Merge remote-tracking branch 'origin/master' into feat/todo-multi-in-progress

examples/headless-agent/goal.cordis.snapshot.yml

@@ -1,12 +1,18 @@
-# Replay counterpart to goal.cordis.yml; only the live model is replaced.
+# Replay counterpart to goal.cordis.yml. It includes cordis.yml directly because
+# a config patch cannot target an entry behind a nested include, then restates
+# the goal overlay while replacing the live model with keyless replay.
 - id: base
   name: '@cordisjs/plugin-include'
   config:
-    path: ./goal.cordis.yml
+    path: ./cordis.yml
     patches:
       - id: llm-deepseek
         name: '@deepseek-ai/dsh-llm-deepseek'
         disabled: true
       - insert:
+          - id: goal
+            name: '@deepseek-ai/dsh-goal'
+          - id: tool-goal
+            name: '@deepseek-ai/dsh-tool-goal'
           - id: llm-replay
             name: '@deepseek-ai/dsh-llm-replay'

examples/headless-agent/tests/code-mode.e2e.ts

@@ -314,12 +314,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
     ctx = await codeModeHarness(workdir)
     const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
 
-    agent.followup([{
+    agent.followup({ content: [{
       type: 'text',
       text: 'Using one run_code program: run `echo alpha-7` with the bash tool, run `echo beta-9` with the bash tool, '
         + 'then write both outputs joined by a plus sign into combined.txt (bash heredoc or redirect), '
         + 'and return only the joined string.',
-    }])
+    }], source: { kind: 'user' } })
     await waitForIdle(ctx, agent)
     const events: SessionEvent[] = [...agent.session.events]
 
@@ -366,21 +366,17 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
       agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
     })
 
-    handle.agent.followup([{
+    handle.agent.followup({ content: [{
       type: 'text',
       text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
-    }])
+    }], source: { kind: 'user' } })
     await waitForIdle(ctx, handle.agent)
 
     const events: SessionEvent[] = [...handle.agent.session.events]
     const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
     const outerResult = events.find(event => event.type === 'tool/result')
     const workspaceContext = events.find(event => event.type === 'user/message'
-      && event.data.source.kind === 'plugin'
-      && typeof event.data.meta === 'object'
-      && event.data.meta !== null
-      && !Array.isArray(event.data.meta)
-      && event.data.meta.kind === 'workspace-instructions')
+      && event.data.source.kind === 'workspace-instructions')
     expect(dispatch).toBeDefined()
     expect(outerResult).toBeDefined()
     expect(workspaceContext).toBeDefined()

examples/headless-agent/tests/coding-task.e2e.ts

@@ -56,12 +56,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test
     ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
     const agent = ctx.agentLoop.create(SessionId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
 
-    agent.followup([{
+    agent.followup({ content: [{
       type: 'text',
       text: 'In the current directory, `node add.test.js` fails because add.js has a bug. '
         + 'Fix add.js so the test passes, run `node add.test.js` to verify, and report the result. '
         + 'Do not modify add.test.js.',
-    }])
+    }], source: { kind: 'user' } })
     await waitForIdle(ctx, agent)
 
     // The agent claims success…

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

@@ -46,12 +46,12 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa
     })
     const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
 
-    agent.followup([{
+    agent.followup({ content: [{
       type: 'text',
       text: 'Read file1.txt, file2.txt, file3.txt, and file4.txt one at a '
         + 'time using cat (a separate bash command for each). After reading all four, tell me how '
         + 'many files you read and the number mentioned in file1.txt.',
-    }])
+    }], source: { kind: 'user' } })
     await waitForIdle(ctx, agent)
 
     const events = [...agent.session.events]

examples/headless-agent/tests/fixtures/cli-mock-llm.ts

@@ -59,7 +59,7 @@ export const inject = ['llm']
 /** Register the keyless `cli-mock` adapter. */
 export function apply(ctx: Context): void {
   ctx.llm.registerAdapter(['cli-mock'], new CliMockAdapter())
-  ctx.on('agent/request', async (_agent, _turn, step, _config, _signal, next) => {
+  ctx.on('agent/request', async (_agent, _turn, step, _signal, next) => {
     const config = await next()
     return step === 2 ? { ...config, reasoningEffort: OFF } : config
   })

examples/headless-agent/tests/fixtures/goal-domain/seed-goal.ts

@@ -7,7 +7,7 @@ export const name = 'seed-goal'
 export const inject = ['goals']
 
 export function apply(ctx: Context): void {
-  ctx.on('agent/pre-step', (agent) => {
+  ctx.on('agent/step', (agent) => {
     if (ctx.goals.get(agent) !== undefined) return
     ctx.goals.create(agent, {
       objective: 'Prove the composed goal survives in the session log',

examples/headless-agent/tests/full-loop.e2e.ts

@@ -30,7 +30,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas
     ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT })
     const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
 
-    agent.followup([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
+    agent.followup({ content: [{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }], source: { kind: 'user' } })
     await waitForIdle(ctx, agent)
 
     const events = [...agent.session.events]

examples/headless-agent/tests/headless.snapshot.ts

@@ -272,14 +272,16 @@ describe('headless stream-json snapshots', () => {
         const goalChanges = records.filter((record) => {
           if (record.type !== 'user/message') return false
           const data = record.data as JsonObject | undefined
-          const meta = data?.meta as JsonObject | undefined
-          return meta?.kind === 'goal/change'
+          const source = data?.source as JsonObject | undefined
+          const change = source?.change as JsonObject | undefined
+          return source?.kind === 'goal' && change?.kind === 'goal/change'
         })
         expect(goalChanges).toHaveLength(1)
         const data = goalChanges[0]?.data as JsonObject | undefined
-        const meta = data?.meta as JsonObject | undefined
-        const goal = meta?.goal as JsonObject | undefined
-        expect(meta?.operation).toBe('create')
+        const source = data?.source as JsonObject | undefined
+        const change = source?.change as JsonObject | undefined
+        const goal = change?.goal as JsonObject | undefined
+        expect(change?.operation).toBe('create')
         expect(goal).toMatchObject({
           objective: 'Finish the headless goal-tool snapshot proof',
           phase: 'active',

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

@@ -41,7 +41,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
       sessionId: SESSION_ID,
       agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
     })).agent
-    first.followup([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
+    first.followup({ content: [{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }], source: { kind: 'user' } })
     await waitForIdle(ctx, first)
     await ctx.fiber.dispose()
     ctx = undefined
@@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses
     // The prior user turn is in the rehydrated log before the model is asked.
     expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET)
 
-    resumed.followup([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
+    resumed.followup({ content: [{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }], source: { kind: 'user' } })
     await waitForIdle(ctx, resumed)
 
     // The model recalls it — only possible from the resumed history.

examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl

@@ -21,7 +21,7 @@
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":20,"outputTokens":8}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","name":"create_goal","arguments":"{\"objective\":\"Finish the headless goal-tool snapshot proof\",\"max_goal_rounds\":7}"}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"call_goal_create","content":[{"type":"text","text":"{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"roundsStarted\":0,\"maxGoalRounds\":7},\"activation\":\"armed\"}"}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"}}
-{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":23,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0},"meta":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}},"surfaceOp":"append"}}
+{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":23,"time":0,"data":{"content":[{"type":"text","text":"<goal_state>{\"goal\":{\"id\":\"goal-{{sessionId}}\",\"revision\":1,\"objective\":\"Finish the headless goal-tool snapshot proof\",\"phase\":\"active\",\"maxGoalRounds\":7},\"roundsStarted\":0,\"createdAt\":0,\"updatedAt\":0}</goal_state>"}],"source":{"kind":"goal","goalId":"goal-{{sessionId}}","revision":1,"round":0,"change":{"kind":"goal/change","version":1,"operation":"create","goal":{"id":"goal-{{sessionId}}","revision":1,"objective":"Finish the headless goal-tool snapshot proof","phase":"active","maxGoalRounds":7},"roundsStarted":0,"createdAt":0,"updatedAt":0}}},"surfaceOp":"append"}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":24,"time":0,"data":{"turn":1,"step":2}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":25,"time":0,"data":{"turn":1,"step":3}}}
 {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}}

examples/headless-agent/tests/todo-write.e2e.ts

@@ -28,11 +28,11 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
     ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
     const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
 
-    agent.followup([{ type: 'text', text:
+    agent.followup({ content: [{ type: 'text', text:
       'Use the todo_write tool to record a plan of exactly three steps for work '
       + 'running in parallel: "inspect the failing test" (in_progress), '
       + '"watch the background build" (in_progress), then "apply the fix" (pending). '
-      + 'Send all three in one todo_write call, then reply with the single word DONE.' }])
+      + 'Send all three in one todo_write call, then reply with the single word DONE.' }], source: { kind: 'user' } })
     await waitForIdle(ctx, agent)
 
     const events = [...agent.session.events]