Merge branch 'stack/agent-profiles-8-authoring' into stack/agent-profiles-9-rename

# Conflicts: # docs/config-catalog.md # docs/cordis-catalog/services.md # packages/core/tools/README.i18n.yaml # packages/core/tools/README.md # packages/core/tools/README.zh.md # packages/core/tools/src/index.ts
2026-08-07 13:57:02 +08:00
parent 6bd50ae637 90734c188e
commit 9b56349ba3
259 changed files with 8053 additions and 1530 deletions
--- a/examples/acp-agent/composition.md
+++ b/examples/acp-agent/composition.md
@@ -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` |
--- a/examples/acp-agent/cordis.yml
+++ b/examples/acp-agent/cordis.yml
@@ -80,6 +80,12 @@
    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`.
@@ -98,8 +104,8 @@

 # 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'

@@ -141,6 +147,8 @@
 # `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.
--- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
+++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md
@@ -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: ({
--- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json
+++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json
+++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md
+++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md
@@ -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: ({
--- a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json
+++ b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json
+++ b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json
+++ b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/subagent-continuable/tool-schemas.1.expected.json
+++ b/examples/acp-agent/tests/snapshots/subagent-continuable/tool-schemas.1.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/subagent-list-agents/tool-schemas.1.expected.json
+++ b/examples/acp-agent/tests/snapshots/subagent-list-agents/tool-schemas.1.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/subagent-report/tool-schemas.1.expected.json
+++ b/examples/acp-agent/tests/snapshots/subagent-report/tool-schemas.1.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json
+++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json
@@ -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": {
--- a/examples/acp-agent/tests/snapshots/todo-write/input.json
+++ b/examples/acp-agent/tests/snapshots/todo-write/input.json
@@ -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." }
  ]
 }
--- a/examples/acp-agent/tests/snapshots/todo-write/session.jsonl
+++ b/examples/acp-agent/tests/snapshots/todo-write/session.jsonl
@@ -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"}}}
--- a/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json
+++ b/examples/acp-agent/tests/snapshots/web-fetch/tool-schemas.expected.json
@@ -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": {
--- a/examples/headless-agent/composition.md
+++ b/examples/headless-agent/composition.md
@@ -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` |
--- a/examples/headless-agent/cordis.yml
+++ b/examples/headless-agent/cordis.yml
@@ -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.
--- a/examples/headless-agent/subagent-diagnostic.cordis.snapshot.yml
+++ b/examples/headless-agent/subagent-diagnostic.cordis.snapshot.yml
@@ -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'
--- a/examples/headless-agent/tests/fixtures/subagent-diagnostic-agent.ts
+++ b/examples/headless-agent/tests/fixtures/subagent-diagnostic-agent.ts
@@ -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')
+}
--- a/examples/headless-agent/tests/harness.ts
+++ b/examples/headless-agent/tests/harness.ts
@@ -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)
--- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
+++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
--- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
+++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
--- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
+++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl
--- a/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
+++ b/examples/headless-agent/tests/snapshots/pty-tools/session.jsonl
--- a/examples/headless-agent/tests/subagent-diagnostic-snapshots/descriptorless-child/parent.expected.jsonl
+++ b/examples/headless-agent/tests/subagent-diagnostic-snapshots/descriptorless-child/parent.expected.jsonl
@@ -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"}}}
--- a/examples/headless-agent/tests/subagent-diagnostic-snapshots/descriptorless-child/replay.override.json
+++ b/examples/headless-agent/tests/subagent-diagnostic-snapshots/descriptorless-child/replay.override.json
@@ -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"}}]}]
--- a/examples/headless-agent/tests/subagent-diagnostic.snapshot.ts
+++ b/examples/headless-agent/tests/subagent-diagnostic.snapshot.ts
@@ -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)
+})
--- a/examples/headless-agent/tests/todo-write.e2e.ts
+++ b/examples/headless-agent/tests/todo-write.e2e.ts
@@ -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)
--- a/examples/jsonrpc-agent/cordis.yml
+++ b/examples/jsonrpc-agent/cordis.yml
@@ -65,6 +65,8 @@

 - id: tool-todo
  name: '@deepseek-ai/dsh-tool-todo'
+  config:
+    allowParallelInProgress: true

 - id: fs-local
  name: '@deepseek-ai/dsh-fs-local'
--- a/examples/package.json
+++ b/examples/package.json
@@ -54,6 +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:*",
				`@@ -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"}}]}]