLM summarization when pruning alone clears pressure', async () => {
+    const ctx = createContext(1_000)
+    void new ToolResultPruneService(ctx, pruneConfig)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.5,
+      retainTokens: 50,
+    })
+    const session = oversizedToolResult()
+
+    expect(ctx.tokenMeter.measure(session).totalTokens).toBeGreaterThanOrEqual(500)
+    expect(await compactIfNeeded(compact, session)).toBeNull()
+    expect(ctx.tokenMeter.measure(session).totalTokens).toBeLessThan(500)
+    expect(compact.calls).toHaveLength(0)
+    expect(session.surface.replaceGeneration).toBe(1)
+  })
+
+  it('summarizes the pruned surface when pruning is insufficient', async () => {
+    const ctx = createContext(2_000)
+    void new ToolResultPruneService(ctx, pruneConfig)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.5,
+      retainTokens: 50,
+    })
+    const session = toolConversation()
+
+    expect(await compactIfNeeded(compact, session)).not.toBeNull()
+    expect(compact.calls).toHaveLength(1)
+    expect(compact.calls[0]!.text).toContain('tool result middle pruned')
+    expect(compact.calls[0]!.text).not.toContain('result 1 '.repeat(300))
+  })
+
+  it('retains the original compact-basic behavior without the optional plugin', async () => {
+    const ctx = createContext(2_000)
+    const compact = new TestCompactService(ctx, {
+      auto: false,
+      thresholdRatio: 0.5,
+      retainTokens: 50,
+    })
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await compactIfNeeded(compact, session)).not.toBeNull()
+    expect(compact.calls).toHaveLength(1)
+    const original = session.events.find(event => event.type === 'tool/result')
+    expect(original?.type === 'tool/result' && original.data.content[0])
+      .toEqual({ type: 'text', text: 'X'.repeat(3_000) })
+    expect(session.events.filter(event =>
+      event.type === 'tool/result' && event.surfaceOp !== 'append')).toHaveLength(0)
+  })
+})
+
 describe('compaction region transaction', () => {
   it('lands a framed, replayable checkpoint with exact pricing provenance', async () => {
     const compact = service()
@@ -950,9 +1066,9 @@ describe('default one-shot summarizer', () => {
   })
 
   it.each([
-    [{ kind: 'error', message: 'provider failed', code: 'PROVIDER' }, 'PROVIDER', /provider failed/],
-    [{ kind: 'error', message: 'opaque' }, undefined, /opaque/],
-    [{ kind: 'aborted' }, 'ABORTED', /aborted/],
+    [{ kind: 'error', failure: { message: 'provider failed', code: 'PROVIDER' } }, 'PROVIDER', /provider failed/],
+    [{ kind: 'error', failure: { message: 'opaque', code: 'UNKNOWN' } }, 'UNKNOWN', /opaque/],
+    [{ kind: 'aborted', failure: { message: 'summarization aborted', code: 'ABORTED' } }, 'ABORTED', /aborted/],
     [{ kind: 'max-tokens' }, 'MAX_TOKENS', /token cap/],
   ] as Array<[(StreamChunk & { type: 'finish' })['reason'], string | undefined, RegExp]>) (
     'rejects terminal finish %#',
@@ -990,7 +1106,9 @@ describe('automatic listener and loader composition', () => {
     signal = SIGNAL,
     next: () => Promise<{ action: 'fail' | 'retry' }> = () => Promise.resolve({ action: 'fail' }),
   ): Promise<{ action: 'fail' | 'retry' }> {
-    return ctx.waterfall('agent/request-error', owner, 1, 1, error, retryAttempt, signal, next)
+    const failure: LlmFailure = { message: error.message, code: error.code ?? 'UNKNOWN' }
+    const priorFailures = Object.freeze(Array.from({ length: retryAttempt }, () => failure))
+    return ctx.waterfall('agent/request-error', owner, 1, 1, error, failure, priorFailures, signal, next)
   }
 
   function overflow(message = 'provider overflow'): Error & { code: string } {
@@ -1101,6 +1219,89 @@ describe('automatic listener and loader composition', () => {
     expect(session.surface.nodes).toContain(retainedSeq)
   })
 
+  it('authorizes overflow retry when pruning alone advances an indivisible surface', async () => {
+    const ctx = createContext(10_000)
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    const session = oversizedToolResult()
+
+    expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
+    expect(session.surface.replaceGeneration).toBe(1)
+    expect(session.events.some(event => event.type === 'compact/summary')).toBe(false)
+    expect(compact.calls).toHaveLength(0)
+  })
+
+  it('continues overflow recovery with summarization on the pruned surface', async () => {
+    const ctx = createContext(10_000)
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    const session = toolConversation()
+
+    expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
+    expect(session.events.some(event => event.type === 'compact/summary')).toBe(true)
+    expect(compact.calls).toHaveLength(1)
+    expect(compact.calls[0]!.text).toContain('tool result middle pruned')
+  })
+
+  it('retries from a durable prune when later overflow summarization throws', async () => {
+    const ctx = createContext(10_000)
+    const warnings: string[] = []
+    ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    compact.error = new Error('summary unavailable after prune')
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' })
+    expect(session.surface.replaceGeneration).toBe(1)
+    expect(session.events.filter(event => event.type === 'tool/result')).toHaveLength(2)
+    expect(session.events.findLast(event => event.type === 'compact/end')?.data)
+      .toMatchObject({ error: 'summary unavailable after prune' })
+    expect(warnings).toContainEqual(expect.stringContaining('retrying from the replacement surface'))
+  })
+
+  it('lets cancellation win when summary throws after a durable prune', async () => {
+    const ctx = createContext(10_000)
+    const controller = new AbortController()
+    void new ToolResultPruneService(ctx, {
+      thresholdChars: 100,
+      headChars: 20,
+      tailChars: 10,
+    })
+    const compact = new TestCompactService(ctx, {
+      thresholdRatio: 1,
+      retainTokens: 900,
+    })
+    compact.mutateDuringSummary = () => { controller.abort('cancelled during summary') }
+    compact.error = new Error('summary cancelled after prune')
+    const session = oversizedToolResult(3_000, true)
+
+    expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal))
+      .toEqual({ action: 'fail' })
+    expect(session.surface.replaceGeneration).toBe(1)
+  })
+
   it('preserves the newest whole tool-call/result pair during forced overflow compaction', async () => {
     const ctx = createContext()
     void new TestCompactService(ctx, {
@@ -1241,6 +1442,23 @@ describe('automatic listener and loader composition', () => {
     expect(compactSpy).not.toHaveBeenCalled()
   })
 
+  it('applies the routed model override to the overflow retry cap', async () => {
+    const ctx = createContext()
+    const compact = new TestCompactService(ctx, {
+      maxOverflowRetries: 2,
+      modelPolicies: [{
+        provider: MODEL,
+        model: MODEL,
+        maxOverflowRetries: 1,
+      }],
+    })
+    const compactSpy = vi.spyOn(compact, 'compactIfNeeded')
+
+    expect(await recover(ctx, agent(conversation(3), MODEL), overflow(), 1))
+      .toEqual({ action: 'fail' })
+    expect(compactSpy).not.toHaveBeenCalled()
+  })
+
   it('does not retry when cancellation lands during an awaited compaction', async () => {
     const ctx = createContext()
     const compact = new TestCompactService(ctx)

packages/compact/compact-basic/tests/compact-loop-repro.spec.ts

@@ -11,6 +11,7 @@ import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-test
 import * as Invariants from '@deepseek-ai/dsh-invariants'
 import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
+import * as LlmRetry from '@deepseek-ai/dsh-llm-retry'
 import { SessionId, type SurfaceEvent } from '@deepseek-ai/dsh-session'
 
 /**
@@ -65,7 +66,10 @@ class OverflowRecoveryAdapter extends LlmAdapter {
   readonly conversationRequests: GenerateOptions[] = []
   readonly summaryRequests: GenerateOptions[] = []
 
-  constructor(private readonly delivery: 'thrown' | 'in-band') {
+  constructor(
+    private readonly delivery: 'thrown' | 'in-band',
+    private readonly transientAfterOverflow = false,
+  ) {
     super()
   }
 
@@ -91,12 +95,17 @@ class OverflowRecoveryAdapter extends LlmAdapter {
         type: 'finish',
         reason: {
           kind: 'error',
-          message: 'request too large for model context',
-          code: CONTEXT_WINDOW_EXCEEDED_CODE,
+          failure: {
+            message: 'request too large for model context',
+            code: CONTEXT_WINDOW_EXCEEDED_CODE,
+          },
         },
       }
       return
     }
+    if (this.transientAfterOverflow && this.conversationRequests.length === 2) {
+      throw new LlmError('temporary provider outage', 'SERVER')
+    }
     yield { type: 'block-start', index: 0, blockType: 'text' }
     yield { type: 'block-end', index: 0, block: { type: 'text', text: 'recovered' } }
     yield { type: 'finish', reason: { kind: 'stop' } }
@@ -142,6 +151,29 @@ function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
   })
 }
 
+function seedOverflowHistory(agent: Agent): void {
+  for (let turn = 1; turn <= 2; turn += 1) {
+    const sentinel = turn === 1 ? 'OLD HISTORY SENTINEL' : 'RECENT HISTORY'
+    agent.session.append('turn/start', {
+      turn,
+      trigger: { kind: 'message', source: { kind: 'user' } },
+    })
+    agent.session.append('user/message', {
+      content: [{ type: 'text', text: `${sentinel} ${'old context '.repeat(200)}` }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    agent.session.append('step/start', { turn, step: 1 })
+    agent.session.append('assistant/message', {
+      provenance: { provider: 'mock', model: 'mock' },
+      turn,
+      step: 1,
+      content: [{ type: 'text', text: `historical response ${turn} ${'detail '.repeat(200)}` }],
+    }, { surfaceOp: 'append' })
+    agent.session.append('step/end', { turn, step: 1 })
+    agent.session.append('turn/end', { turn, reason: { kind: 'completed' } })
+  }
+}
+
 describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () => {
   it('uses the model actually routed by agent/request for post-step pressure', async () => {
     const { ctx } = await harness(8)
@@ -249,26 +281,7 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
           provider: 'unconfigured-agent-fallback',
           model: 'unconfigured-agent-fallback',
         })
-        for (let turn = 1; turn <= 2; turn += 1) {
-          const sentinel = turn === 1 ? 'OLD HISTORY SENTINEL' : 'RECENT HISTORY'
-          agent.session.append('turn/start', {
-            turn,
-            trigger: { kind: 'message', source: { kind: 'user' } },
-          })
-          agent.session.append('user/message', {
-            content: [{ type: 'text', text: `${sentinel} ${'old context '.repeat(200)}` }],
-            source: { kind: 'user' },
-          }, { surfaceOp: 'append' })
-          agent.session.append('step/start', { turn, step: 1 })
-          agent.session.append('assistant/message', {
-            provenance: { provider: 'mock', model: 'mock' },
-            turn,
-            step: 1,
-            content: [{ type: 'text', text: `historical response ${turn} ${'detail '.repeat(200)}` }],
-          }, { surfaceOp: 'append' })
-          agent.session.append('step/end', { turn, step: 1 })
-          agent.session.append('turn/end', { turn, reason: { kind: 'completed' } })
-        }
+        seedOverflowHistory(agent)
 
         agent.send([{ type: 'text', text: 'continue from history' }])
         await agent.whenIdle()
@@ -307,4 +320,47 @@ describe('context-overflow recovery across the real loop and compact-basic', ()
       }
     },
   )
+
+  it('keeps context-overflow and transient retry budgets independent in one sequence', async () => {
+    const ctx = new Context()
+    const adapter = new OverflowRecoveryAdapter('thrown', true)
+    await mountAgentLoopTestDependencies(ctx)
+    await ctx.plugin(Invariants)
+    await ctx.plugin(LlmRetry, {
+      maxTransientRetries: 1,
+      initialDelayMs: 1,
+      maxDelayMs: 1,
+      jitterRatio: 0,
+    })
+    await ctx.plugin(AgentLoop, { agents: [] })
+    await ctx.plugin(TokenMeterService)
+    ctx.llm.registerAdapter(['mock'], adapter)
+    await ctx.plugin(BasicCompactService, {
+      thresholdRatio: 1,
+      retainTokens: 100,
+      maxTokens: 64,
+      compactionRetries: 0,
+      maxOverflowRetries: 1,
+    })
+
+    try {
+      const agent = ctx.agentLoop.create(SessionId('alternating-recovery'), { provider: 'mock', model: 'mock' })
+      seedOverflowHistory(agent)
+      agent.send([{ type: 'text', text: 'continue from history' }])
+      await agent.whenIdle()
+
+      expect(adapter.conversationRequests).toHaveLength(3)
+      expect(adapter.summaryRequests).toHaveLength(1)
+      expect(agent.session.events.filter(event => event.type === 'llm/retry').map(event => event.data))
+        .toEqual([expect.objectContaining({ step: 2, retry: 1, failure: { message: 'temporary provider outage', code: 'SERVER' } })])
+      expect(agent.session.events.filter(event => event.type === 'step/start').slice(-3).map(event => event.data.step))
+        .toEqual([1, 2, 3])
+      expect(agent.session.events.at(-1)).toMatchObject({
+        type: 'turn/end',
+        data: { reason: { kind: 'completed' } },
+      })
+    } finally {
+      await ctx.fiber.dispose()
+    }
+  })
 })

packages/compact/compact-basic/tests/loader-composition.spec.ts

@@ -9,6 +9,7 @@ import Include from '@cordisjs/plugin-include'
 import LlmService from '@deepseek-ai/dsh-llm'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
 import BasicCompactService from '@deepseek-ai/dsh-compact-basic'
+import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
 
 let root: string | undefined
 let context: Context | undefined
@@ -32,6 +33,7 @@ async function loadYaml(lines: readonly string[]): Promise<Context> {
   const modules = new Map<string, unknown>([
     ['@deepseek-ai/dsh-llm', LlmService],
     ['@deepseek-ai/dsh-token-meter', TokenMeterService],
+    ['@deepseek-ai/dsh-compact-tool-result-prune', ToolResultPruneService],
     ['@deepseek-ai/dsh-compact-basic', BasicCompactService],
   ])
   context.loader.internal = {
@@ -50,10 +52,15 @@ async function loadYaml(lines: readonly string[]): Promise<Context> {
 }
 
 describe('real Loader composition', () => {
-  it('loads the flat token-meter and compact-basic YAML shape', async () => {
+  it('loads the shipped token-meter, pruning, and compact-basic YAML order', async () => {
     const loaded = await loadYaml([
       "- name: '@deepseek-ai/dsh-llm'",
       "- name: '@deepseek-ai/dsh-token-meter'",
+      "- name: '@deepseek-ai/dsh-compact-tool-result-prune'",
+      '  config:',
+      '    thresholdChars: 100',
+      '    headChars: 20',
+      '    tailChars: 10',
       "- name: '@deepseek-ai/dsh-compact-basic'",
       '  config:',
       '    thresholdRatio: 0.5',
@@ -65,6 +72,7 @@ describe('real Loader composition', () => {
       .filter(entry => entry.fiber === undefined && !entry.disabled)
       .map(entry => entry.options.name)
     expect(unloaded).toEqual([])
+    expect(loaded.get('toolResultPrune')).toBeInstanceOf(ToolResultPruneService)
     expect(loaded.get('compact')).toBeInstanceOf(BasicCompactService)
     expect((loaded.compact as BasicCompactService).config).toMatchObject({
       thresholdRatio: 0.5,