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

Merge remote-tracking branch 'origin/master' into claude/unified-environment-credentials-c8841a

Browse Source 
# Conflicts:
#	apps/web/tests/models-settings.e2e.ts
#	docs/config-catalog.md
#	packages/llm/llm-deepseek/README.i18n.yaml
#	packages/llm/llm-deepseek/README.md
#	packages/llm/llm-deepseek/README.zh.md
#	packages/llm/llm-deepseek/src/index.ts
#	packages/llm/llm-pi-ai/src/config.ts
#	packages/llm/llm-pi-ai/src/index.ts
This commit is contained in:
Yichen Jiang
2026-08-07 15:54:13 +08:00
parent fe31cd7609 7ce9c244ae
commit dfaf3c288e
365 changed files with 11131 additions and 1772 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -33,6 +33,8 @@ flowchart LR
cfg --> plugin_acp_token_meter
plugin_acp_compact_basic["compact-basic<br/>@deepseek-ai/dsh-compact-basic"]
cfg --> plugin_acp_compact_basic
plugin_acp_session_projection["session-projection<br/>@deepseek-ai/dsh-session-projection"]
cfg --> plugin_acp_session_projection
plugin_acp_subagent["subagent<br/>@deepseek-ai/dsh-subagent"]
cfg --> plugin_acp_subagent
plugin_acp_subagent_spawn["subagent-spawn<br/>@deepseek-ai/dsh-subagent-spawn"]
@@ -82,6 +84,7 @@ flowchart LR
| `acp-agent` | `@deepseek-ai/dsh-acp-demo` |
| `token-meter` | `@deepseek-ai/dsh-token-meter` |
| `compact-basic` | `@deepseek-ai/dsh-compact-basic` |
| `session-projection` | `@deepseek-ai/dsh-session-projection` |
| `subagent` | `@deepseek-ai/dsh-subagent` |
| `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` |
| `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` |

12
examples/acp-agent/cordis.yml
View File

@@ -78,6 +78,12 @@
maxTokens: 8192
compactionRetries: 1
# Projection registry: subagent catalog identity (mode/label) folds through
# its registered units; the catalog surfaces (`list_agents`, subagent listing)
# fail loud without the capability.
- id: session-projection
name: '@deepseek-ai/dsh-session-projection'
# Expose fresh-child `spawn` and completed-prefix `fork` through separate tool
# names so multi-child scenarios exercise both transports. These leaves follow
# the app because it provides `ctx.agents` and `ctx.tools`.
@@ -96,8 +102,8 @@
# Continuable background children are selected per delegation tool. The
# separately loaded control package registers the global `send_message`; its
# list plugin registers `list_agents` and requires the app's session query.
# `report` is installed only in continuable child scopes.
# list plugin registers `list_agents`, served through the sessionProjections
# registry mounted above. `report` is installed only in continuable child scopes.
- id: tool-subagent-control
name: '@deepseek-ai/dsh-tool-subagent-control'
@@ -139,6 +145,8 @@
# `todo_write` replaces the logged whole list for later model requests.
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
config:
allowParallelInProgress: true
# Identical repeat calls trigger advisory context, never a block, at the default
# thresholds [3, 5, 8]. Only the repeat-tool-guard snapshot scenario reaches them.

2
examples/acp-agent/tests/acp.snapshot.ts
View File

@@ -276,6 +276,8 @@ const SCENARIOS: Scenario[] = [
// symlinked instruction file to its target's content. A second nested path
// containing a literal closing tag is created at runtime: Git cannot check
// that name out on Windows, so this delimiter-injection case is POSIX-only.
// The fixture also shadows the baseline after the first touch finishes its
// projection; the next entering pre-step restores it before request 2.
// The scenario-specific config keeps home/root discovery hermetic, and the
// resulting prefix needs its own pinned header class.
{

36
examples/acp-agent/tests/fixtures/workspace-context-compaction.ts vendored Normal file
View File

@@ -0,0 +1,36 @@
import type { Context } from 'cordis'
import type {} from '@deepseek-ai/dsh-agent'
import { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact'
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import type {} from '@deepseek-ai/dsh-tools'
export const name = 'workspace-context-compaction'
/** Replace the visible workspace baseline after the first touch is fully projected. */
export function apply(ctx: Context): void {
ctx.on('tools/post-execute', async (exec, result, next) => {
const downstream = await next()
if (result.isError
|| exec.agent === undefined
|| exec.name !== 'read'
|| typeof exec.arguments !== 'object'
|| exec.arguments === null
|| !('file_path' in exec.arguments)
|| exec.arguments.file_path !== 'nested/task.txt') return downstream
const agent = exec.agent
const baseline = agent.session.surface.nodes
.map(seq => agent.session.events[seq])
.find(event => event?.type === 'user/message'
&& event.data.source.kind === 'workspace-instructions'
&& event.data.source.baseline === true)
if (baseline === undefined) throw new Error('workspace baseline missing before snapshot compaction')
agent.session.append('user/message', createUserMessage({
content: [{ type: 'text', text: 'Earlier context was compacted for this snapshot.' }],
source: COMPACT_CHECKPOINT_SOURCE,
}), {
surfaceOp: { op: 'replace', start: baseline.seq, end: baseline.seq },
sourceEventSeqs: [baseline.seq],
})
return downstream
})
}

2
examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
View File

@@ -160,7 +160,7 @@ interface ToolArgsMap {
/** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */
timeout_ms?: number;
} & Record<string, JsonValue>;
/** 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). */
/** 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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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). */
todo_write: {
/** The COMPLETE task list, replacing any previous list. */
todos: ({

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

@@ -386,7 +386,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

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

@@ -329,7 +329,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

2
examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md
View File

@@ -143,7 +143,7 @@ interface ToolArgsMap {
/** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */
timeout_ms?: number;
} & Record<string, JsonValue>;
/** 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). */
/** 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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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). */
todo_write: {
/** The COMPLETE task list, replacing any previous list. */
todos: ({

2
examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl
View File

@@ -4,7 +4,7 @@
{"type":"agent/inbox/spliced","seq":2,"time":1785498825916,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":3,"time":1785901435161,"data":{"turn":1,"step":1}}
{"type":"user/message","seq":4,"time":1785498825917,"data":{"content":[{"type":"text","text":"Using ONE run_code program, call tools.read on nested/task.txt. After the program finishes, answer the workspace handshake question using the newly discovered instructions: What is the Code Mode workspace handshake?"}],"source":{"kind":"user"},"role":"user","id":"3b04578e-7b22-4b44-b4cd-ef9d4d26fe8b"},"surfaceOp":"append"}
{"type":"user/message","seq":5,"time":1785901435161,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2119a7072358cc727f8d9c4cb7388e905b075fe6"}]},"role":"user","id":"ac92e76e-4861-47a6-87f8-4e9ca904eb24"},"surfaceOp":"append"}
{"type":"user/message","seq":5,"time":1785901435161,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nWorkspace snapshot root instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".git\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"AGENTS.md\",\"CLAUDE.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2119a7072358cc727f8d9c4cb7388e905b075fe6"}]},"role":"user","id":"ac92e76e-4861-47a6-87f8-4e9ca904eb24"},"surfaceOp":"append"}
{"type":"user/message","seq":6,"time":1785730478198,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"d6d78330-05c0-4ebd-9e29-595df6440250"},"surfaceOp":"append"}
{"type":"session/title","seq":7,"time":1785730478198,"data":{"title":"Using ONE run_code program, call","messageSeqs":[4],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":8,"time":1785498825920,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}

2
examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl
View File

@@ -18,7 +18,7 @@
{"type":"assistant/chunk","seq":80,"time":1785730437884,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":81,"time":1785730437884,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"fc73e1c1-7ff3-4722-9f4a-b245d8fdc040"},"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[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],"surfaceOp":"append"}
{"type":"tool/call","seq":82,"time":1785730437885,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}}
{"type":"tool/result","seq":83,"time":1785730437894,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119"},"content":[{"type":"tool-result","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: edit requires reading \"{{cwd}}/settings.txt\" first"}],"isError":true}],"role":"user","id":"5d9bc635-9fc4-4810-a49d-a627b23122e4"},"error":{"name":"FsError","code":"FS_NOT_OBSERVED"}},"sourceEventSeqs":[82],"surfaceOp":"append"}
{"type":"tool/result","seq":83,"time":1785730437894,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119"},"content":[{"type":"tool-result","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: edit requires reading \"{{cwd}}/settings.txt\" first — read the file, then retry"}],"isError":true}],"role":"user","id":"5d9bc635-9fc4-4810-a49d-a627b23122e4"},"error":{"name":"FsError","code":"FS_NOT_OBSERVED"}},"sourceEventSeqs":[82],"surfaceOp":"append"}
{"type":"step/end","seq":84,"time":1785730437894,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":85,"time":1785730437903,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":86,"time":1783611704931,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}

2
examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json
View File

@@ -345,7 +345,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

2
examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json
View File

@@ -437,7 +437,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

2
examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json
View File

@@ -512,7 +512,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

2
examples/acp-agent/tests/snapshots/subagent-continuable/tool-schemas.1.expected.json
View File

@@ -324,7 +324,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

2
examples/acp-agent/tests/snapshots/subagent-list-agents/tool-schemas.1.expected.json
View File

@@ -324,7 +324,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

2
examples/acp-agent/tests/snapshots/subagent-report/tool-schemas.1.expected.json
View File

@@ -324,7 +324,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

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

@@ -308,7 +308,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

2
examples/acp-agent/tests/snapshots/todo-write/input.json
View File

@@ -2,6 +2,6 @@
"steps": [
{ "op": "initialize" },
{ "op": "newSession" },
{ "op": "prompt", "text": "Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop." }
{ "op": "prompt", "text": "Use the todo_write tool to record a plan with exactly three todos for work running in parallel: \"read the code\" (in_progress), \"watch the background build\" (in_progress), \"write the fix\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop." }
]
}

73
examples/acp-agent/tests/snapshots/todo-write/session.jsonl
View File

@@ -1,36 +1,37 @@
{"type":"session","version":0,"id":"b0f1f758-dcf0-474e-851d-e62c11ec0a09","createdAt":1783352057652,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"agent/inbox/spliced","seq":0,"time":1785498772484,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"5ecf5e4b-6a18-447d-9341-48f38afdd12e"}]}}
{"type":"turn/start","seq":1,"time":1785821376741,"data":{"turn":1}}
{"type":"agent/inbox/spliced","seq":2,"time":1785821376741,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":3,"time":1783352057657,"data":{"turn":1,"step":1}}
{"type":"user/message","seq":4,"time":1785498772510,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"5ecf5e4b-6a18-447d-9341-48f38afdd12e"},"surfaceOp":"append"}
{"type":"user/message","seq":5,"time":1785730425725,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"8d4ac045-8016-4cec-8b12-91d9459231e1"},"surfaceOp":"append"}
{"type":"session/title","seq":6,"time":1785730425725,"data":{"title":"Use the todo_write tool to","messageSeqs":[4],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":7,"time":1785498772511,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/context","seq":8,"time":1785730425726,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
{"type":"assistant/chunk","seq":9,"time":1783352058426,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":10,"time0":1783352058466,"data":{"turn":1,"step":1,"index":0,"dt":[1,0,0,0,17,0,0,0,1,26,1,1,0,0,1,26,0,31,1,25,0,0,0,29,0,0,0,0,91,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," todo","_write"," tool"," to"," record"," a"," plan"," with"," exactly"," three"," todos"," in"," the"," specified"," status","es",","," then"," reply"," with"," \"","D","ONE","\"."]}}
{"type":"assistant/chunk","seq":41,"time":1783352058746,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"tool-call-chunks","seq0":42,"time0":1783352058747,"data":{"turn":1,"step":1,"index":1,"dt":[0,0,28,0,1,29,1,0,0,0,0,26,0,0,0,0,0,30,1,0,0,0,0,26,1,0,0,0,0,28,0,0,0,0,0,29,0,0,0,0,1,28,0,0,0,1,0,27,1,0,28,62,1],"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","args":["","{","\"","t","odos","\"",": ","[","{\"","content","\":"," \"","read"," the"," code","\","," \"","status","\":"," \"","in","_pro","gress","\"},"," {\"","content","\":"," \"","write"," the"," fix","\","," \"","status","\":"," \"","pending","\"},"," {\"","content","\":"," \"","run"," the"," tests","\","," \"","status","\":"," \"","pending","\"","}]","}"]}}
{"type":"assistant/chunk","seq":96,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."}}}}
{"type":"assistant/chunk","seq":97,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}}}
{"type":"assistant/chunk","seq":98,"time":1785498772522,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}}}}
{"type":"assistant/chunk","seq":99,"time":1785730425738,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":100,"time":1785730425738,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"08141496-5477-4d05-b2c7-414865ea9a17"},"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[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],"surfaceOp":"append"}
{"type":"tool/call","seq":101,"time":1785730425739,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}
{"type":"todo/write","seq":102,"time":1785730425747,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}}
{"type":"tool/result","seq":103,"time":1785730425748,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_fjAnBThbDjxepBtp3hDt3264"},"content":[{"type":"tool-result","toolCallId":"call_00_fjAnBThbDjxepBtp3hDt3264","content":[{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}],"isError":false}],"role":"user","id":"c178ad5b-7c1f-4239-9aa6-20d1c6b00a82"}},"sourceEventSeqs":[101],"surfaceOp":"append"}
{"type":"step/end","seq":104,"time":1785730425748,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":105,"time":1785730425759,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":106,"time":1783352059835,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":107,"time0":1783352059863,"data":{"turn":1,"step":2,"index":0,"dt":[0,1,0,28,0,1,0,27,0,1,0,0,29,0,0,0,1,0,28,0],"texts":["The"," todos"," have"," been"," written"," successfully","."," Now"," I"," just"," need"," to"," reply"," with"," the"," single"," word"," \"","D","ONE","\"."]}}
{"type":"assistant/chunk","seq":128,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":129,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
{"type":"assistant/chunk","seq":130,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
{"type":"assistant/chunk","seq":131,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."}}}}
{"type":"assistant/chunk","seq":132,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":133,"time":1785498772545,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}}}}
{"type":"assistant/chunk","seq":134,"time":1785730425764,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":135,"time":1785730425764,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"c4e454ce-14cc-4030-be47-0395ac9f12fb"},"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[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],"surfaceOp":"append"}
{"type":"step/end","seq":136,"time":1785730425764,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":137,"time":1785730425764,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"session","version":0,"id":"d9d967e8-0112-471c-a3b5-dfdc171aba61","createdAt":1785987077399,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"agent/inbox/spliced","seq":0,"time":1785987077401,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos for work running in parallel: \"read the code\" (in_progress), \"watch the background build\" (in_progress), \"write the fix\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"befb10e9-f992-4a19-9e1b-333ad7fd72f8"}]}}
{"type":"turn/start","seq":1,"time":1785987077401,"data":{"turn":1}}
{"type":"agent/inbox/spliced","seq":2,"time":1785987077401,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":3,"time":1785987077430,"data":{"turn":1,"step":1}}
{"type":"user/message","seq":4,"time":1785987077430,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos for work running in parallel: \"read the code\" (in_progress), \"watch the background build\" (in_progress), \"write the fix\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"befb10e9-f992-4a19-9e1b-333ad7fd72f8"},"surfaceOp":"append"}
{"type":"user/message","seq":5,"time":1785987077430,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"3893b488-4678-4b29-be9f-6365854b0ddc"},"surfaceOp":"append"}
{"type":"session/title","seq":6,"time":1785987077430,"data":{"title":"Use the todo_write tool to","messageSeqs":[4],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":7,"time":1785987077431,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/context","seq":8,"time":1785987077431,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
{"type":"assistant/chunk","seq":9,"time":1785987079233,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"reasoning-chunks","seq0":10,"time0":1785987079233,"data":{"turn":1,"step":1,"index":0,"dt":[152,51,2,0,0,61,55,0,1,0,47,53,0,1,0,46,1,0,0,1,45,1,0],"texts":["The"," user"," wants"," me"," to"," use"," todo","_write"," to"," create"," exactly"," three"," todos",","," then"," reply"," with"," \"","D","ONE","\""," and"," stop","."]}}
{"type":"assistant/chunk","seq":34,"time":1785987079909,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
{"type":"tool-call-chunks","seq0":35,"time0":1785987079910,"data":{"turn":1,"step":1,"index":1,"dt":[52,0,1,0,0,0,55,1,0,0,50,1,0,0,0,0,52,0,0,0,0,1,52,1,0,0,0,0,59,0,0,0,0,0,57,0,0,0,0,0,54,0,0,0,0,0,45,1,0,0,0,0,67,0,0,46],"id":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","args":["","{","\"","t","odos","\"",": ","[","{\"","content","\":"," \"","read"," the"," code","\","," \"","status","\":"," \"","in","_pro","gress","\"},"," {\"","content","\":"," \"","watch"," the"," background"," build","\","," \"","status","\":"," \"","in","_pro","gress","\"},"," {\"","content","\":"," \"","write"," the"," fix","\","," \"","status","\":"," \"","pending","\"","}]","}"]}}
{"type":"assistant/chunk","seq":92,"time":1785987080614,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use todo_write to create exactly three todos, then reply with \"DONE\" and stop."}}}}
{"type":"assistant/chunk","seq":93,"time":1785987080614,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"watch the background build\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}]}"}}}}
{"type":"assistant/chunk","seq":94,"time":1785987080615,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5778,"outputTokens":117,"cacheReadTokens":0,"reasoningTokens":24}}}}
{"type":"assistant/chunk","seq":95,"time":1785987080615,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":96,"time":1785987080618,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to use todo_write to create exactly three todos, then reply with \"DONE\" and stop."},{"type":"tool-call","id":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"watch the background build\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}]}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"600b618f-2403-4584-b7aa-84b474e7ef08"},"usage":{"inputTokens":5778,"outputTokens":117,"cacheReadTokens":0,"reasoningTokens":24}},"sourceEventSeqs":[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],"surfaceOp":"append"}
{"type":"tool/call","seq":97,"time":1785987080619,"data":{"turn":1,"step":1,"callId":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"watch the background build\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}]}"}}
{"type":"todo/write","seq":98,"time":1785987080632,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"watch the background build","status":"in_progress"},{"content":"write the fix","status":"pending"}]}}
{"type":"tool/result","seq":99,"time":1785987080633,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_UHvM5RrwIkjNJ9xh3S735164"},"content":[{"type":"tool-result","toolCallId":"call_00_UHvM5RrwIkjNJ9xh3S735164","content":[{"type":"text","text":"Updated todo list: 1 pending, 2 in progress, 0 completed."}],"isError":false}],"role":"user","id":"65e181f3-565f-4be4-9ffe-9d59c808f7f8"}},"sourceEventSeqs":[97],"surfaceOp":"append"}
{"type":"step/end","seq":100,"time":1785987080633,"data":{"turn":1,"step":1}}
{"type":"step/start","seq":101,"time":1785987080647,"data":{"turn":1,"step":2}}
{"type":"assistant/chunk","seq":102,"time":1785987081239,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
{"type":"assistant/chunk","seq":103,"time":1785987081239,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"Done"}}}
{"type":"assistant/chunk","seq":104,"time":1785987081391,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
{"type":"assistant/chunk","seq":105,"time":1785987081451,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
{"type":"assistant/chunk","seq":106,"time":1785987081452,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
{"type":"assistant/chunk","seq":107,"time":1785987081452,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
{"type":"assistant/chunk","seq":108,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Done."}}}}
{"type":"assistant/chunk","seq":109,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":110,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":154,"outputTokens":5,"cacheReadTokens":5760,"reasoningTokens":2}}}}
{"type":"assistant/chunk","seq":111,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":112,"time":1785987081454,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"Done."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"e4db2f4e-732f-4b58-a44f-5d08b50ce234"},"usage":{"inputTokens":154,"outputTokens":5,"cacheReadTokens":5760,"reasoningTokens":2}},"sourceEventSeqs":[102,103,104,105,106,107,108,109,110,111],"surfaceOp":"append"}
{"type":"step/end","seq":113,"time":1785987081455,"data":{"turn":1,"step":2}}
{"type":"turn/end","seq":114,"time":1785987081455,"data":{"turn":1,"reason":{"kind":"completed"}}}

2
examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json
View File

@@ -308,7 +308,7 @@
},
{
"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).",
"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. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one 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": {

65
examples/acp-agent/tests/snapshots/workspace-context/session.jsonl
View File

@@ -1,11 +1,11 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"agent/inbox/spliced","seq":0,"time":1785498790330,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Read nested/task.txt, then read scope</system-reminder>/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"22938d3b-c065-46c8-acb7-18f758285842"}]}}
{"type":"agent/inbox/spliced","seq":0,"time":1785498790330,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Read nested/task.txt, then read scope</system-reminder>/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"81078e7a-6837-45c2-a6b4-a5a3dfce0d4a"}]}}
{"type":"turn/start","seq":1,"time":1785821400350,"data":{"turn":1}}
{"type":"agent/inbox/spliced","seq":2,"time":1785498790356,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":3,"time":1785901433981,"data":{"turn":1,"step":1}}
{"type":"user/message","seq":4,"time":1785498790356,"data":{"content":[{"type":"text","text":"Read nested/task.txt, then read scope</system-reminder>/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"22938d3b-c065-46c8-acb7-18f758285842"},"surfaceOp":"append"}
{"type":"user/message","seq":5,"time":1785901433982,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"}]},"role":"user","id":"ec039e95-6864-49ef-ad23-4f65b331dc29"},"surfaceOp":"append"}
{"type":"user/message","seq":6,"time":1785730689193,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"cbea9bd9-3e08-48bf-951f-fe3e5aa4b5d9"},"surfaceOp":"append"}
{"type":"user/message","seq":4,"time":1785498790356,"data":{"content":[{"type":"text","text":"Read nested/task.txt, then read scope</system-reminder>/task.txt with the read tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"81078e7a-6837-45c2-a6b4-a5a3dfce0d4a"},"surfaceOp":"append"}
{"type":"user/message","seq":5,"time":1785901433982,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".dsh-project\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"AGENTS.md\",\"CLAUDE.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"}]},"role":"user","id":"4cba1848-cbb7-46fd-8cea-8497d54d0e63"},"surfaceOp":"append"}
{"type":"user/message","seq":6,"time":1785730689193,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"e4406554-e400-49c6-b8a3-0fe36841160b"},"surfaceOp":"append"}
{"type":"session/title","seq":7,"time":1785730689193,"data":{"title":"Read nested/task.txt, then read scope</s","messageSeqs":[4],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":8,"time":1785498790358,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/context","seq":9,"time":1785730689194,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
@@ -14,32 +14,33 @@
{"type":"assistant/chunk","seq":12,"time":1784903339801,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":13,"time":1785498790358,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":14,"time":1785730689194,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":15,"time":1785730689194,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"cb229812-91a1-4aa6-8bce-d3b8d032f6dd"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"}
{"type":"assistant/message","seq":15,"time":1785730689194,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"9e9648c4-949e-4cf1-b9ef-0eb65897d36b"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[10,11,12,13,14],"surfaceOp":"append"}
{"type":"tool/call","seq":16,"time":1785730689195,"data":{"turn":1,"step":1,"callId":"call_workspace_read","name":"read","arguments":"{\"file_path\":\"nested/task.txt\"}"}}
{"type":"tool/result","seq":17,"time":1785730689204,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_workspace_read"},"content":[{"type":"tool-result","toolCallId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false}],"role":"user","id":"260bbd5d-4496-40cf-b987-d1d944d93cf1"},"meta":{"path":"{{cwd}}/nested/task.txt","offset":1,"lines":[{"number":1,"text":"snapshot task"}],"totalLines":1}},"sourceEventSeqs":[16],"surfaceOp":"append"}
{"type":"step/end","seq":18,"time":1785498790369,"data":{"turn":1,"step":1}}
{"type":"agent/inbox/spliced","seq":19,"time":1785498790369,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]},"role":"user","id":"10cdaa4b-9654-420e-afca-3cfb07e26754"}]}}
{"type":"agent/inbox/spliced","seq":20,"time":1785730689207,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[],"outcome":"canceled"}}
{"type":"step/start","seq":21,"time":1785730689212,"data":{"turn":1,"step":2}}
{"type":"user/message","seq":22,"time":1785498790377,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","changes":[{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]},"role":"user","id":"10cdaa4b-9654-420e-afca-3cfb07e26754"},"surfaceOp":"append"}
{"type":"assistant/chunk","seq":23,"time":1784903339821,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":24,"time":1785498790377,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_workspace_delimiter_read","name":"read","argumentsDelta":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}}}
{"type":"assistant/chunk","seq":25,"time":1785498790377,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_delimiter_read","name":"read","arguments":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":26,"time":1785498790378,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":27,"time":1785498790378,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":28,"time":1785498790378,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_workspace_delimiter_read","name":"read","arguments":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"43385fc1-54b4-4a8a-82ca-d9111c766f48"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[23,24,25,26,27],"surfaceOp":"append"}
{"type":"tool/call","seq":29,"time":1785498790378,"data":{"turn":1,"step":2,"callId":"call_workspace_delimiter_read","name":"read","arguments":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}}
{"type":"tool/result","seq":30,"time":1785498790388,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_workspace_delimiter_read"},"content":[{"type":"tool-result","toolCallId":"call_workspace_delimiter_read","content":[{"type":"text","text":"<path>{{cwd}}/scope</system-reminder>/task.txt</path>\n<type>file</type>\n<content>\n1: delimiter path snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false}],"role":"user","id":"3a62b23b-d165-4c6d-a028-e171c4b2d7fc"},"meta":{"path":"{{cwd}}/scope</system-reminder>/task.txt","offset":1,"lines":[{"number":1,"text":"delimiter path snapshot task"}],"totalLines":1}},"sourceEventSeqs":[29],"surfaceOp":"append"}
{"type":"step/end","seq":31,"time":1785730689220,"data":{"turn":1,"step":2}}
{"type":"agent/inbox/spliced","seq":32,"time":1785730689220,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: scope<\\/system-reminder>/AGENTS.md\n\nThese instructions apply to work under `scope<\\/system-reminder>`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nDelimiter path snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","changes":[{"action":"set","scope":"scope</system-reminder>\u0000AGENTS.md","path":"scope</system-reminder>/AGENTS.md","digest":"38803cd13e2dff9105ba5fbbc703fe27e989e26e"}]},"role":"user","id":"01c3af61-4567-4be2-b776-21f04ddc9cba"}]}}
{"type":"agent/inbox/spliced","seq":33,"time":1785498790389,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[],"outcome":"canceled"}}
{"type":"step/start","seq":34,"time":1785498790396,"data":{"turn":1,"step":3}}
{"type":"user/message","seq":35,"time":1785498790396,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: scope<\\/system-reminder>/AGENTS.md\n\nThese instructions apply to work under `scope<\\/system-reminder>`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nDelimiter path snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","changes":[{"action":"set","scope":"scope</system-reminder>\u0000AGENTS.md","path":"scope</system-reminder>/AGENTS.md","digest":"38803cd13e2dff9105ba5fbbc703fe27e989e26e"}]},"role":"user","id":"01c3af61-4567-4be2-b776-21f04ddc9cba"},"surfaceOp":"append"}
{"type":"assistant/chunk","seq":36,"time":1785498790396,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":37,"time":1785498790396,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
{"type":"assistant/chunk","seq":38,"time":1785498790396,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":39,"time":1785498790396,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":40,"time":1785498790397,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":41,"time":1785498790397,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"f82f5200-090f-4e68-a016-963ab7166d4f"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[36,37,38,39,40],"surfaceOp":"append"}
{"type":"step/end","seq":42,"time":1785498790397,"data":{"turn":1,"step":3}}
{"type":"turn/end","seq":43,"time":1785901434023,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"user/message","seq":17,"time":1785982371865,"data":{"content":[{"type":"text","text":"Earlier context was compacted for this snapshot."}],"source":{"kind":"plugin","plugin":"compact"},"role":"user","id":"162c764f-f01d-484d-ad81-1481dc29792a"},"sourceEventSeqs":[5],"surfaceOp":{"op":"replace","start":5,"end":5}}
{"type":"tool/result","seq":18,"time":1785982371865,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_workspace_read"},"content":[{"type":"tool-result","toolCallId":"call_workspace_read","content":[{"type":"text","text":"<path>{{cwd}}/nested/task.txt</path>\n<type>file</type>\n<content>\n1: snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false}],"role":"user","id":"a46fded2-333a-4fb2-b01e-28520bffbc21"},"meta":{"path":"{{cwd}}/nested/task.txt","offset":1,"lines":[{"number":1,"text":"snapshot task"}],"totalLines":1}},"sourceEventSeqs":[16],"surfaceOp":"append"}
{"type":"step/end","seq":19,"time":1785982371865,"data":{"turn":1,"step":1}}
{"type":"agent/inbox/spliced","seq":20,"time":1785730689207,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"},{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".dsh-project\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"AGENTS.md\",\"CLAUDE.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"},{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]},"role":"user","id":"09640903-80ea-4eb6-8635-90ddfb4e24e4"}]}}
{"type":"agent/inbox/spliced","seq":21,"time":1785982371873,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[],"outcome":"canceled"}}
{"type":"step/start","seq":22,"time":1785982371873,"data":{"turn":1,"step":2}}
{"type":"user/message","seq":23,"time":1785982371873,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nRoot snapshot instruction.\n\n</system-reminder>"},{"type":"text","text":"<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nThese instructions apply to work under `nested`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nNested snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".dsh-project\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"AGENTS.md\",\"CLAUDE.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"2e18766c26603608f321508caae00ea8f4434d59"},{"action":"set","scope":"nested\u0000AGENTS.md","path":"nested/AGENTS.md","digest":"c446df9a85c7e73a3055f394a4822a19ac9ead5a"}]},"role":"user","id":"09640903-80ea-4eb6-8635-90ddfb4e24e4"},"surfaceOp":"append"}
{"type":"assistant/chunk","seq":24,"time":1785498790377,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":25,"time":1785498790377,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_workspace_delimiter_read","name":"read","argumentsDelta":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}}}
{"type":"assistant/chunk","seq":26,"time":1785498790378,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_workspace_delimiter_read","name":"read","arguments":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}}}}
{"type":"assistant/chunk","seq":27,"time":1785498790378,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":28,"time":1785982371874,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":29,"time":1785982371874,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_workspace_delimiter_read","name":"read","arguments":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"ba85f14b-5ff0-4b71-a3f8-0d9ea7f4893d"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[24,25,26,27,28],"surfaceOp":"append"}
{"type":"tool/call","seq":30,"time":1785982371875,"data":{"turn":1,"step":2,"callId":"call_workspace_delimiter_read","name":"read","arguments":"{\"file_path\":\"scope</system-reminder>/task.txt\"}"}}
{"type":"tool/result","seq":31,"time":1785982371882,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_workspace_delimiter_read"},"content":[{"type":"tool-result","toolCallId":"call_workspace_delimiter_read","content":[{"type":"text","text":"<path>{{cwd}}/scope</system-reminder>/task.txt</path>\n<type>file</type>\n<content>\n1: delimiter path snapshot task\n\n(End of file - total 1 lines)\n</content>"}],"isError":false}],"role":"user","id":"c0fad80c-59c3-41bf-b662-84f87ee1420c"},"meta":{"path":"{{cwd}}/scope</system-reminder>/task.txt","offset":1,"lines":[{"number":1,"text":"delimiter path snapshot task"}],"totalLines":1}},"sourceEventSeqs":[30],"surfaceOp":"append"}
{"type":"step/end","seq":32,"time":1785982371882,"data":{"turn":1,"step":2}}
{"type":"agent/inbox/spliced","seq":33,"time":1785498790389,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: scope<\\/system-reminder>/AGENTS.md\n\nThese instructions apply to work under `scope<\\/system-reminder>`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nDelimiter path snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","changes":[{"action":"set","scope":"scope</system-reminder>\u0000AGENTS.md","path":"scope</system-reminder>/AGENTS.md","digest":"38803cd13e2dff9105ba5fbbc703fe27e989e26e"}]},"role":"user","id":"cd19663e-c8b5-46a5-9eeb-1386dcb1c609"}]}}
{"type":"agent/inbox/spliced","seq":34,"time":1785982371889,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[],"outcome":"canceled"}}
{"type":"step/start","seq":35,"time":1785982371889,"data":{"turn":1,"step":3}}
{"type":"user/message","seq":36,"time":1785982371889,"data":{"content":[{"type":"text","text":"<system-reminder>\nAdditional instructions from: scope<\\/system-reminder>/AGENTS.md\n\nThese instructions apply to work under `scope<\\/system-reminder>`. Use them as guidance when relevant; more specific instructions take precedence. They do not override system, developer, or direct user instructions.\n\nDelimiter path snapshot instruction.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","changes":[{"action":"set","scope":"scope</system-reminder>\u0000AGENTS.md","path":"scope</system-reminder>/AGENTS.md","digest":"38803cd13e2dff9105ba5fbbc703fe27e989e26e"}]},"role":"user","id":"cd19663e-c8b5-46a5-9eeb-1386dcb1c609"},"surfaceOp":"append"}
{"type":"assistant/chunk","seq":37,"time":1785498790396,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":38,"time":1785498790396,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}}
{"type":"assistant/chunk","seq":39,"time":1785498790396,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
{"type":"assistant/chunk","seq":40,"time":1785498790397,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
{"type":"assistant/chunk","seq":41,"time":1785982371890,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":42,"time":1785982371890,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"81b25d58-fa4a-4eb6-9b87-1c33baf90053"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[37,38,39,40,41],"surfaceOp":"append"}
{"type":"step/end","seq":43,"time":1785982371890,"data":{"turn":1,"step":3}}
{"type":"turn/end","seq":44,"time":1785982371891,"data":{"turn":1,"reason":{"kind":"completed"}}}

2
examples/acp-agent/workspace-context.cordis.snapshot.yml
View File

@@ -28,3 +28,5 @@
- insert:
- id: llm-replay
name: '@deepseek-ai/dsh-llm-replay'
- id: workspace-context-compaction
name: './tests/fixtures/workspace-context-compaction.ts'

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

@@ -31,6 +31,8 @@ flowchart LR
cfg --> plugin_headless_token_meter
plugin_headless_compact_basic["compact-basic<br/>@deepseek-ai/dsh-compact-basic"]
cfg --> plugin_headless_compact_basic
plugin_headless_session_projection["session-projection<br/>@deepseek-ai/dsh-session-projection"]
cfg --> plugin_headless_session_projection
plugin_headless_subagent["subagent<br/>@deepseek-ai/dsh-subagent"]
cfg --> plugin_headless_subagent
plugin_headless_subagent_spawn["subagent-spawn<br/>@deepseek-ai/dsh-subagent-spawn"]
@@ -71,6 +73,7 @@ flowchart LR
| `cli-agent` | `@deepseek-ai/dsh-cli-demo` |
| `token-meter` | `@deepseek-ai/dsh-token-meter` |
| `compact-basic` | `@deepseek-ai/dsh-compact-basic` |
| `session-projection` | `@deepseek-ai/dsh-session-projection` |
| `subagent` | `@deepseek-ai/dsh-subagent` |
| `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` |
| `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` |

7
examples/headless-agent/cordis.yml
View File

@@ -71,6 +71,11 @@
maxTokens: 8192
compactionRetries: 1
# Projection registry: durable subagent identity (mode/label) folds through
# its registered units; subagent catalog reads fail loud without the capability.
- id: session-projection
name: '@deepseek-ai/dsh-session-projection'
# Expose fresh-child `spawn` and completed-prefix `fork` through independent
# in-process backends.
- id: subagent
@@ -129,6 +134,8 @@
# `todo_write` replaces the logged whole list.
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
config:
allowParallelInProgress: true
# Policy loads before the model-facing filesystem tools so writes and edits
# require an observed file. Relative paths resolve from the process cwd.

44
examples/headless-agent/subagent-diagnostic.cordis.snapshot.yml Normal file
View File

@@ -0,0 +1,44 @@
# Keyless real-Loader composition for the descriptor-less cold-child
# diagnostic snapshot. The seeded parent owns one session-backed child whose
# log carries `origin: 'subagent'` but no descriptor event, so the projection
# fold produces no identity and `list_agents` must surface the child as a
# `[diagnostic: corrupt]` row instead of silently dropping it.
- id: persistence
name: '@deepseek-ai/dsh-session-persistence-jsonl'
config:
root: './.sessions'
compression: none
# file/override both default to their DSH_SNAPSHOT_* env vars.
- id: replay
name: '@deepseek-ai/dsh-llm-replay'
# This scenario probes the subagent catalog only, so the bash/filesystem
# stacks are absent; the bundle must opt out of the tools that would wait
# forever for executors this tree never mounts.
- id: agent
name: '@deepseek-ai/dsh-agent-spine-demo'
config:
agents: []
workspaceContext: false
skills:
enabled: false
toolBash: false
toolTasks: false
goals: false
# Projection registry: the cold child's identity fold runs through it; the
# catalog read fails loud when the capability is absent.
- id: session-projection
name: '@deepseek-ai/dsh-session-projection'
- id: subagent
name: '@deepseek-ai/dsh-subagent'
- id: tool-subagent-list-agents
name: '@deepseek-ai/dsh-tool-subagent-control/list-agents'
# Await the persisted resume before the headless driver inspects root agents.
- id: resumed-agent
name: './tests/fixtures/subagent-diagnostic-agent.ts'

26
examples/headless-agent/tests/fixtures/subagent-diagnostic-agent.ts vendored Normal file
View File

@@ -0,0 +1,26 @@
/**
* Loader fixture that resumes the seeded diagnostic-scenario parent before
* CLI dispatch, so `list_agents` runs against its pre-seeded cold child.
* @module subagent-diagnostic-agent
*/
import type { Context } from 'cordis'
import type { SessionId } from '@deepseek-ai/dsh-session'
/** Fixture plugin name. */
export const name = 'subagent-diagnostic-agent'
/** Services that must exist before the fixture resumes its agent. */
export const inject = ['agents', 'agentLoop', 'sessionPersistence']
/**
* Resume the seeded session and bind its exact handle to this fixture's lifetime.
* @param ctx - settled agent and persistence services from the Loader tree.
* @returns after the resumed agent is published.
*/
export async function apply(ctx: Context): Promise<void> {
const handle = await ctx.agents.resume({
resumeSessionId: 'subagent-diagnostic-parent' as SessionId,
agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
})
ctx.effect(() => () => handle.dispose(), 'subagent-diagnostic-agent.handle')
}

25
examples/headless-agent/tests/fixtures/workspace-context-resume-agent.ts vendored Normal file
View File

@@ -0,0 +1,25 @@
/**
* Loader fixture that resumes the seeded workspace-context session.
* @module workspace-context-resume-agent
*/
import type { Context } from 'cordis'
import type { SessionId } from '@deepseek-ai/dsh-session'
/** Fixture plugin name. */
export const name = 'workspace-context-resume-agent'
/** Services that must exist before the fixture resumes its agent. */
export const inject = ['agents', 'agentLoop', 'sessionPersistence']
/**
* Resume the seeded session and bind its handle to this fixture's lifetime.
* @param ctx - settled agent and persistence services from the Loader tree.
* @returns after the resumed agent is published.
*/
export async function apply(ctx: Context): Promise<void> {
const handle = await ctx.agents.resume({
resumeSessionId: 'workspace-context-resume' as SessionId,
agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
})
ctx.effect(() => () => handle.dispose(), 'workspace-context-resume-agent.handle')
}

7
examples/headless-agent/tests/harness.ts
View File

@@ -30,8 +30,9 @@ export const SYSTEM_PROMPT = 'You are a coding agent. Use bash for file operatio
/** System prompt for the todo_write e2e: nudges the model to plan with the tool. */
export const TODO_SYSTEM_PROMPT = 'You are a coding agent. For multi-step work, '
+ 'use the todo_write tool to track a task list: send the WHOLE list each call, '
+ 'keep at most one task in_progress (exactly one while work remains), and mark '
+ 'a task completed as soon as it is done.'
+ 'mark every task being actively worked on in_progress (several at once when '
+ 'work runs in parallel, at least one while work remains), and mark a task '
+ 'completed as soon as it is done.'
/** Options for {@link codingHarness}. */
export interface CodingHarnessOptions {
@@ -65,7 +66,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
await ctx.plugin(BashEnvPlugin)
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
await ctx.plugin(ToolBash)
await ctx.plugin(ToolTodo)
await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
// Compaction is opt-in: only the compaction e2e loads the reusable meter and backend.
if (options.compact !== undefined) {
await ctx.plugin(TokenMeterService)

40
examples/headless-agent/tests/headless.snapshot.ts
View File

@@ -31,6 +31,10 @@ const retryScenarioDir = join(snapshotsDir, 'provider-retry')
const retryConfigPath = fileURLToPath(new URL('../retry.cordis.snapshot.yml', import.meta.url))
const credentialsScenarioDir = join(snapshotsDir, 'missing-credential')
const credentialsConfigPath = fileURLToPath(new URL('../credentials.cordis.snapshot.yml', import.meta.url))
// Same keyless composition as the missing-credential scenario: the endpoint is
// never dialed either way, because a supplied-but-unusable key fails credential
// resolution exactly where an absent one does.
const invalidCredentialScenarioDir = join(snapshotsDir, 'invalid-credential')
const ralphScenarioDir = join(snapshotsDir, 'ralph-loop')
const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url))
const startupFailureConfigPath = fileURLToPath(new URL('./fixtures/startup-activation-error/cordis.yml', import.meta.url))
@@ -260,6 +264,42 @@ describe('headless stream-json snapshots', () => {
expect(normalized).not.toContain('as a last resort')
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('logs actionable invalid-credential guidance through the one-shot app', async () => {
const streamExpected = join(invalidCredentialScenarioDir, 'stream-json.expected.jsonl')
let runCwd = ''
const result = await runLoaderSmoke({
label: 'invalid-credential headless stream-json snapshot',
tempDirPrefix: 'headless-snapshot-invalid-credential-',
binScript,
configPath: credentialsConfigPath,
binArgs: ['--config', credentialsConfigPath, '--output-format', 'stream-json', 'say pong'],
tsconfigPath,
env: {
// A key that exists but no HTTP header can carry — the paste this
// change exists for. Before it, `fetch` refused to build the header
// and the turn ended on a retried ByteString TypeError.
DEEPSEEK_API_KEY: 'sk-\u{1F600}pasted-from-a-chat-window',
DEEPSEEK_BASE_URL: '',
NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
},
prepare: (cwd) => { runCwd = cwd },
})
expect(result.stderr).toBe('')
const normalized = normalizeHeadlessStream(result.stdout, runCwd)
if (refreshing) await writeFile(streamExpected, normalized)
expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
// The durable failure names the reference to correct and the writer that
// usually owns it, and stays true in a composition that mounts no Models
// page at all.
expect(normalized).toContain('the API key resolved from DEEPSEEK_API_KEY contains characters')
expect(normalized).toContain('the web Models page writes it')
// Neither the key nor the transport-level symptom it used to produce may
// reach the user: the code point of one character is still the key.
expect(normalized).not.toContain('pasted-from-a-chat-window')
expect(normalized).not.toContain('ByteString')
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('logs the model default and a dynamic next-step reasoning effort', async () => {
const result = await runLoaderSmoke({
label: 'reasoning effort headless stream-json snapshot',

2
examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
View File

File diff suppressed because one or more lines are too long

2
examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
View File

File diff suppressed because one or more lines are too long

2
examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
View File

File diff suppressed because one or more lines are too long

12
examples/headless-agent/tests/snapshots/invalid-credential/stream-json.expected.jsonl Normal file
View File

@@ -0,0 +1,12 @@
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":0,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"say pong"}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":1,"time":0,"data":{"turn":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"agent/inbox/spliced","seq":2,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":3,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":4,"time":0,"data":{"content":[{"type":"text","text":"say pong"}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"session/title","seq":5,"time":0,"data":{"title":"say pong","messageSeqs":[4],"source":{"kind":"fallback"}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":6,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/context","seq":7,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":1000000}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"llm-deepseek: the API key resolved from DEEPSEEK_API_KEY contains characters no HTTP header can carry; set DEEPSEEK_API_KEY to the raw key alone (the web Models page writes it)","code":"INVALID_CREDENTIAL"}}}}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":9,"time":0,"data":{"turn":1,"step":1}}}
{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":10,"time":0,"data":{"turn":1,"reason":{"kind":"error","error":{"message":"llm-deepseek: the API key resolved from DEEPSEEK_API_KEY contains characters no HTTP header can carry; set DEEPSEEK_API_KEY to the raw key alone (the web Models page writes it)","code":"INVALID_CREDENTIAL"}}}}}
{"type":"result","sessionId":"{{sessionId}}","output":""}

2
examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
View File

File diff suppressed because one or more lines are too long

31
examples/headless-agent/tests/subagent-diagnostic-snapshots/descriptorless-child/parent.expected.jsonl Normal file
View File

@@ -0,0 +1,31 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1}}
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Start a background task."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"turn/end","seq":2,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"session/end-seed","seq":3,"time":0,"data":{}}
{"type":"agent/inbox/spliced","seq":4,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Call list_agents once and report what it shows."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}
{"type":"turn/start","seq":5,"time":0,"data":{"turn":2}}
{"type":"agent/inbox/spliced","seq":6,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":7,"time":0,"data":{"turn":2,"step":1}}
{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"Call list_agents once and report what it shows."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"session/title","seq":9,"time":0,"data":{"title":"Start a background task.","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
{"type":"assistant/chunk","seq":12,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
{"type":"assistant/chunk","seq":13,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"list-once","name":"list_agents","argumentsDelta":"{}"}}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"list-once","name":"list_agents","arguments":"{}"}}}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
{"type":"assistant/message","seq":17,"time":0,"data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"list-once","name":"list_agents","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[12,13,14,15,16],"surfaceOp":"append"}
{"type":"tool/call","seq":18,"time":0,"data":{"turn":2,"step":1,"callId":"list-once","name":"list_agents","arguments":"{}"}}
{"type":"tool/result","seq":19,"time":0,"data":{"turn":2,"step":1,"message":{"source":{"kind":"tool","callId":"list-once"},"content":[{"type":"tool-result","toolCallId":"list-once","content":[{"type":"text","text":"{{sessionId}} [diagnostic: corrupt]"}],"isError":false}],"role":"user","id":"{{sessionId}}"}},"sourceEventSeqs":[18],"surfaceOp":"append"}
{"type":"step/end","seq":20,"time":0,"data":{"turn":2,"step":1}}
{"type":"step/start","seq":21,"time":0,"data":{"turn":2,"step":2}}
{"type":"assistant/chunk","seq":22,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":23,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":0,"text":"The stored subagent is unreadable. PARENT_DONE"}}}
{"type":"assistant/chunk","seq":24,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"The stored subagent is unreadable. PARENT_DONE"}}}}
{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":27,"time":0,"data":{"turn":2,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"The stored subagent is unreadable. PARENT_DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[22,23,24,25,26],"surfaceOp":"append"}
{"type":"step/end","seq":28,"time":0,"data":{"turn":2,"step":2}}
{"type":"turn/end","seq":29,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}

1
examples/headless-agent/tests/subagent-diagnostic-snapshots/descriptorless-child/replay.override.json Normal file
View File

@@ -0,0 +1 @@
[{"kind": "chunks", "chunks": [{"type": "block-start", "index": 0, "blockType": "tool-call"}, {"type": "tool-call-delta", "index": 0, "id": "list-once", "name": "list_agents", "argumentsDelta": "{}"}, {"type": "block-end", "index": 0, "block": {"type": "tool-call", "id": "list-once", "name": "list_agents", "arguments": "{}"}}, {"type": "usage", "usage": {"inputTokens": 10, "outputTokens": 5}}, {"type": "finish", "reason": {"kind": "tool-calls"}}]}, {"kind": "chunks", "chunks": [{"type": "block-start", "index": 0, "blockType": "text"}, {"type": "text-delta", "index": 0, "text": "The stored subagent is unreadable. PARENT_DONE"}, {"type": "block-end", "index": 0, "block": {"type": "text", "text": "The stored subagent is unreadable. PARENT_DONE"}}, {"type": "usage", "usage": {"inputTokens": 10, "outputTokens": 5}}, {"type": "finish", "reason": {"kind": "stop"}}]}]

119
examples/headless-agent/tests/subagent-diagnostic.snapshot.ts Normal file
View File

@@ -0,0 +1,119 @@
/**
* Assembled-app regression: a persisted `origin: 'subagent'` child whose log
* carries no descriptor event is surfaced by `list_agents` as a
* `[diagnostic: corrupt]` row instead of being silently dropped.
*/
import { readFile, readdir, writeFile } from 'node:fs/promises'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import { normalizeSessionLog, scrubRequestHeaders, type NormalizeContext } from '@deepseek-ai/dsh-acp-snapshot'
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import SessionStore, { SESSION_FORMAT_VERSION, SessionId, type SessionEvent, type SessionHeader } from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { describe, expect, it } from 'vitest'
const fixtureDir = fileURLToPath(new URL('./subagent-diagnostic-snapshots/descriptorless-child', import.meta.url))
const replayOverride = join(fixtureDir, 'replay.override.json')
const parentExpected = join(fixtureDir, 'parent.expected.jsonl')
const configPath = fileURLToPath(new URL('../subagent-diagnostic.cordis.snapshot.yml', import.meta.url))
const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
const parentId = SessionId('subagent-diagnostic-parent')
const childId = SessionId('subagent-diagnostic-child')
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
const task = 'Call list_agents once and report what it shows.'
/**
* Seed a completed parent turn plus one cold child that durably classifies
* as a subagent (`origin`) but never appended its descriptor event — the
* publication-window death the diagnostic row exists for.
*/
async function seedDescriptorlessChild(root: string, cwd: string): Promise<void> {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(SessionPersistenceJsonl, { root, compression: 'none' })
const parentMeta: SessionHeader = {
version: SESSION_FORMAT_VERSION,
id: parentId,
createdAt: 1,
cwd,
delegationDepth: 0,
}
const parentEvents: SessionEvent[] = [
{ type: 'turn/start', seq: 0, time: 10, data: { turn: 1 } },
{ type: 'user/message', seq: 1, time: 11, data: createUserMessage({ content: [{ type: 'text', text: 'Start a background task.' }], source: { kind: 'user' } }), surfaceOp: 'append' },
{ type: 'turn/end', seq: 2, time: 12, data: { turn: 1, reason: { kind: 'completed' } } },
]
const childMeta: SessionHeader = {
version: SESSION_FORMAT_VERSION,
id: childId,
createdAt: 2,
cwd,
parentSession: parentId,
origin: 'subagent',
delegationDepth: 1,
}
const childEvents: SessionEvent[] = [
{ type: 'turn/start', seq: 0, time: 20, data: { turn: 1 } },
{ type: 'turn/end', seq: 1, time: 21, data: { turn: 1, reason: { kind: 'interrupted' } } },
]
try {
await ctx.sessionPersistence.create(parentMeta)
await ctx.sessionPersistence.append(parentId, parentEvents)
await ctx.sessionPersistence.create(childMeta)
await ctx.sessionPersistence.append(childId, childEvents)
} finally {
await ctx.fiber.dispose()
}
}
describe('descriptor-less cold child diagnostic snapshot', () => {
it('surfaces the unreadable child as a corrupt diagnostic through the assembled headless app', async () => {
let cwd = ''
const result = await runLoaderSmoke({
label: 'subagent diagnostic headless stream-json snapshot',
tempDirPrefix: 'dsh-subagent-diag-',
binScript,
configPath,
binArgs: ['--config', configPath, '--output-format', 'stream-json', task],
tsconfigPath,
env: {
DSH_SNAPSHOT_FILE: replayOverride,
DSH_SNAPSHOT_OVERRIDE: replayOverride,
},
prepare: async (runCwd) => {
cwd = runCwd
await seedDescriptorlessChild(join(runCwd, '.sessions'), runCwd)
},
inspect: async (runCwd) => {
const sessionsDir = join(runCwd, '.sessions')
const files = (await readdir(sessionsDir, { recursive: true })).filter(file => file.endsWith('.jsonl'))
const logs = await Promise.all(files.map(async file => readFile(join(sessionsDir, file), 'utf8')))
const parent = logs.find(content => content.includes('"subagent-diagnostic-parent"'))
if (parent === undefined) throw new Error('missing persisted parent log')
// THE model-visible fact: the descriptor-less child is reported, not
// silently dropped, and its reason is the corrupt classification.
expect(parent).toContain(`${childId} [diagnostic: corrupt]`)
const context: NormalizeContext = { sessionIds: [parentId, childId], cwd }
const normalizedParent = scrubRequestHeaders(normalizeSessionLog(parent, context))
if (refreshing) {
await writeFile(parentExpected, normalizedParent)
}
expect(normalizedParent).toBe(await readFile(parentExpected, 'utf8'))
},
})
expect(result.stderr).toBe('')
const records = result.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record<string, unknown>)
expect(records.at(-1)).toMatchObject({
type: 'result',
sessionId: parentId,
output: 'The stored subagent is unreadable. PARENT_DONE',
})
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
})

11
examples/headless-agent/tests/todo-write.e2e.ts
View File

@@ -31,9 +31,10 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
agent.followup(createUserMessage({
content: [{ 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.' }], source: { kind: 'user' } }))
'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.' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const events = [...agent.session.events]
@@ -42,13 +43,15 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
const calls = events.filter(event => event.type === 'tool/call')
expect(calls.some(event => event.data.name === 'todo_write')).toBe(true)
// And the tool wrote a todo/write event to the log — verify the WORLD.
// And the tool wrote a todo/write event to the log — verify the WORLD,
// including two simultaneously in_progress tasks (the parallel contract).
const todoEvents = events.filter(event => event.type === 'todo/write')
expect(todoEvents.length).toBeGreaterThan(0)
const todos = (todoEvents.at(-1)!).data.todos
expect(todos).toEqual([
{ content: 'inspect the failing test', status: 'in_progress' },
{ content: 'watch the background build', status: 'in_progress' },
{ content: 'apply the fix', status: 'pending' },
])
}, 120_000)

1
examples/headless-agent/tests/workspace-context-resume-snapshots/offline-edit/replay.jsonl Normal file
View File

@@ -0,0 +1 @@
{"type":"session","version":0,"id":"workspace-context-resume-replay","createdAt":1,"delegationDepth":0}

11
examples/headless-agent/tests/workspace-context-resume-snapshots/offline-edit/replay.override.json Normal file
View File

@@ -0,0 +1,11 @@
[
{
"kind": "chunks",
"chunks": [
{ "type": "block-start", "index": 0, "blockType": "text" },
{ "type": "text-delta", "index": 0, "text": "RESUME_DONE" },
{ "type": "block-end", "index": 0, "block": { "type": "text", "text": "RESUME_DONE" } },
{ "type": "finish", "reason": { "kind": "stop" } }
]
}
]

22
examples/headless-agent/tests/workspace-context-resume-snapshots/offline-edit/session.expected.jsonl Normal file
View File

@@ -0,0 +1,22 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1}}
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Remember the workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":2,"time":0,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nOld workspace instruction.\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".git\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"AGENTS.md\",\"CLAUDE.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"ba65bdb41810f4d0129129dcbd6cadcd643c069d"}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"turn/end","seq":3,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"session/end-seed","seq":4,"time":0,"data":{}}
{"type":"agent/inbox/spliced","seq":5,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Acknowledge the current workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}
{"type":"turn/start","seq":6,"time":0,"data":{"turn":2}}
{"type":"agent/inbox/spliced","seq":7,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":8,"time":0,"data":{"turn":2,"step":1}}
{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Acknowledge the current workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":10,"time":0,"data":{"content":[{"type":"text","text":"<system-reminder>\nUpdated instructions from: AGENTS.md\n\nThis file changed after it was loaded. Use the following content instead of the previously loaded instructions from this file.\n\nNew workspace instruction after offline edit.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","changes":[{"action":"replace","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"d8375b516f158718bd3463bc8eb7ed42c011b29f"}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"session/title","seq":11,"time":0,"data":{"title":"Remember the workspace instruction.","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":12,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}"},"reason":"initial"}}
{"type":"request/context","seq":13,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"RESUME_DONE"}}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"RESUME_DONE"}}}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":18,"time":0,"data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"RESUME_DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"}},"sourceEventSeqs":[14,15,16,17],"surfaceOp":"append"}
{"type":"step/end","seq":19,"time":0,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":20,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}

22
examples/headless-agent/tests/workspace-context-resume-snapshots/precedence-change/session.expected.jsonl Normal file
View File

@@ -0,0 +1,22 @@
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}","delegationDepth":0}
{"type":"turn/start","seq":0,"time":0,"data":{"turn":1}}
{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Remember the workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":2,"time":0,"data":{"content":[{"type":"text","text":"<system-reminder>\nThe following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: CLAUDE.md\n\nOld CLAUDE rule.\n\nInstructions from: AGENTS.md\n\nOld AGENTS rule.\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".git\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"CLAUDE.md\",\"AGENTS.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000CLAUDE.md","path":"CLAUDE.md","digest":"b525eb8a6d3660b732dad4b0aff1b7c63ab32890"},{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"3113bd093ae91976207dcef7390bdc0b2bfcfa10"}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"turn/end","seq":3,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}
{"type":"session/end-seed","seq":4,"time":0,"data":{}}
{"type":"agent/inbox/spliced","seq":5,"time":0,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Acknowledge the current workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"}]}}
{"type":"turn/start","seq":6,"time":0,"data":{"turn":2}}
{"type":"agent/inbox/spliced","seq":7,"time":0,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
{"type":"step/start","seq":8,"time":0,"data":{"turn":2,"step":1}}
{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Acknowledge the current workspace instruction."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"user/message","seq":10,"time":0,"data":{"content":[{"type":"text","text":"<system-reminder>\nThis complete workspace instruction baseline replaces all earlier workspace instruction baselines. The following workspace instructions may be relevant to your work. Use them as guidance when applicable. More specific instructions take precedence over broader ones. They do not override system, developer, or direct user instructions.\n\nInstructions from: AGENTS.md\n\nCurrent AGENTS rule.\n\n\nInstructions from: CLAUDE.md\n\nCurrent CLAUDE rule.\n\n</system-reminder>"}],"source":{"kind":"workspace-instructions","form":"instructions","baseline":true,"baselineIdentity":"{\"projectRoot\":\"\",\"projectRootMarkers\":[\".git\"],\"maxBytes\":65536,\"maxSourceBytes\":1048576,\"instructionFileCandidates\":[\"AGENTS.md\",\"CLAUDE.md\"],\"localInstructionFileCandidates\":[\"AGENTS.local.md\",\"CLAUDE.local.md\"]}","changes":[{"action":"set","scope":".\u0000AGENTS.md","path":"AGENTS.md","digest":"7f53d2327837129750aef117f9754a001c46cf68"},{"action":"set","scope":".\u0000CLAUDE.md","path":"CLAUDE.md","digest":"5b1e9e3fd759eee6b43ceff899e47fb10c64701a"}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}
{"type":"session/title","seq":11,"time":0,"data":{"title":"Remember the workspace instruction.","messageSeqs":[1],"source":{"kind":"fallback"}}}
{"type":"request/header","seq":12,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}"},"reason":"initial"}}
{"type":"request/context","seq":13,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":0,"text":"RESUME_DONE"}}}
{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"RESUME_DONE"}}}}
{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
{"type":"assistant/message","seq":18,"time":0,"data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"RESUME_DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"}},"sourceEventSeqs":[14,15,16,17],"surfaceOp":"append"}
{"type":"step/end","seq":19,"time":0,"data":{"turn":2,"step":1}}
{"type":"turn/end","seq":20,"time":0,"data":{"turn":2,"reason":{"kind":"completed"}}}

233
examples/headless-agent/tests/workspace-context-resume.snapshot.ts Normal file
View File

@@ -0,0 +1,233 @@
/**
* Assembled-app regression for persisted workspace-instruction resume state.
* @module workspace-context-resume-snapshot
*/
import { createHash } from 'node:crypto'
import { mkdir, readFile, readdir, writeFile } from 'node:fs/promises'
import { dirname, join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import { normalizeSessionLog, scrubRequestHeaders, type NormalizeContext } from '@deepseek-ai/dsh-acp-snapshot'
import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke'
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import SessionStore, {
SESSION_FORMAT_VERSION,
SessionId,
type SessionEvent,
type SessionHeader,
} from '@deepseek-ai/dsh-session'
import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl'
import { renderWorkspaceContext } from '@deepseek-ai/dsh-workspace-context'
import { resolveConfig, workspaceBaselineIdentity } from '@deepseek-ai/dsh-workspace-context/src/config.ts'
import { describe, expect, it } from 'vitest'
const fixtureDir = join(dirname(fileURLToPath(import.meta.url)), 'workspace-context-resume-snapshots/offline-edit')
const replayFixture = join(fixtureDir, 'replay.jsonl')
const replayOverride = join(fixtureDir, 'replay.override.json')
const sessionExpected = join(fixtureDir, 'session.expected.jsonl')
const precedenceExpected = join(dirname(fixtureDir), 'precedence-change/session.expected.jsonl')
const configPath = fileURLToPath(new URL('../workspace-context-resume.cordis.snapshot.yml', import.meta.url))
const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
const sessionId = SessionId('workspace-context-resume')
const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
const oldInstruction = 'Old workspace instruction.'
const newInstruction = 'New workspace instruction after offline edit.'
interface SeedBaselineOptions {
files?: Array<{ name: string; content: string }>
instructionFileCandidates?: string[]
}
async function seedVisibleBaseline(
root: string,
cwd: string,
options: SeedBaselineOptions = {},
): Promise<string> {
const ctx = new Context()
await ctx.plugin(SessionStore)
await ctx.plugin(SessionPersistenceJsonl, { root, compression: 'none' })
const meta: SessionHeader = {
version: SESSION_FORMAT_VERSION,
id: sessionId,
createdAt: 1,
cwd,
delegationDepth: 0,
}
const files = options.files ?? [{ name: 'AGENTS.md', content: oldInstruction }]
const baseline = renderWorkspaceContext(files.map(file => ({
absolutePath: join(cwd, file.name),
displayPath: file.name,
content: file.content,
})), { maxBytes: 65536 })
const config = resolveConfig({
dshHome: join(cwd, '.dsh'),
maxBytes: 65536,
...options.instructionFileCandidates === undefined
? {}
: { instructionFileCandidates: options.instructionFileCandidates },
})
const events: SessionEvent[] = [
{ type: 'turn/start', seq: 0, time: 10, data: { turn: 1 } },
{
type: 'user/message',
seq: 1,
time: 11,
data: createUserMessage({ content: [{ type: 'text', text: 'Remember the workspace instruction.' }], source: { kind: 'user' } }),
surfaceOp: 'append',
},
{
type: 'user/message',
seq: 2,
time: 12,
data: createUserMessage({
content: [{ type: 'text', text: baseline.text }],
source: {
kind: 'workspace-instructions',
form: 'instructions',
baseline: true,
baselineIdentity: workspaceBaselineIdentity(config, cwd, cwd),
changes: files.map(file => ({
action: 'set',
scope: `.\0${file.name}`,
path: file.name,
digest: createHash('sha1').update(file.content).digest('hex'),
})),
},
}),
surfaceOp: 'append',
},
{ type: 'turn/end', seq: 3, time: 13, data: { turn: 1, reason: { kind: 'completed' } } },
]
try {
await ctx.sessionPersistence.create(meta)
await ctx.sessionPersistence.append(sessionId, events)
const location = ctx.sessionPersistence.locate(meta)
if (location === undefined) throw new Error('JSONL backend did not locate the seeded session')
return location.path
} finally {
await ctx.fiber.dispose()
}
}
describe('workspace-context resume snapshot', () => {
it('appends an offline replacement without duplicating the visible baseline', async () => {
let cwd = ''
let sessionPath = ''
const result = await runLoaderSmoke({
label: 'workspace-context resume headless stream-json snapshot',
tempDirPrefix: 'dsh-workspace-context-resume-',
binScript,
configPath,
binArgs: ['--config', configPath, '--output-format', 'stream-json', 'Acknowledge the current workspace instruction.'],
tsconfigPath,
env: {
DSH_SNAPSHOT_FILE: replayFixture,
DSH_SNAPSHOT_OVERRIDE: replayOverride,
},
prepare: async (runCwd) => {
cwd = runCwd
await mkdir(join(runCwd, '.git'), { recursive: true })
await writeFile(join(runCwd, 'AGENTS.md'), `${newInstruction}\n`)
sessionPath = await seedVisibleBaseline(join(runCwd, '.sessions'), runCwd)
},
inspect: async () => {
const normalization: NormalizeContext = { sessionIds: [sessionId], cwd }
const session = scrubRequestHeaders(normalizeSessionLog(await readFile(sessionPath, 'utf8'), normalization))
if (refreshing) await writeFile(sessionExpected, session)
expect(session).toBe(await readFile(sessionExpected, 'utf8'))
const records = session.trimEnd().split('\n').map(line => JSON.parse(line) as {
type?: string
data?: {
source?: { kind?: string; baseline?: boolean; changes?: Array<Record<string, unknown>> }
content?: Array<{ type?: string; text?: string }>
}
})
const workspaceEvents = records.filter(record => record.type === 'user/message'
&& record.data?.source?.kind === 'workspace-instructions')
expect(workspaceEvents.filter(record => record.data?.source?.baseline === true)).toHaveLength(1)
expect(workspaceEvents.filter(record => record.data?.source?.baseline !== true)).toHaveLength(1)
expect(workspaceEvents.at(-1)?.data?.source?.changes).toMatchObject([{
action: 'replace', scope: '.\0AGENTS.md', path: 'AGENTS.md',
}])
expect(JSON.stringify(workspaceEvents.at(-1)?.data?.content)).toContain(newInstruction)
const files = await readdir(join(cwd, '.sessions'), { recursive: true })
expect(files.filter(file => file.endsWith('.jsonl'))).toHaveLength(1)
},
})
expect(result.stderr).toBe('')
const records = result.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record<string, unknown>)
expect(records.at(-1)).toMatchObject({
type: 'result',
sessionId,
output: 'RESUME_DONE',
})
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
it('supersedes an incompatible baseline when precedence changed offline', async () => {
let cwd = ''
let sessionPath = ''
const result = await runLoaderSmoke({
label: 'workspace-context precedence-change resume snapshot',
tempDirPrefix: 'dsh-workspace-context-precedence-',
binScript,
configPath,
binArgs: ['--config', configPath, '--output-format', 'stream-json', 'Acknowledge the current workspace instruction.'],
tsconfigPath,
env: {
DSH_SNAPSHOT_FILE: replayFixture,
DSH_SNAPSHOT_OVERRIDE: replayOverride,
},
prepare: async (runCwd) => {
cwd = runCwd
await mkdir(join(runCwd, '.git'), { recursive: true })
await writeFile(join(runCwd, 'AGENTS.md'), 'Current AGENTS rule.\n')
await writeFile(join(runCwd, 'CLAUDE.md'), 'Current CLAUDE rule.\n')
sessionPath = await seedVisibleBaseline(join(runCwd, '.sessions'), runCwd, {
files: [
{ name: 'CLAUDE.md', content: 'Old CLAUDE rule.' },
{ name: 'AGENTS.md', content: 'Old AGENTS rule.' },
],
instructionFileCandidates: ['CLAUDE.md', 'AGENTS.md'],
})
},
inspect: async () => {
const normalization: NormalizeContext = { sessionIds: [sessionId], cwd }
const session = scrubRequestHeaders(normalizeSessionLog(await readFile(sessionPath, 'utf8'), normalization))
if (refreshing) {
await mkdir(dirname(precedenceExpected), { recursive: true })
await writeFile(precedenceExpected, session)
}
expect(session).toBe(await readFile(precedenceExpected, 'utf8'))
const records = session.trimEnd().split('\n').map(line => JSON.parse(line) as {
type?: string
data?: {
source?: { kind?: string; baseline?: boolean }
content?: Array<{ type?: string; text?: string }>
}
})
const baselines = records.filter(record => record.type === 'user/message'
&& record.data?.source?.kind === 'workspace-instructions'
&& record.data.source.baseline === true)
expect(baselines).toHaveLength(2)
const replacement = JSON.stringify(baselines.at(-1)?.data?.content)
expect(replacement).toContain('replaces all earlier workspace instruction baselines')
expect(replacement.indexOf('Instructions from: AGENTS.md'))
.toBeLessThan(replacement.indexOf('Instructions from: CLAUDE.md'))
},
})
expect(result.stderr).toBe('')
expect(result.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record<string, unknown>).at(-1))
.toMatchObject({
type: 'result',
sessionId,
output: 'RESUME_DONE',
})
}, LOADER_SMOKE_TEST_TIMEOUT_MS)
})

37
examples/headless-agent/workspace-context-resume.cordis.snapshot.yml Normal file
View File

@@ -0,0 +1,37 @@
# Keyless real-Loader composition for workspace-instruction resume
# reconciliation. The test seeds one persisted baseline, changes AGENTS.md
# while the session is offline, then resumes through the public agent service.
- id: persistence
name: '@deepseek-ai/dsh-session-persistence-jsonl'
config:
root: './.sessions'
compression: none
- id: replay
name: '@deepseek-ai/dsh-llm-replay'
config:
file: !!js process.env.DSH_SNAPSHOT_FILE
overrideFile: !!js process.env.DSH_SNAPSHOT_OVERRIDE
- id: fs-local
name: '@deepseek-ai/dsh-fs-local'
config:
cwd: !!js process.cwd()
- id: agent
name: '@deepseek-ai/dsh-agent-spine-demo'
config:
agents: []
workspaceContext:
maxBytes: 65536
dshHome: !!js process.cwd() + '/.dsh'
skills:
enabled: false
toolBash: false
toolTasks: false
goals: false
# Await the persisted resume before the headless driver inspects root agents.
- id: resumed-agent
name: './tests/fixtures/workspace-context-resume-agent.ts'

2
examples/jsonrpc-agent/cordis.yml
View File

@@ -63,6 +63,8 @@
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
config:
allowParallelInProgress: true
- id: fs-local
name: '@deepseek-ai/dsh-fs-local'

2
examples/package.json
View File

@@ -21,6 +21,7 @@
"@deepseek-ai/dsh-code-runtime-worker": "workspace:*",
"@deepseek-ai/dsh-command-goal": "workspace:*",
"@deepseek-ai/dsh-commands": "workspace:*",
"@deepseek-ai/dsh-compact": "workspace:*",
"@deepseek-ai/dsh-compact-basic": "workspace:*",
"@deepseek-ai/dsh-compact-tool-result-prune": "workspace:*",
"@deepseek-ai/dsh-credentials-local": "workspace:*",
@@ -53,6 +54,7 @@
"@deepseek-ai/dsh-session": "workspace:*",
"@deepseek-ai/dsh-session-checkpoint-policy": "workspace:*",
"@deepseek-ai/dsh-session-persistence-jsonl": "workspace:*",
"@deepseek-ai/dsh-session-projection": "workspace:*",
"@deepseek-ai/dsh-session-query": "workspace:*",
"@deepseek-ai/dsh-session-query-sqlite": "workspace:*",
"@deepseek-ai/dsh-session-reference": "workspace:*",