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

Merge latest origin/master into parallel-tool-call

Browse Source 
# Conflicts:
#	docs/architecture.md
#	examples/acp-agent/tests/snapshots/bash-spill/session.jsonl
#	examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
#	examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
#	packages/core/agent-loop/src/loop.ts
This commit is contained in:
Tianyi Cui
2026-07-18 15:09:39 +08:00
parent 21ec178841 7a29676c01
commit 50f0291b93
198 changed files with 6086 additions and 4036 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/AGENTS.md
View File

@@ -1,6 +1,6 @@
# AGENTS.md — Examples
Runnable harness compositions. **Examples are NOT workspaces**: their private `package.json` files are dependency-free stubs, and the cordis Loader boots each `cordis.yml` unbuilt through `tsx` plus the root tsconfig paths.
Runnable harness compositions. `examples/` is one workspace member and the module-resolution root for runnable and test Cordis configs; it is not a build target. [package.json](package.json) declares the packages loaded by those configs, while each leaf's private `package.json` remains metadata only.
Extract reusable logic into `packages/`, where per-file coverage and README gates apply. Examples keep only `cordis.yml` wiring, demo artifacts, and e2e/snapshot scenarios; app package bins own boot glue.
@@ -13,7 +13,7 @@ Each example has both:
Mock-only examples require only the keyless tier; state that exception in the test.
Keyless stdio smokes use `@deepseek-ai/dsh-loader-smoke` for isolation, root-tsconfig loading, subprocess lifecycle, diagnostics, EOF, and cleanup; tests supply paths, environment, input, and assertions.
Keyless stdio smokes use `@deepseek-ai/dsh-loader-smoke`; tests supply paths, environment, input, and assertions. Every checked-in test Cordis config lives under its corresponding `examples/<agent>/` leaf. Map a package-owned config to `examples/<agent>/tests/fixtures/<group>/<package>/cordis.yml`, keep its driver and assertions package-local, and declare every package it names in both root `tsconfig.json` references and `examples/package.json`.
Do not inventory example tests here; the `tests/` trees and root scripts are authoritative.

44
examples/acp-agent/tests/acp.e2e.ts
View File

@@ -15,6 +15,7 @@ import {
type RequestPermissionResponse,
type SessionNotification,
} from '@agentclientprotocol/sdk'
import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
/**
* Boots examples/acp-agent as an ACP subprocess. The key-gated prompt leg
@@ -25,8 +26,6 @@ import {
// The child runs from a temp cwd, so its bin and config path are absolute.
const binScript = fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url))
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
// Resolve tsx absolutely because the subprocess runs outside the repo.
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// The root tsconfig supplies unbuilt workspace `paths`; making it explicit
// avoids accidental resolution through stale built output.
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
@@ -38,24 +37,21 @@ interface Spawned {
stderr: string[]
}
// TODO(acp-test-harness): this subprocess/client boot glue is duplicated with
// hooks.e2e.ts and partly with dsh-acp-snapshot's harness. Migrate both e2e
// files onto that launcher before the TSX/env/permission-stub details drift.
function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawned {
const child = spawn(
process.execPath,
['--import', tsxLoader, binScript, '--config', configPath],
{
cwd,
env: {
...env,
TSX_TSCONFIG_PATH: repoTsconfig,
DSH_PERMISSION_MODE: 'danger-full-access',
DSH_HOME: join(cwd, '.dsh'),
DSH_AGENTS_HOME: join(cwd, '.agents'),
},
stdio: ['pipe', 'pipe', 'pipe'],
const launch = resolveExampleLaunch({
srcBin: binScript,
configArgs: ['--config', configPath],
tsconfigPath: repoTsconfig,
env: {
DSH_PERMISSION_MODE: 'danger-full-access',
DSH_HOME: join(cwd, '.dsh'),
DSH_AGENTS_HOME: join(cwd, '.agents'),
},
})
const child = spawn(
launch.command,
launch.args,
{ cwd, env: { ...env, ...launch.env }, stdio: ['pipe', 'pipe', 'pipe'] },
)
const stderr: string[] = []
child.stderr.setEncoding('utf8')
@@ -138,16 +134,20 @@ describe('acp-agent over real stdio (no key required)', () => {
workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-'))
// Collect raw stdout bytes directly (bypass the SDK framing) to inspect.
// A dummy key boots the adapter; this purity test sends no prompt and makes no model call.
const child = spawn(process.execPath, ['--import', tsxLoader, binScript, '--config', configPath], {
cwd: workdir,
const launch = resolveExampleLaunch({
srcBin: binScript,
configArgs: ['--config', configPath],
tsconfigPath: repoTsconfig,
env: {
...process.env,
DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot',
TSX_TSCONFIG_PATH: repoTsconfig,
DSH_PERMISSION_MODE: 'danger-full-access',
DSH_HOME: join(workdir, '.dsh'),
DSH_AGENTS_HOME: join(workdir, '.agents'),
},
})
const child = spawn(launch.command, launch.args, {
cwd: workdir,
env: { ...process.env, ...launch.env },
stdio: ['pipe', 'pipe', 'pipe'],
})
const out: string[] = []

6
examples/acp-agent/tests/acp.snapshot.ts
View File

@@ -74,13 +74,13 @@ const SCENARIOS: Scenario[] = [
{ name: 'multi-turn', hasModelTurn: true, recorded: true },
// ACP exposes the adapter catalog as a session-scoped model select. This
// scenario pins the default flash request, the switch response, and the
// resulting request-header delta to pro.
// resulting changed request-header snapshot for pro.
{
name: 'model-switching',
hasModelTurn: true,
recorded: true,
pinsHeader: true,
expectedHeaderDeltas: 1,
expectedHeaderChanges: 1,
headerClass: 'model-switching',
},
{ name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true },
@@ -168,7 +168,7 @@ const SCENARIOS: Scenario[] = [
// Real-kernel confinement remains in escalation.e2e.ts and the sandbox
// packages' e2e suites.
{ name: 'config-options', hasModelTurn: false, recorded: false, headerClass: 'sandbox' },
{ name: 'permission-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1, headerClass: 'sandbox' },
{ name: 'permission-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'sandbox' },
{ name: 'escalation-approved', hasModelTurn: true, recorded: true, headerClass: 'sandbox' },
{ name: 'escalation-rejected', hasModelTurn: true, recorded: true, headerClass: 'sandbox' },
]

26
examples/acp-agent/tests/escalation.e2e.ts
View File

@@ -15,6 +15,7 @@ import {
type RequestPermissionResponse,
type SessionNotification,
} from '@agentclientprotocol/sdk'
import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
/**
* Exercises the default ACP composition through the real bin and Loader. The
@@ -28,9 +29,8 @@ import {
const binScript = fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url))
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
// The subprocess runs from a temp cwd outside the repo; point tsx at the repo
// tsconfig so the unbuilt `paths` map resolves (see examples/AGENTS.md).
// tsconfig so the unbuilt `paths` map resolves in src mode (see examples/AGENTS.md).
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
// Without a usable bwrap/Seatbelt runner, the strict attempt fails closed with
@@ -55,17 +55,19 @@ interface Spawned {
/** Boot the example as an ACP subprocess; the scripted client answers every permission prompt with `answer`. */
function spawnAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned {
const launch = resolveExampleLaunch({
srcBin: binScript,
configArgs: ['--config', configPath],
tsconfigPath: repoTsconfig,
// A dummy key lets the deepseek adapter boot keyless (presence-checked at
// apply, used only on a real model call); the with-key tests carry the
// real key, so the fallback is inert there.
env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY || 'sk-dummy-for-boot' },
})
const child = spawn(
process.execPath,
['--import', tsxLoader, binScript, '--config', configPath],
{
cwd,
// A dummy key lets the deepseek adapter boot keyless (presence-checked at
// apply, used only on a real model call); the with-key tests carry the
// real key, so the fallback is inert there.
env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY || 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig },
stdio: ['pipe', 'pipe', 'pipe'],
},
launch.command,
launch.args,
{ cwd, env: { ...process.env, ...launch.env }, stdio: ['pipe', 'pipe', 'pipe'] },
)
const stderr: string[] = []
child.stderr.setEncoding('utf8')

14
examples/acp-agent/tests/hooks.e2e.ts
View File

@@ -15,6 +15,7 @@ import {
type RequestPermissionResponse,
type SessionNotification,
} from '@agentclientprotocol/sdk'
import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
/**
* With-key e2e for the Claude hook bridge. The process-level `./hooks.json` is
@@ -25,7 +26,6 @@ import {
const binScript = fileURLToPath(new URL('../../../packages/examples/acp-demo/src/bin.ts', import.meta.url))
const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url))
const tsxLoader = fileURLToPath(import.meta.resolve('tsx'))
const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
interface Spawned {
@@ -36,10 +36,16 @@ interface Spawned {
}
function spawnAcpAgent(cwd: string): Spawned {
const launch = resolveExampleLaunch({
srcBin: binScript,
configArgs: ['--config', configPath],
tsconfigPath: repoTsconfig,
env: { DSH_PERMISSION_MODE: 'danger-full-access' },
})
const child = spawn(
process.execPath,
['--import', tsxLoader, binScript, '--config', configPath],
{ cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig, DSH_PERMISSION_MODE: 'danger-full-access' }, stdio: ['pipe', 'pipe', 'pipe'] },
launch.command,
launch.args,
{ cwd, env: { ...process.env, ...launch.env }, stdio: ['pipe', 'pipe', 'pipe'] },
)
const stderr: string[] = []
child.stderr.setEncoding('utf8')

2
examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json
View File

@@ -342,5 +342,5 @@
}
}
],
"deltas": []
"changes": []
}

2
examples/acp-agent/tests/snapshots/bash-spill/session.jsonl
View File

@@ -10,7 +10,7 @@
{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_spill","name":"bash","arguments":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}
{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","name":"bash","arguments":"{\"command\":\"node -e \\\"process.stdout.write('SPILL_START-' + 'x'.repeat(2000) + '-SPILL_END')\\\"\",\"description\":\"Print large deterministic output\"}"}}
{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","content":[{"type":"text","text":"SPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: /tmp/dsh-acp-snapshot-spill/session-e2a13560e58a/f7e08c805fe9-bash.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"call_spill","content":[{"type":"text","text":"SPILL_START-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-SPILL_END\n\n(Omitted 1417 bytes. Full formatted result stored at: /tmp/dsh-acp-snapshot-spill/session-ad78080217cd/dccd97e3c558-bash.txt. Use read with offset/limit, or grep this path to search within it.)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}
{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}

2
examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.golden.json
View File

@@ -289,5 +289,5 @@
}
}
],
"deltas": []
"changes": []
}

2
examples/acp-agent/tests/snapshots/code-mode-turn/tool-schemas.golden.json
View File

@@ -17,5 +17,5 @@
}
}
],
"deltas": []
"changes": []
}

2
examples/acp-agent/tests/snapshots/code-mode-workspace-context/tool-schemas.golden.json
View File

@@ -17,5 +17,5 @@
}
}
],
"deltas": []
"changes": []
}

4
examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl
View File

@@ -131,8 +131,8 @@
{"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"}
{"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"23c17684-b99e-4c10-9c54-ff96ab5d7b89","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"23c17684-b99e-4c10-9c54-ff96ab5d7b89","outcome":"allowed-once"}}
{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"19974166-a6ad-4f46-bef8-ce7d6bda3214","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"19974166-a6ad-4f46-bef8-ce7d6bda3214","outcome":"allowed-once"}}
{"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"}
{"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}}

4
examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl
View File

@@ -155,8 +155,8 @@
{"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"}
{"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}}
{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"ebd9ad34-7da0-4417-afa3-a011affc96fd","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"ebd9ad34-7da0-4417-afa3-a011affc96fd","outcome":"rejected"}}
{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"564d6e1b-4330-42bd-a646-461e7a6c2d1a","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}}
{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"564d6e1b-4330-42bd-a646-461e7a6c2d1a","outcome":"rejected"}}
{"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"}
{"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}}

4
examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
View File

@@ -55,8 +55,8 @@
{"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}}
{"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}}
{"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}}
{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"b00e28dd-7349-480d-bc56-454247365ca8","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"b00e28dd-7349-480d-bc56-454247365ca8","outcome":"rejected"}}
{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"281bce21-7aee-4642-88a9-56917e50829c","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}}
{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"281bce21-7aee-4642-88a9-56917e50829c","outcome":"rejected"}}
{"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"}
{"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}}

2
examples/acp-agent/tests/snapshots/model-switching/session.jsonl
View File

@@ -37,7 +37,7 @@
{"type":"turn/start","seq":35,"time":1784086276811,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}}
{"type":"user/message","seq":36,"time":1784086276812,"data":{"content":[{"type":"text","text":"Without using tools, reply with exactly PRO and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"step/start","seq":37,"time":1784086276812,"data":{"turn":2,"step":1}}
{"type":"request/header-delta","seq":38,"time":1784086276813,"data":{"system":{"keepStart":2,"keepEnd":12,"insert":["{{system}}"]},"config":{"provider":"deepseek","model":"deepseek-v4-pro"}}}
{"type":"request/header","seq":38,"time":1784298376621,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
{"type":"assistant/chunk","seq":39,"time":1784086278053,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":40,"time":1784086278053,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
{"type":"assistant/chunk","seq":41,"time":1784086278242,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}

16
examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md
View File

@@ -14,6 +14,20 @@ Approval prompts are disabled in this session: actions that require approval are
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
<!-- request/header-delta 1: keepStart=2, keepEnd=12 -->
<!-- request/header change 1 -->
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-pro model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
Verify your work by running the code or tests. Keep answers brief and factual.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.

277
examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json
View File

@@ -273,5 +273,280 @@
}
}
],
"deltas": []
"changes": [
[
{
"name": "bash",
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The bash command to execute."
},
"description": {
"type": "string",
"description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
},
"timeoutMs": {
"type": "number",
"description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
},
"workdir": {
"type": "string",
"description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
},
"run_in_background": {
"type": "boolean",
"description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
}
},
"required": [
"command",
"description"
]
}
},
{
"name": "skill",
"description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The exact skill name from the available skills list."
}
},
"required": [
"name"
]
}
},
{
"name": "subagent",
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"parameters": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "A short (3-5 word) description of the delegated task, for display."
},
"prompt": {
"type": "string",
"description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "subagent_fork",
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"parameters": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "A short (3-5 word) description of the delegated task, for display."
},
"prompt": {
"type": "string",
"description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "task_kill",
"description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"reason": {
"type": "string",
"description": "Optional short reason, recorded in the log and forwarded to the task."
}
},
"required": [
"task_id"
]
}
},
{
"name": "task_list",
"description": "List your background tasks (running and finished) with their ids, kinds, and statuses.",
"parameters": {
"type": "object",
"properties": {}
}
},
{
"name": "task_output",
"description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"wait": {
"type": "boolean",
"description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."
},
"timeout_ms": {
"type": "number",
"description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."
}
},
"required": [
"task_id"
]
}
},
{
"name": "todo_write",
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
"parameters": {
"type": "object",
"properties": {
"todos": {
"type": "array",
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "What the task is — a short imperative line."
},
"status": {
"type": "string",
"description": "pending (not started) | in_progress (now) | completed (done).",
"enum": [
"pending",
"in_progress",
"completed"
]
}
},
"required": [
"content",
"status"
]
}
}
},
"required": [
"todos"
]
}
},
{
"name": "workflow",
"description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
"parameters": {
"type": "object",
"properties": {
"script": {
"type": "string",
"description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
},
"meta": {
"type": "object",
"description": "The workflow identity block (plain JSON — never code).",
"properties": {
"name": {
"type": "string",
"description": "Short kebab-case workflow name."
},
"description": {
"type": "string",
"description": "One-line description of what the workflow does."
},
"whenToUse": {
"type": "string",
"description": "Optional guidance on when this workflow applies."
},
"phases": {
"type": "array",
"description": "Optional phase declarations matched by phase() calls.",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "The phase title phase() calls match by exact string."
},
"detail": {
"type": "string",
"description": "Optional one-line description of the phase."
},
"provider": {
"type": "string",
"description": "Optional provider override this phase is expected to use."
},
"model": {
"type": "string",
"description": "Optional model override this phase is expected to use."
}
},
"required": [
"title"
]
}
}
},
"required": [
"name",
"description"
]
},
"args": {
"type": "object",
"description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
}
},
"required": [
"script",
"meta"
]
}
}
]
]
}

2
examples/acp-agent/tests/snapshots/permission-switching/session.jsonl
View File

@@ -107,7 +107,7 @@
{"type":"user/message","seq":105,"time":1783962244624,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"}
{"type":"context/message","seq":106,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"}
{"type":"step/start","seq":107,"time":1783962244624,"data":{"turn":2,"step":1}}
{"type":"request/header-delta","seq":108,"time":1783962244624,"data":{"system":{"keepStart":11,"keepEnd":2,"insert":["{{system}}","{{system}}"]}}}
{"type":"request/header","seq":108,"time":1784000791271,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"change"}}
{"type":"assistant/chunk","seq":109,"time":1783860671025,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":110,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}}
{"type":"assistant/chunk","seq":111,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}}

15
examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md
View File

@@ -13,7 +13,20 @@ Track every background task id you start. You are notified in-session when a tas
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.
<!-- request/header-delta 1: keepStart=11, keepEnd=2 -->
<!-- request/header change 1 -->
You are an AI agent powered by the DeepSeek Harness SDK.
You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug.
Verify your work by running the code or tests. Keep answers brief and factual.
Check the [exit code: N] marker on every bash result; investigate failures before moving on.
Track every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.
Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).
<!-- dsh-user-approval-policy:never -->
Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.

277
examples/acp-agent/tests/snapshots/permission-switching/tool-schemas.golden.json
View File

@@ -273,5 +273,280 @@
}
}
],
"deltas": []
"changes": [
[
{
"name": "bash",
"description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The bash command to execute."
},
"description": {
"type": "string",
"description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."
},
"timeoutMs": {
"type": "number",
"description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."
},
"workdir": {
"type": "string",
"description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."
},
"run_in_background": {
"type": "boolean",
"description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."
},
"sandbox_permissions": {
"type": "string",
"description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.",
"enum": [
"workspace-write",
"danger-full-access"
]
},
"justification": {
"type": "string",
"description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."
}
},
"required": [
"command",
"description"
]
}
},
{
"name": "skill",
"description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.",
"parameters": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The exact skill name from the available skills list."
}
},
"required": [
"name"
]
}
},
{
"name": "subagent",
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"parameters": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "A short (3-5 word) description of the delegated task, for display."
},
"prompt": {
"type": "string",
"description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "subagent_fork",
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.",
"parameters": {
"type": "object",
"properties": {
"description": {
"type": "string",
"description": "A short (3-5 word) description of the delegated task, for display."
},
"prompt": {
"type": "string",
"description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."
},
"run_in_background": {
"type": "boolean",
"description": "Run as a background task and return its id; collect with task_output or stop with task_kill."
}
},
"required": [
"description",
"prompt"
]
}
},
{
"name": "task_kill",
"description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"reason": {
"type": "string",
"description": "Optional short reason, recorded in the log and forwarded to the task."
}
},
"required": [
"task_id"
]
}
},
{
"name": "task_list",
"description": "List your background tasks (running and finished) with their ids, kinds, and statuses.",
"parameters": {
"type": "object",
"properties": {}
}
},
{
"name": "task_output",
"description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.",
"parameters": {
"type": "object",
"properties": {
"task_id": {
"type": "string",
"description": "Task id returned by the tool that started the background work."
},
"wait": {
"type": "boolean",
"description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."
},
"timeout_ms": {
"type": "number",
"description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."
}
},
"required": [
"task_id"
]
}
},
{
"name": "todo_write",
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
"parameters": {
"type": "object",
"properties": {
"todos": {
"type": "array",
"description": "The COMPLETE task list, replacing any previous list.",
"items": {
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "What the task is — a short imperative line."
},
"status": {
"type": "string",
"description": "pending (not started) | in_progress (now) | completed (done).",
"enum": [
"pending",
"in_progress",
"completed"
]
}
},
"required": [
"content",
"status"
]
}
}
},
"required": [
"todos"
]
}
},
{
"name": "workflow",
"description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return <value>` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise<any>` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise<any[]>` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise<any[]>` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.",
"parameters": {
"type": "object",
"properties": {
"script": {
"type": "string",
"description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return <json-value>`)."
},
"meta": {
"type": "object",
"description": "The workflow identity block (plain JSON — never code).",
"properties": {
"name": {
"type": "string",
"description": "Short kebab-case workflow name."
},
"description": {
"type": "string",
"description": "One-line description of what the workflow does."
},
"whenToUse": {
"type": "string",
"description": "Optional guidance on when this workflow applies."
},
"phases": {
"type": "array",
"description": "Optional phase declarations matched by phase() calls.",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "The phase title phase() calls match by exact string."
},
"detail": {
"type": "string",
"description": "Optional one-line description of the phase."
},
"provider": {
"type": "string",
"description": "Optional provider override this phase is expected to use."
},
"model": {
"type": "string",
"description": "Optional model override this phase is expected to use."
}
},
"required": [
"title"
]
}
}
},
"required": [
"name",
"description"
]
},
"args": {
"type": "object",
"description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."
}
},
"required": [
"script",
"meta"
]
}
}
]
]
}

2
examples/acp-agent/tests/snapshots/skill-load/tool-schemas.golden.json
View File

@@ -273,5 +273,5 @@
}
}
],
"deltas": []
"changes": []
}

2
examples/acp-agent/tests/snapshots/text-turn/tool-schemas.golden.json
View File

@@ -273,5 +273,5 @@
}
}
],
"deltas": []
"changes": []
}

2
examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.golden.json
View File

@@ -348,5 +348,5 @@
}
}
],
"deltas": []
"changes": []
}

2
examples/acp-agent/tests/snapshots/workspace-edit/tool-schemas.golden.json
View File

@@ -348,5 +348,5 @@
}
}
],
"deltas": []
"changes": []
}

3
examples/coding-agent/composition.md
View File

@@ -23,6 +23,8 @@ 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_coding_token_meter["token-meter<br/>@deepseek-ai/dsh-token-meter"]
cfg --> plugin_coding_token_meter
plugin_coding_compact_basic["compact-basic<br/>@deepseek-ai/dsh-compact-basic"]
cfg --> plugin_coding_compact_basic
plugin_coding_subagent["subagent<br/>@deepseek-ai/dsh-subagent"]
@@ -63,6 +65,7 @@ flowchart LR
| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` |
| `bash` | `@deepseek-ai/dsh-bash-local` |
| `stdio-agent` | `@deepseek-ai/dsh-stdio-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` |

16
examples/coding-agent/cordis.yml
View File

@@ -45,18 +45,14 @@
Verify your work by running the code or tests. Keep answers brief and
factual.
# Summarize an older range when derived history approaches the context window.
# This leaf consumes `ctx.llm` and the app's `agent/pre-step` seam.
# Replay-aware request pressure with one service-wide context window.
- id: token-meter
name: '@deepseek-ai/dsh-token-meter'
# Summarize an older range when measured history approaches the context window.
# Service-wide policy provides the ordinary threshold and retained-tail defaults.
- id: compact-basic
name: '@deepseek-ai/dsh-compact-basic'
config:
contextWindow: 128000
thresholdRatio: 0.8
retainTokens: 20480
summarizationProvider: ''
summarizationModel: ''
maxTokens: 8192
compactionRetries: 1
# Expose fresh-child `spawn` and completed-prefix `fork` through independent
# in-process backends. Each tool instance needs a distinct `toolName`; the registry

4
examples/coding-agent/tests/compaction.e2e.ts
View File

@@ -33,8 +33,10 @@ 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,
compact: {
tokenMeter: {
contextWindow: 2000,
},
compact: {
thresholdRatio: 0.5,
retainTokens: 400,
summarizationProvider: '',

13
examples/coding-agent/tests/harness.ts
View File

@@ -6,6 +6,8 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
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 SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic'
import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic'
@@ -42,6 +44,8 @@ export interface CodingHarnessOptions {
* compaction plugin (the default suites run without it).
*/
compact?: BasicCompactConfig
/** Optional token-meter capacity loaded before compact-basic. */
tokenMeter?: TokenMeterConfig
}
export async function codingHarness(workdir: string, options: CodingHarnessOptions = {}): Promise<Context> {
@@ -54,9 +58,12 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
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 it, with a lowered
// contextWindow/retainTokens so a short real session crosses the threshold.
if (options.compact !== undefined) await ctx.plugin(BasicCompactService, options.compact)
// 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.
if (options.compact !== undefined) {
await ctx.plugin(TokenMeterService, options.tokenMeter)
await ctx.plugin(BasicCompactService, options.compact)
}
// Durable JSONL persistence is opt-in: only the resume e2e needs it, and the
// other suites stay file-free. Loaded last so a resume's deferred
// `ctx.inject(['sessionPersistence'])` resolves once this is present.

19
examples/echo-agent/tests/fixtures/context/time-context/cordis.yml vendored Normal file
View File

@@ -0,0 +1,19 @@
# Test-only composition: keep time-context opt-in while exercising its real Loader/app path.
- id: mock-llm
name: '../../../../src/mock-llm.ts'
- id: bash
name: '@deepseek-ai/dsh-bash-local'
- id: time-context
name: '@deepseek-ai/dsh-time-context'
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-demo'
config:
provider: mock
model: mock-echo
persona: 'Test the time-context plugin.'
welcome: 'time-context e2e ready.'
persistenceRoot: './.sessions'
workspaceContext: false

46
examples/package.json Normal file
View File

@@ -0,0 +1,46 @@
{
"name": "dsh-examples",
"private": true,
"version": "0.0.1",
"type": "module",
"description": "Workspace umbrella for runnable demos and example-owned test compositions: declares their cordis.yml packages so plain Node resolves real exports→lib. Not a build target.",
"dependencies": {
"@cordisjs/plugin-hmr": "workspace:*",
"@cordisjs/plugin-include": "workspace:*",
"@deepseek-ai/dsh-acp-demo": "workspace:*",
"@deepseek-ai/dsh-bash-local": "workspace:*",
"@deepseek-ai/dsh-bash-sandbox": "workspace:*",
"@deepseek-ai/dsh-code-runtime-worker": "workspace:*",
"@deepseek-ai/dsh-compact-basic": "workspace:*",
"@deepseek-ai/dsh-fs-local": "workspace:*",
"@deepseek-ai/dsh-fs-policy": "workspace:*",
"@deepseek-ai/dsh-hooks-claude": "workspace:*",
"@deepseek-ai/dsh-hooks-codex": "workspace:*",
"@deepseek-ai/dsh-llm": "workspace:*",
"@deepseek-ai/dsh-llm-deepseek": "workspace:*",
"@deepseek-ai/dsh-llm-replay": "workspace:*",
"@deepseek-ai/dsh-permission": "workspace:*",
"@deepseek-ai/dsh-repeat-tool-guard": "workspace:*",
"@deepseek-ai/dsh-sandbox-local": "workspace:*",
"@deepseek-ai/dsh-spill-local": "workspace:*",
"@deepseek-ai/dsh-spill-policy": "workspace:*",
"@deepseek-ai/dsh-stdio-demo": "workspace:*",
"@deepseek-ai/dsh-subagent": "workspace:*",
"@deepseek-ai/dsh-subagent-fork": "workspace:*",
"@deepseek-ai/dsh-subagent-spawn": "workspace:*",
"@deepseek-ai/dsh-time-context": "workspace:*",
"@deepseek-ai/dsh-timeout-policy": "workspace:*",
"@deepseek-ai/dsh-token-meter": "workspace:*",
"@deepseek-ai/dsh-tool-cordis": "workspace:*",
"@deepseek-ai/dsh-tool-fs": "workspace:*",
"@deepseek-ai/dsh-tool-fs-search": "workspace:*",
"@deepseek-ai/dsh-tool-subagent": "workspace:*",
"@deepseek-ai/dsh-tool-todo": "workspace:*",
"@deepseek-ai/dsh-tool-workflow": "workspace:*",
"@deepseek-ai/dsh-tools": "workspace:*",
"@deepseek-ai/dsh-user-approval": "workspace:*",
"@deepseek-ai/dsh-web": "workspace:*",
"@deepseek-ai/dsh-web-fetch-local": "workspace:*",
"@deepseek-ai/dsh-workflow-workerthread": "workspace:*"
}
}