Merge branch 'codex/canonical-tool-output' into codex/code-mode-typed-results

# Conflicts:
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	packages/code-runtime/code-runtime-worker/package.json
#	packages/spill/spill-policy/package.json
#	pnpm-lock.yaml

examples/headless-agent/composition.md

@@ -21,6 +21,8 @@ flowchart LR
   bundle_agent_core --> spine_sessions["ctx.sessions"]
   bundle_agent_core --> spine_tools["ctx.tools + tool-bash"]
   bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"]
+  plugin_headless_token_meter["token-meter<br/>@deepseek-ai/dsh-token-meter"]
+  cfg --> plugin_headless_token_meter
   plugin_headless_compact_basic["compact-basic<br/>@deepseek-ai/dsh-compact-basic"]
   cfg --> plugin_headless_compact_basic
   plugin_headless_subagent["subagent<br/>@deepseek-ai/dsh-subagent"]
@@ -54,6 +56,7 @@ flowchart LR
 | `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
 | `bash` | `@deepseek-ai/dsh-bash-local` |
 | `cli-agent` | `@deepseek-ai/dsh-cli-demo` |
+| `token-meter` | `@deepseek-ai/dsh-token-meter` |
 | `compact-basic` | `@deepseek-ai/dsh-compact-basic` |
 | `subagent` | `@deepseek-ai/dsh-subagent` |
 | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` |

examples/headless-agent/cordis.yml

@@ -11,7 +11,9 @@
     baseURL: !!js process.env.DEEPSEEK_BASE_URL
     models:
       - id: deepseek-v4-pro
+        contextWindow: 128000
       - id: deepseek-v4-flash
+        contextWindow: 128000
 
 - id: bash
   name: '@deepseek-ai/dsh-bash-local'
@@ -35,13 +37,14 @@
       factual.
 
 # Summarize an older range when derived history approaches the context window.
+- id: token-meter
+  name: '@deepseek-ai/dsh-token-meter'
+
 - id: compact-basic
   name: '@deepseek-ai/dsh-compact-basic'
   config:
-    contextWindow: 128000
     thresholdRatio: 0.8
-    retainTokens: 20480
-    summarizationModel: ''
+    retainRatio: 0.16
     maxTokens: 8192
     compactionRetries: 1
 

examples/headless-agent/tests/compaction.e2e.ts

@@ -33,9 +33,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
     // Reasoning tokens require a larger generation cap than the retained checkpoint.
     ctx = await codingHarness(workdir, {
       persona: SYSTEM_PROMPT,
-      tokenMeter: {
-        contextWindow: 2000,
-      },
+      modelContextWindow: 2000,
       compact: {
         thresholdRatio: 0.5,
         retainTokens: 400,

examples/headless-agent/tests/harness.ts

@@ -8,7 +8,6 @@ import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
 import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
 import TokenMeterService from '@deepseek-ai/dsh-token-meter'
-import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter'
 import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune'
 import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
 import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
@@ -46,8 +45,8 @@ export interface CodingHarnessOptions {
    * compaction plugin (the default suites run without it).
    */
   compact?: BasicCompactConfig
-  /** Optional token-meter capacity loaded before compact-basic. */
-  tokenMeter?: TokenMeterConfig
+  /** Test-only context capacity advertised for `deepseek-v4-flash`. */
+  modelContextWindow?: number
 }
 
 export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise<Context> {
@@ -56,14 +55,15 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
     systemPrompt: { persona: options.persona ?? '' },
   })
   await ctx.plugin(AgentLoop, { agents: [] })
-  await ctx.plugin(LlmDeepSeek)
+  await ctx.plugin(LlmDeepSeek, options.modelContextWindow === undefined ? {} : {
+    models: [{ id: 'deepseek-v4-flash', contextWindow: options.modelContextWindow }],
+  })
   await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
   await ctx.plugin(ToolBash)
   await ctx.plugin(ToolTodo)
-  // Compaction is opt-in: only the compaction e2e loads the reusable meter and
-  // backend, with a lower context window so a short real session crosses the threshold.
+  // Compaction is opt-in: only the compaction e2e loads the reusable meter and backend.
   if (options.compact !== undefined) {
-    await ctx.plugin(TokenMeterService, options.tokenMeter)
+    await ctx.plugin(TokenMeterService)
     await ctx.plugin(ToolResultPruneService)
     await ctx.plugin(BasicCompactService, options.compact)
   }