Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/feat/send-unify' into xtr/agent-loop-message-machine

Browse Source 
# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.md
#	.agents/notes/implemented/architecture/2026-07-22-unified-send-and-coalesced-user-messages.zh.md
#	docs/architecture.i18n.yaml
#	docs/architecture.md
#	docs/architecture.zh.md
#	docs/core-data-structures/core.md
#	packages/context/session-reference/README.md
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent-loop/src/inbox.ts
#	packages/core/agent-loop/tests/agent.spec.ts
#	packages/core/agent-loop/tests/cancel.spec.ts
#	packages/core/agent-loop/tests/contract-regressions.spec.ts
#	packages/core/agent-loop/tests/coverage-edges.spec.ts
#	packages/core/agent-loop/tests/interception.spec.ts
#	packages/core/agent-loop/tests/loop.spec.ts
#	packages/core/agent/README.md
#	packages/core/agent/src/types.ts
#	packages/core/agent/tests/agent.spec.ts
#	packages/ui/acp/src/index.ts
#	packages/ui/tui/src/index.ts
#	packages/ui/tui/tests/harness.ts
This commit is contained in:
_Kerman
2026-07-24 16:25:53 +08:00
parent e23960b8ad 4a0d8bb0d5
commit 66645638fb
74 changed files with 310 additions and 303 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/cordis-agent/tests/cordis-tools.e2e.ts
View File

@@ -42,7 +42,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
const log = vi.spyOn(console, 'log').mockImplementation(() => {})
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
agent.followup([{
type: 'text',
text: 'Use cordis_mount to mount a plugin that listens to the \'agent/status\' '
+ 'cordis event and logs every change with console.log. Reply "mounted" once done.',
@@ -58,7 +58,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
})
expect(resultText(mid)).toContain('dyn-')
agent.send([{ type: 'text', text: 'Now unmount the plugin you just mounted.' }])
agent.followup([{ type: 'text', text: 'Now unmount the plugin you just mounted.' }])
await waitForIdle(ctx, agent)
const after = await ctx.tools.execute({
@@ -72,7 +72,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
ctx = await cordisHarness()
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
agent.followup([{
type: 'text',
text: 'Give yourself a new tool: use cordis_mount to mount a plugin with '
+ 'inject ["tools"] that calls harness.registerTool(ctx, harness.defineTool({...})) '
@@ -119,7 +119,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
ctx = await cordisHarness()
const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
agent.send([{
agent.followup([{
type: 'text',
text: 'Mount TWO separate plugins with cordis_mount. First a provider: apply calls '
+ 'ctx.provide(\'shouter\', { shout: (s) => s.toUpperCase() }). Second a consumer with '
@@ -144,7 +144,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif
.flatMap(event => event.data.content.filter(block => block.type === 'text').map(block => block.text))
expect(shoutResults.some(text => text.includes('QUIET'))).toBe(true)
agent.send([{ type: 'text', text: 'Now unmount ONLY the provider plugin (the one that provided shouter).' }])
agent.followup([{ type: 'text', text: 'Now unmount ONLY the provider plugin (the one that provided shouter).' }])
await waitForIdle(ctx, agent)
// The consumer must have been parked by cordis itself: service gone,

4
examples/headless-agent/tests/code-mode.e2e.ts
View File

@@ -311,7 +311,7 @@ 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.send([{
agent.followup([{
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), '
@@ -363,7 +363,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
})
handle.agent.send([{
handle.agent.followup([{
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?',
}])

2
examples/headless-agent/tests/coding-task.e2e.ts
View File

@@ -56,7 +56,7 @@ 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.send([{
agent.followup([{
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. '

2
examples/headless-agent/tests/compaction.e2e.ts
View File

@@ -46,7 +46,7 @@ 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.send([{
agent.followup([{
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 '

2
examples/headless-agent/tests/full-loop.e2e.ts
View File

@@ -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.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
agent.followup([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }])
await waitForIdle(ctx, agent)
const events = [...agent.session.events]

4
examples/headless-agent/tests/resume.e2e.ts
View File

@@ -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.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
first.followup([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }])
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.send([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
resumed.followup([{ type: 'text', text: 'What was the code I asked you to remember? Reply with just the code.' }])
await waitForIdle(ctx, resumed)
// The model recalls it — only possible from the resumed history.

2
examples/headless-agent/tests/todo-write.e2e.ts
View File

@@ -28,7 +28,7 @@ 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.send([{ type: 'text', text:
agent.followup([{ type: 'text', text:
'Use the todo_write tool to record a plan of exactly two steps: first '
+ '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
+ 'Send both in one todo_write call, then reply with the single word DONE.' }])