Merge current master into debug-pangwenjie

# Conflicts: # docs/cordis-catalog/events.md # docs/core-data-structures/core.md # docs/core-data-structures/tools.md # docs/event-producer-consumer.md # docs/rfc/implemented/feature/2026-06-30-interception-seams.md # docs/tool-execution-pipeline.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/loop.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent/README.md # packages/core/tools/src/index.ts # scripts/gen-doc-graphs.ts
2026-08-15 21:04:50 +00:00 · 2026-07-18 13:39:12 +08:00
parent 4bf36e4dd1 f07ae453cc
commit aacedf2700
701 changed files with 38518 additions and 8779 deletions
--- a/packages/core/agent-loop/src/loop.ts
+++ b/packages/core/agent-loop/src/loop.ts
@@ -6,7 +6,8 @@
 */

 import type { Context } from 'cordis'
-import type { FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm'
+import type { ContentBlock, FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm'
+import { isDeepStrictEqual } from 'node:util'
 import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm'
 import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent'
 import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent'
@@ -236,10 +237,15 @@ async function runTurn(
      // `allow.content` REPLACES the prompt bytes (a rewrite); absent keeps them.
      const content = decision.content ?? message.content
      session.append('user/message', { content, source: message.source }, { surfaceOp: 'append' })
-      // `allow.additionalContext` is a SEPARATE context/message the next request
-      // also sees. The turn is open, so inject() appends it into THIS turn.
-      if (decision.additionalContext) {
-        agent.inject(decision.additionalContext.content, { source: decision.additionalContext.source })
+      // Every `allow.additionalContexts` entry is a separate context/message the
+      // next request also sees. The turn is open, so inject() appends each one
+      // into THIS turn without flattening provenance, framing, or metadata.
+      for (const context of decision.additionalContexts ?? []) {
+        agent.inject(context.content, {
+          source: context.source,
+          ...context.envelope !== undefined ? { envelope: context.envelope } : {},
+          ...context.meta !== undefined ? { meta: context.meta } : {},
+        })
      }
    }

@@ -480,12 +486,12 @@ async function runStep(
  const seedConfig: LlmCallConfig = deepFreeze(structuredClone(transmission.loggedHeader
    // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- loggedHeader ⟹ a snapshot is in the log
    ? session.requestHeader()!.config
-    : { model: options.model ?? '' }))
+    : { provider: options.provider ?? '', model: options.model ?? '' }))

  // Listener replacements are recorded in the request header before dispatch.
  const config = await events.waterfall('agent/request', turn, step, seedConfig, () => Promise.resolve(seedConfig))
-  if (!config.model) {
-    throw new Error(`agent "${agent.id}" has no model: set AgentOptions.model or supply one via the agent/request waterfall`)
+  if (!config.provider || !config.model) {
+    throw new Error(`agent "${agent.id}" has no provider/model: set AgentOptions.provider and AgentOptions.model or supply both via the agent/request waterfall`)
  }

  // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- runTurn composes the prefix before every runStep call
@@ -502,6 +508,7 @@ async function runStep(

  // Freeze the logged header plus boundary snapshot; the prefix precedes derived history.
  const request: GenerateOptions = deepFreeze({
+    provider: header.config.provider,
    model: header.config.model,
    messages: [...header.messagePrefix ?? [], ...boundaryMessages],
    ...header.system !== undefined ? { system: header.system } : {},
@@ -529,32 +536,28 @@ async function runStep(
  if (stepError) throw stepError

  if (assembler.finish.kind === 'max-tokens') {
-    let message: Message = withoutToolCalls(assembler.message())
-    message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)))
+    const assembled = assembler.message()
+    const assembledContent = structuredClone(assembled.content)
+    let message: Message = withoutToolCalls(assembled)
+    message = withoutToolCalls(await processStepResult(
+      events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs,
+    ))
    // Preserve usage even when max-token truncation produced no content.
-    if (message.content.length > 0 || assembler.usage) {
-      // The finish chunk guarantees non-empty provenance here.
-      session.append(
-        'assistant/message',
-        { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) },
-        { surfaceOp: 'append', sourceEventSeqs: chunkSeqs },
-      )
-    }
+    recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs)
    return { hadToolCalls: false, finish: assembler.finish }
  }

  // Record the post-waterfall message that tool dispatch uses.
-  let message: Message = assembler.message()
-  message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))
+  const assembled = assembler.message()
+  const assembledContent = structuredClone(assembled.content)
+  let message: Message = assembled
+  message = await processStepResult(
+    events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs,
+  )

-  // Empty messages exist only to carry usage; omit empty provenance.
-  if (message.content.length > 0 || assembler.usage) {
-    session.append(
-      'assistant/message',
-      { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) },
-      { surfaceOp: 'append', ...(chunkSeqs.length > 0 ? { sourceEventSeqs: chunkSeqs } : {}) },
-    )
-  }
+  // Every successful call records its completion anchor, including explicit
+  // empty chunk provenance for a contentless, usage-less provider response.
+  recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs)

  // Tool execution stays sequential; recheck abort around each normalized result.
  const toolCalls = message.content.filter(block => block.type === 'tool-call')
@@ -590,20 +593,89 @@ async function runStep(
        // Persist tool-owned presentation data for replay.
        ...result.meta !== undefined ? { meta: result.meta } : {},
      }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] })
-      // Accept into the batch FIFO immediately; it remains deferred until every
-      // result settles and survives abort, cancellation, or disposal afterward.
-      if (result.additionalContext) acceptContext(result.additionalContext)
+      // Accept into the batch FIFO immediately; entries remain deferred until
+      // every recorded result settles and survive abort or disposal afterward.
+      for (const context of result.additionalContexts ?? []) acceptContext(context)
      // The signal may flip while the tool is awaited.
      /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */
      // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
      if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted'))
      /* v8 ignore stop */
    }
-
    return { hadToolCalls: true, finish: assembler.finish }
  })
 }

+/** Preserve successful-call accounting without retaining output that result processing rejected. */
+async function processStepResult(
+  events: AgentEventDispatch,
+  session: Session,
+  turn: number,
+  step: number,
+  config: LlmCallConfig,
+  assembledContent: ContentBlock[],
+  message: Message,
+  assembler: BlockAssembler,
+  chunkSeqs: number[],
+): Promise<Message> {
+  try {
+    return await events.waterfall(
+      'agent/step-result', turn, step, message, () => Promise.resolve(message),
+    )
+  } catch (error: unknown) {
+    recordAssistantMessage(
+      session,
+      turn,
+      step,
+      config,
+      assembledContent,
+      { ...message, content: [] },
+      assembler,
+      chunkSeqs,
+      false,
+    )
+    throw error
+  }
+}
+
+/** Record one content-or-usage assistant message with replay-safe provenance. */
+function recordAssistantMessage(
+  session: Session,
+  turn: number,
+  step: number,
+  config: LlmCallConfig,
+  assembledContent: ContentBlock[],
+  message: Message,
+  assembler: BlockAssembler,
+  chunkSeqs: number[],
+  preserveReplayState = true,
+): void {
+  session.append(
+    'assistant/message',
+    {
+      turn,
+      step,
+      content: message.content,
+      provenance: assistantProvenance(
+        config,
+        assembler.replayState,
+        preserveReplayState && isDeepStrictEqual(message.content, assembledContent),
+      ),
+      ...assembler.usage === undefined ? {} : { usage: assembler.usage },
+    },
+    { surfaceOp: 'append', sourceEventSeqs: chunkSeqs },
+  )
+}
+
+/** Build durable assistant provenance, dropping replay state after any content rewrite. */
+function assistantProvenance(config: LlmCallConfig, replayState: unknown, contentUnchanged: boolean): NonNullable<Message['provenance']> {
+  return {
+    provider: config.provider,
+    model: config.model,
+    ...contentUnchanged && replayState !== undefined ? { replayState } : {},
+  }
+}
+
 function withoutToolCalls(message: Message): Message {
  return { ...message, content: message.content.filter(block => block.type !== 'tool-call') }
 }