diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml index d021cfbab7..7d14cbe963 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md -2026-08-12-production-dsh-excludes-product-subagent-providers.md: 94cfe82d0aa42076f3c0723ed99a83a1e53e3724 -2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md: a9dbdcff748ea46dc84c1480e6e50a945219a5c7 +2026-08-12-production-dsh-excludes-product-subagent-providers.md: 53551ad06ce7b735620d605669ddb5ca2d20aef5 +2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md: a5ff017e2717dee326e8aaf7987ab8360452902f diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md index 94cfe82d0a..53551ad06c 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md @@ -16,7 +16,7 @@ The two Bundles remain independent. The Codex Bundle owns its `@deepseek-ai/dsh- ## Verification -Package tests pin each Bundle manifest, exported patch, exact self-provider row, and product-specific runtime dependency. Workspace validation discovers Bundle manifests by declaration rather than directory. Production-closure tests prove the default, Codex-only, and Claude-only dependency boundaries, while real Bundle-patch and Agent-Preset composition covers all four installed sets against all four tool sets and proves composition starts no product process. The base bundle test continues to reject both provider dependencies and configuration rows. +Package tests pin each Bundle manifest, published patch, exact self-provider row, and product-specific runtime dependency. Workspace validation derives each published patch from its Bundle declaration rather than a package catalog. Production-closure tests prove the default, Codex-only, and Claude-only dependency boundaries, while real Bundle-patch and Agent-Preset composition covers all four installed sets, the full tool-grant matrix on a Host with both providers, representative missing-provider cases, and zero product processes. The base bundle test continues to reject both provider dependencies and configuration rows. ## Alternatives considered diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md index a9dbdcff74..a5ff017e27 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md @@ -16,7 +16,7 @@ Status: implemented ## 验证 -包测试会固定每个 Bundle 的 manifest、导出的 patch、准确的自身提供方行以及产品专属运行时依赖。工作区验证会按 Bundle 声明发现 manifest，而非按目录发现。生产闭包测试证明默认、仅 Codex 与仅 Claude 三种依赖边界；真实 Bundle patch 与 Agent Preset 的组装会覆盖四种安装集合与四种工具集合的完整矩阵，并证明组装不会启动产品进程。base 组合包测试仍会拒绝这两个提供方依赖与配置行。 +包测试会固定每个 Bundle 的 manifest、发布 patch、准确的自身提供方行以及产品专属运行时依赖。工作区验证会从 Bundle 声明派生每个发布 patch，而非维护包目录。生产闭包测试证明默认、仅 Codex 与仅 Claude 三种依赖边界；真实 Bundle patch 与 Agent Preset 的组装会覆盖四种安装集合、同时安装两个提供方时的完整工具授权矩阵、缺失提供方的代表场景以及零产品进程。base 组合包测试仍会拒绝这两个提供方依赖与配置行。 ## 考虑过的替代方案 diff --git a/apps/cli/config/agent-presets/cordis/skills/editing-cordis-compositions/SKILL.md b/apps/cli/config/agent-presets/cordis/skills/editing-cordis-compositions/SKILL.md index 2eff9a9cce..68999a7ed6 100644 --- a/apps/cli/config/agent-presets/cordis/skills/editing-cordis-compositions/SKILL.md +++ b/apps/cli/config/agent-presets/cordis/skills/editing-cordis-compositions/SKILL.md @@ -154,7 +154,7 @@ Copy these disabled templates from a shipped full preset and remove `disabled` o maxDepth: provider-managed ``` -The two rows are independent. Leaving both disabled preserves the copied preset, enabling one exposes only an installed matching provider, and enabling both exposes the installed intersection. The host must already provide `codex` or `claude` on `PATH`; neither the Bundle nor the preset installs, authenticates, selects a model for, starts, or probes either product. +The two rows are independent. Leaving both disabled preserves the copied preset, enabling one exposes only an installed matching provider, and enabling both exposes the installed intersection. The host must already provide `codex` or `claude` on `PATH`; neither the Bundle nor the preset starts, authenticates, selects a model for, probes, or manages a host-level installation of either product. The Claude Code Bundle's Agent SDK dependency still carries its platform CLI payload, which production ignores in favor of the host's `claude`. ## What not to move into a preset diff --git a/apps/cli/reference/README.i18n.yaml b/apps/cli/reference/README.i18n.yaml index 5b97a26ad2..6d2f457b01 100644 --- a/apps/cli/reference/README.i18n.yaml +++ b/apps/cli/reference/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write apps/cli/reference/README.md -README.md: c220fd68cb0d79d2060e46a33d8af54c249a9c68 -README.zh.md: 15f026c79665ae2978bdfd65c321b05c10cc06e4 +README.md: dcbe28fab05031b2f176e5a20df77967d2d97885 +README.zh.md: 0cd7216615a58b206b441096292e1a19a73a01b3 diff --git a/apps/cli/reference/README.md b/apps/cli/reference/README.md index c220fd68cb..dcbe28fab0 100644 --- a/apps/cli/reference/README.md +++ b/apps/cli/reference/README.md @@ -52,7 +52,7 @@ dsh plugin --profile remove @deepseek-ai/dsh-subagent-codex dsh plugin --profile remove @deepseek-ai/dsh-subagent-claude-code ``` -The successful pnpm operation changes the Profile manifest and Bundle list on disk; a running Profile keeps the Bundle set from its current start. Restart that Profile after adding, removing, or updating a Bundle. This startup boundary applies to Bundle membership, while ordinary edits to the Profile or home `cordis.patch.yml` retain their existing hot-reload behavior. On the next start, each installed product Bundle registers only its dormant Host provider and does not start, install, authenticate, or configure the native product. Full Agent Presets keep both product tool rows disabled, so a copied Preset must separately enable the matching row before a new Agent can see that tool. Installing one provider never installs the other product package; the default dsh dependency closure includes neither provider nor the Claude Agent SDK. +The successful pnpm operation changes the Profile manifest and Bundle list on disk; a running Profile keeps the Bundle set from its current start. Restart that Profile after adding, removing, or updating a Bundle. This startup boundary applies to Bundle membership, while ordinary edits to the Profile or home `cordis.patch.yml` retain their existing hot-reload behavior. On the next start, each installed product Bundle registers only its dormant Host provider and does not start, authenticate, configure, or manage a host-level installation of the native product. The Claude Code Bundle's Agent SDK dependency still carries its platform CLI payload, which production ignores in favor of the host's `claude`. Full Agent Presets keep both product tool rows disabled, so a copied Preset must separately enable the matching row before a new Agent can see that tool. Installing one provider never installs the other product package; the default dsh dependency closure includes neither provider nor the Claude Agent SDK. ```sh dsh plugin --profile tui add github:deepseek-harness/turtle-ui diff --git a/apps/cli/reference/README.zh.md b/apps/cli/reference/README.zh.md index 15f026c796..0cd7216615 100644 --- a/apps/cli/reference/README.zh.md +++ b/apps/cli/reference/README.zh.md @@ -52,7 +52,7 @@ dsh plugin --profile remove @deepseek-ai/dsh-subagent-codex dsh plugin --profile remove @deepseek-ai/dsh-subagent-claude-code ``` -pnpm 操作成功后只会改变磁盘上的 Profile manifest 与 Bundle 列表；正在运行的 Profile 会保留本次启动时的 Bundle 集合。添加、移除或更新 Bundle 后须重启该 Profile。这个启动边界只适用于 Bundle 成员变化，Profile 或 home 中普通 `cordis.patch.yml` 的编辑仍保留既有热重载行为。下一次启动时，每个已安装的产品 Bundle 只注册自己的休眠 Host provider，不会启动、安装、认证或配置原生产品。完整 Agent Preset 中的两个产品工具行仍默认禁用，因此还须在复制出的 Preset 中单独启用对应行，新 Agent 才能看到该工具。只安装一个 provider 不会安装另一个产品包；默认 dsh 依赖闭包不包含任一 provider，也不包含 Claude Agent SDK。 +pnpm 操作成功后只会改变磁盘上的 Profile manifest 与 Bundle 列表；正在运行的 Profile 会保留本次启动时的 Bundle 集合。添加、移除或更新 Bundle 后须重启该 Profile。这个启动边界只适用于 Bundle 成员变化，Profile 或 home 中普通 `cordis.patch.yml` 的编辑仍保留既有热重载行为。下一次启动时，每个已安装的产品 Bundle 只注册自己的休眠 Host provider，不会启动、认证、配置原生产品，也不会管理宿主级产品安装。Claude Code Bundle 的 Agent SDK 依赖仍携带平台 CLI 载荷，但生产环境会忽略该载荷并使用宿主提供的 `claude`。完整 Agent Preset 中的两个产品工具行仍默认禁用，因此还须在复制出的 Preset 中单独启用对应行，新 Agent 才能看到该工具。只安装一个 provider 不会安装另一个产品包；默认 dsh 依赖闭包不包含任一 provider，也不包含 Claude Agent SDK。 ```sh dsh plugin --profile tui add github:deepseek-harness/turtle-ui diff --git a/apps/cli/tests/web-agent-presets.e2e.ts b/apps/cli/tests/web-agent-presets.e2e.ts index 5da62e0aba..77185270e9 100644 --- a/apps/cli/tests/web-agent-presets.e2e.ts +++ b/apps/cli/tests/web-agent-presets.e2e.ts @@ -437,6 +437,7 @@ describe('the shipped Web composition', () => { describe('product subagent Bundle and user-preset intersection', () => { const presetIds = ['products-none', 'products-codex', 'products-claude', 'products-both'] as const type Product = 'codex' | 'claude-code' + type PresetId = typeof presetIds[number] async function bootProducts(installed: readonly Product[]): Promise { const root = await mkdtemp(join(tmpdir(), 'dsh-product-presets-')) @@ -477,20 +478,20 @@ describe('product subagent Bundle and user-preset intersection', () => { } it('composes the intersection of installed Bundles and enabled preset rows', async () => { - const enabledByPreset = new Map([ - ['products-none', []], - ['products-codex', ['codex']], - ['products-claude', ['claude-code']], - ['products-both', ['codex', 'claude-code']], - ]) - const installations: Product[][] = [ - [], - ['codex'], - ['claude-code'], - ['codex', 'claude-code'], + const enabledByPreset: Record = { + 'products-none': [], + 'products-codex': ['codex'], + 'products-claude': ['claude-code'], + 'products-both': ['codex', 'claude-code'], + } + const scenarios: Array<{ installed: Product[]; presets: readonly PresetId[] }> = [ + { installed: [], presets: ['products-both'] }, + { installed: ['codex'], presets: ['products-both'] }, + { installed: ['claude-code'], presets: ['products-both'] }, + { installed: ['codex', 'claude-code'], presets: presetIds }, ] - for (const installed of installations) { + for (const { installed, presets } of scenarios) { const productCtx = await bootProducts(installed) const spawn = vi.spyOn(productCtx.subprocess, 'spawn') try { @@ -498,7 +499,8 @@ describe('product subagent Bundle and user-preset intersection', () => { .filter(name => name === 'codex' || name === 'claude-code') .sort()) .toEqual([...installed].sort()) - for (const [id, enabled] of enabledByPreset) { + for (const id of presets) { + const enabled = enabledByPreset[id] const handle = await productCtx.agents.create({ sessionId: SessionId(`preset-${id}-${installed.join('-') || 'none'}-${randomUUID()}`), setup: agentCtx => productCtx.agentPresets.mount(agentCtx, id).then(() => undefined), diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index db4a2b5d2f..19bb86c298 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -1,7 +1,7 @@ import { fileURLToPath } from 'node:url' import { readFileSync } from 'node:fs' import { spawnSync } from 'node:child_process' -import { mkdir, utimes, writeFile } from 'node:fs/promises' +import { copyFile, mkdir, utimes, writeFile } from 'node:fs/promises' import { dirname, join } from 'node:path' import { homedir } from 'node:os' import { expect, it } from 'vitest' @@ -28,6 +28,10 @@ const AGENT = { configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } +const EDITING_CORDIS_SKILL = fileURLToPath(new URL( + '../../../apps/cli/config/agent-presets/cordis/skills/editing-cordis-compositions/SKILL.md', + import.meta.url, +)) // The Code Mode overlay configs (include-patched variants of cordis.yml; the // replay swap resolves each one's sibling `*cordis.snapshot.yml`). @@ -69,6 +73,12 @@ const FS_DIFF_BOUND_CONFIG = fileURLToPath(new URL('./fs-diff-bound.cordis.yml', const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') const PACKED_CHUNKS_SOURCE = 'hook-cc-pretool-deny' +async function prepareEditingCordisSkillWorkspace(cwd: string): Promise { + const target = join(cwd, '.dsh', 'skills', 'editing-cordis-compositions', 'SKILL.md') + await mkdir(dirname(target), { recursive: true }) + await copyFile(EDITING_CORDIS_SKILL, target) +} + async function prepareDelimiterPathWorkspace(cwd: string): Promise { const dir = join(cwd, 'scope') await mkdir(dir, { recursive: true }) @@ -280,6 +290,7 @@ const SCENARIOS: Scenario[] = [ headerClass: 'skill', systemPromptSource: 'text-turn', toolSchemasSource: 'text-turn', + prepareWorkspace: prepareEditingCordisSkillWorkspace, }, { name: 'lsp-definition', hasModelTurn: true, recorded: false, pinsHeader: true, headerClass: 'lsp', configPath: LSP_CONFIG }, // web_fetch markdown rendering end to end: the overlay's loopback fixture diff --git a/examples/acp-agent/tests/snapshots/skill-load/input.json b/examples/acp-agent/tests/snapshots/skill-load/input.json index a5ee78bff6..48235fc667 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/input.json +++ b/examples/acp-agent/tests/snapshots/skill-load/input.json @@ -2,6 +2,6 @@ "steps": [ { "op": "initialize" }, { "op": "newSession" }, - { "op": "prompt", "text": "Load the snapshot-skill skill with the skill tool, then reply DONE." } + { "op": "prompt", "text": "Load the editing-cordis-compositions skill with the skill tool, then reply DONE." } ] } diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index ec369b492a..0f9608ae4c 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -1,25 +1,25 @@ {"type":"session","version":0,"id":"9eb4181f-2d05-49d3-98fc-3711fe2f5664","createdAt":1783654655599,"cwd":"{{cwd}}","delegationDepth":0} -{"type":"agent/inbox/spliced","seq":0,"time":1785498773710,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"0ca31b92-27ac-451d-98d3-d1e5f605454b"}]}} +{"type":"agent/inbox/spliced","seq":0,"time":1785498773710,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Load the editing-cordis-compositions skill with the skill tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"0ca31b92-27ac-451d-98d3-d1e5f605454b"}]}} {"type":"turn/start","seq":1,"time":1785821378605,"data":{"turn":1}} {"type":"agent/inbox/spliced","seq":2,"time":1785821378605,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","seq":3,"time":1785498773754,"data":{"turn":1,"step":1}} -{"type":"user/message","seq":4,"time":1785498773754,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"0ca31b92-27ac-451d-98d3-d1e5f605454b"},"surfaceOp":"append"} +{"type":"user/message","seq":4,"time":1785498773754,"data":{"content":[{"type":"text","text":"Load the editing-cordis-compositions skill with the skill tool, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"0ca31b92-27ac-451d-98d3-d1e5f605454b"},"surfaceOp":"append"} {"type":"user/message","seq":5,"time":1785498773755,"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":"3fc7e2f8-90fc-496c-b516-700cef1d86f1"},"surfaceOp":"append"} -{"type":"user/message","seq":6,"time":1785730426818,"data":{"content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `model-only-skill`: Prove user-disabled skills remain available to the model.\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n"}],"source":{"kind":"skill-catalog","form":"catalog","entries":[{"name":"model-only-skill","description":"Prove user-disabled skills remain available to the model."},{"name":"snapshot-skill","description":"Exercise project skill discovery and loading in snapshot tests."}]},"role":"user","id":"60880315-9799-44c8-8a99-e6fe9ee5bdc5"},"surfaceOp":"append"} -{"type":"session/title","seq":7,"time":1785730426818,"data":{"title":"Load the snapshot-skill skill with","messageSeqs":[4],"source":{"kind":"fallback"}}} +{"type":"user/message","seq":6,"time":1785730426818,"data":{"content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `editing-cordis-compositions`: Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing.\n- `model-only-skill`: Prove user-disabled skills remain available to the model.\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n"}],"source":{"kind":"skill-catalog","form":"catalog","entries":[{"name":"editing-cordis-compositions","description":"Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted but contributed nothing."},{"name":"model-only-skill","description":"Prove user-disabled skills remain available to the model."},{"name":"snapshot-skill","description":"Exercise project skill discovery and loading in snapshot tests."}]},"role":"user","id":"59831057-0914-4e8b-967d-ef7dc850a62a"},"surfaceOp":"append"} +{"type":"session/title","seq":7,"time":1785730426818,"data":{"title":"Load the editing-cordis-compositions ski","messageSeqs":[4],"source":{"kind":"fallback"}}} {"type":"request/header","seq":8,"time":1785498773756,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","seq":9,"time":1785730426819,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"assistant/chunk","seq":10,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":11,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":13,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skill_load","name":"skill","argumentsDelta":"{\"name\":\"snapshot-skill\"}"}}} +{"type":"assistant/chunk","seq":13,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skill_load","name":"skill","argumentsDelta":"{\"name\":\"editing-cordis-compositions\"}"}}} {"type":"assistant/chunk","seq":14,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Load the requested skill."}}}} -{"type":"assistant/chunk","seq":15,"time":1784903324935,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}}} +{"type":"assistant/chunk","seq":15,"time":1784903324935,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"editing-cordis-compositions\"}"}}}} {"type":"assistant/chunk","seq":16,"time":1785498773765,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}}}} {"type":"assistant/chunk","seq":17,"time":1785730426828,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":18,"time":1785730426828,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"3fd7a47e-84c9-4d31-aa95-9939671ba0a5"},"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[10,11,12,13,14,15,16,17],"surfaceOp":"append"} -{"type":"tool/call","seq":19,"time":1785730426828,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}} -{"type":"tool/result","seq":20,"time":1785730426838,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_skill_load"},"content":[{"type":"tool-result","toolCallId":"call_skill_load","content":[{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}],"isError":false}],"role":"user","id":"1609c2f6-3bc5-4ade-95dd-29e7f7565987"}},"sourceEventSeqs":[19],"surfaceOp":"append"} +{"type":"assistant/message","seq":18,"time":1785730426828,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"editing-cordis-compositions\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"3fd7a47e-84c9-4d31-aa95-9939671ba0a5"},"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[10,11,12,13,14,15,16,17],"surfaceOp":"append"} +{"type":"tool/call","seq":19,"time":1785730426828,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"editing-cordis-compositions\"}"}} +{"type":"tool/result","seq":20,"time":1785730426838,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_skill_load"},"content":[{"type":"tool-result","toolCallId":"call_skill_load","content":[{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/editing-cordis-compositions\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\n# Editing Cordis compositions\n\nEvery capability in this harness is a plugin row in a `cordis.yml`. There is no separate configuration language: changing what an agent can do means changing which rows are composed for it.\n\n## Off-limits\n\n**Never edit, delete, or overwrite a preset that ships with the deployment** — the `agent-presets` directory beside the deployment's own config, which supplies `standard`, `code`, `minimal`, and `cordis`. Never escalate the sandbox to reach it, even when a change there looks quicker. An upgrade overwrites that install, and corrupting `cordis` disables preset authoring itself. Reading a shipped composition is the intended way to start; writing to one is not, and neither is editing the host composition to work around a preset limitation.\n\nTo change what a shipped preset does, copy it and edit the copy. Locally authored presets under the user root are yours to create, edit, and delete.\n\n## Decide the plane first\n\nTwo planes, and the choice is not about how \"agent-related\" something feels — it is about whether the thing must be shared.\n\n**Host composition.** The registries themselves (`tools`, `systemPrompt`, `agents`, `agent-loop`, `sessions`), anything crossing sessions (persistence, session query, storage, settings, credentials, telemetry), the sandbox and approval stack, the model route, and the subagent registry with its spawn/fork backends. One instance for the process.\n\n**Agent preset.** What one session contributes to those registries: its tool plugins, its persona and prompt sections, its compaction policy. One instance per session, mounted under that session's scope and unwound with it.\n\n**A service with a consumer outside the agent plane cannot move into a preset.** `subagents` is the worked example: the registry answers cross-session queries for the host api-proxy, so a per-session copy both starves that host row — it waits forever for a service nothing provides — and collides on the second session, since a provider name registers once. The preset contributes the delegation *tools*; the registry and its backends stay host-side.\n\nA preset is a directory holding one `agent.cordis.yml`, optionally beside a `preset.yml` carrying display metadata — `name` and `description` (and, for shipped presets, a roster `order`). Write the metadata too: a preset without it shows up in every picker as its bare directory name.\n\nLocally authored presets live one directory per preset under `${DSH_HOME:-$HOME/.dsh}/.agent-presets/`, and the shipped set sits beside the deployment's own config. Use those when the user asks where to look. A deployment can configure other roots, so the path you read or edit comes from `list()` or `resolve()` — which is also where `copy()` reports what it just created.\n\n## The roster service\n\n`ctx.agentPresets` owns discovery, authoring, and mounting. You reach it by mounting a temporary plugin that injects it and registers a tool for yourself — `cordis_mount` returns only the mount acknowledgement, so a registered tool is how a service answer gets back to you, and it becomes callable on your next step.\n\nRead `cordis_inspect what:\"api\" name:\"agentPresets\"` for the current signatures before writing the code. What this skill relies on:\n\n- `list()` — every preset with its `id`, `trust` (`system` for the shipped set, `user` for authored ones), and the absolute `path` of its composition file. This is how you locate any composition without knowing the install layout; the directory is that path's parent.\n- `read(id)` — one preset's composition text, without a file tool or a path.\n- `copy(from, id, name?)` — the only authoring write (see below).\n- `standingKeyFor(id)` — mount-validate one preset (see below).\n\n```js\nreturn {\n name: 'preset-tools',\n inject: ['agentPresets', 'tools'],\n apply(ctx) {\n harness.registerTool(ctx, harness.defineTool({\n name: 'preset_check',\n description: 'Mount-validate one preset by id.',\n parameters: { id: { type: 'string', required: true } },\n output: { schema: { type: 'string' }, render(_a, v) { return [{ type: 'text', text: v }] } },\n async execute(args) {\n try {\n await ctx.agentPresets.standingKeyFor(args.id)\n return 'mounted OK'\n } catch (error) {\n return error.message\n }\n },\n }))\n },\n}\n```\n\nUnmount the plugin with `cordis_unmount` when you are done; it is a probe, not a capability to leave behind.\n\n## Authoring a preset\n\n1. **Start from a copy.** `copy(from, id, name)` copies a whole preset directory into the user root — composition, metadata, skill directories, assets. It validates the id against `[a-z0-9][a-z0-9-]*` (it becomes the directory name, so no leading hyphen), refuses an id any root already supplies, rolls a failed copy back, and rewrites the copy's `preset.yml` to keep the source's description while dropping its name and roster `order`. Prefer it over a shell copy: it needs no sandbox escalation, it lands the copy in whichever root this deployment made writable, and the copy is exactly as loadable as its source. `resolve(id)` then names the file it created — that path, not a guessed one, is what the following edits target. `standard` is the full coding agent and the usual source.\n2. **Expect the file sandbox on every edit after the copy.** The user preset root lies outside the session workspace, so under the default `workspace-write` policy the first write there is denied. Only writes are: reading any composition by absolute path needs no escalation. Retry that exact command once with `sandbox_permissions` escalation and a short justification — the user sees and approves it. Batch your writes (one heredoc per file) rather than escalating many small commands. `copy()` itself runs host-side and needs none of this; the edits do.\n3. **Write the copy's `description`** in `preset.yml`, and its `name` if you passed none to `copy()`.\n4. **Edit `agent.cordis.yml`** row by row, keeping the plane rule and the realm rule.\n5. **Mount-validate the result**, then hand off to the user for a real session — both under *Verifying a change*.\n\nA composition written from scratch usually forgets a group realm or a consumer row; a copy starts loadable.\n\n## The rule that catches people\n\n**A row that publishes a service may not sit loose in a preset.** Registering a service without an isolate realm puts it in the process-global realm, so the second session mounting that preset collides with the first. The mount rejects it rather than letting the collision surface later.\n\nWhether a row publishes a service is not visible from its name, and package READMEs are absent from an installed deployment. Read it off the live runtime instead: `cordis_inspect what:\"services\"` lists every service with the fiber that owns it, so a service attributed to a fiber other than the row you are adding is one that row consumes rather than provides. For a row not in your current composition, mount-validate and read the rejection — it names the offending service.\n\nWhen a preset genuinely owns a service, wrap the provider **and every consumer that reaches it** in one group carrying an `isolate` realm. The shipped `standard` composition does this for `workflows`, which nothing outside an agent reads — its `delegation` group, with the delegation tools omitted here:\n\n```yaml\n- id: delegation\n name: cordis:group\n group: true\n isolate:\n workflows: true\n config:\n - id: workflow-worker-thread\n name: '@deepseek-ai/dsh-workflow-worker-thread'\n config:\n provider: spawn\n - id: tool-workflow\n name: '@deepseek-ai/dsh-tool-workflow'\n```\n\n`true` means a realm private to each mounting session. A string label instead joins subtrees into one shared realm; `provide()` still throws on the second registration under that symbol, so a label does not pool instances and is not what a preset needs.\n\nA consumer left outside the group resolves the host's registry, which the preset did not populate, and then contributes nothing. Mount-validation catches that as a row that never activated.\n\nRealms are for services a preset owns, not for every group. A host capability the preset only consumes must stay outside a realm, or the row cannot resolve it: `tool-bash`, `tool-jobs`, and `tool-goal` publish nothing and sit loose in `standard`, which explains in comments which host instance each one resolves and why a realm would break it. Wrapping a consumer row in a realm of its own is the same error as leaving one outside its provider's realm.\n\n## Verifying a change\n\n**`standingKeyFor(id)` is the check.** It composes the preset's plugin subtree for real — the same mount a session start performs, minus the agent — and rejects the four ways a composition fails:\n\n- a row whose package does not resolve (`Cannot find package …`);\n- a row whose config is invalid (`invalid config: $. missing required value`);\n- a row that never activated (`N row(s) did not activate: : waiting for `);\n- a service published into the root realm, which arrives as one of two messages. A name the host does not supply lands in the root realm and the mount audit rejects it: `row(s) published process-global service(s) []; a preset service must sit behind an isolate realm or move to the host composition` — this is the shape a preset's own forgotten realm takes. A name the host already supplies collides before the audit: `service \"\" has been registered at `. Both name the offending service.\n\nIt returns normally when the composition mounts. Run it as the final check on a finished edit rather than after every line: a successful mount installs a standing generation that lives until the process exits, while a failed one disposes its subtree and leaves nothing behind.\n\n**Do not treat the roster's `broken` field as validation.** `list()` reports `broken` from a shape check — the file parses in the loader's YAML dialect and holds named rows — which every failure above passes. It catches a damaged file, not an unusable composition.\n\n`cordis_inspect` reports THIS session's composition, so it confirms what a row does in the runtime you are already in, never what your new preset will do.\n\nAfter a clean mount-validation, ask the user to start a session on the new preset and confirm the tool list; the preset decides tool schemas and prompt sections, and only a real session shows the agent that composition produces.\n\n`cordis_mount` evaluates JavaScript against the live runtime and disappears on restart. It is for probing, not for shipping a capability: a capability belongs in a composition file.\n\n## Native product subagents\n\nCodex and Claude Code providers are optional Profile Bundles. Install only the products the Profile needs, then restart the Profile so its Host registers those providers:\n\n```sh\ndsh plugin --profile add @deepseek-ai/dsh-subagent-codex\ndsh plugin --profile add @deepseek-ai/dsh-subagent-claude-code\n```\n\nThe Bundle owns Host availability; the preset separately grants one Agent its ordinary delegation tool. Never move a product provider into the preset and never add a product-specific settings field. Removing either package with `dsh plugin --profile remove ` withdraws only that provider on the next Profile start.\n\nCopy these disabled templates from a shipped full preset and remove `disabled` only for the products the user requested:\n\n```yaml\n- id: tool-subagent-codex\n name: '@deepseek-ai/dsh-tool-subagent'\n disabled: true\n config:\n provider: codex\n toolName: subagent_codex\n enableRunInBackground: false\n maxDepth: provider-managed\n\n- id: tool-subagent-claude-code\n name: '@deepseek-ai/dsh-tool-subagent'\n disabled: true\n config:\n provider: claude-code\n toolName: subagent_claude_code\n enableRunInBackground: false\n maxDepth: provider-managed\n```\n\nThe two rows are independent. Leaving both disabled preserves the copied preset, enabling one exposes only an installed matching provider, and enabling both exposes the installed intersection. The host must already provide `codex` or `claude` on `PATH`; neither the Bundle nor the preset starts, authenticates, selects a model for, probes, or manages a host-level installation of either product. The Claude Code Bundle's Agent SDK dependency still carries its platform CLI payload, which production ignores in favor of the host's `claude`.\n\n## What not to move into a preset\n\n`agent-loop` registers the one agent factory and throws on a second. The registries own the per-session layering and cannot themselves be per-session. Session persistence must stay host-side or the session list fragments. The sandbox, approval, and permission rows are a deliberate boundary: a preset is exactly as privileged as the plugins it names, so letting one relax its own confinement would defeat the confinement.\n\n"}],"isError":false}],"role":"user","id":"fa340fc0-3edc-4a61-92b2-2c4d70c4b6d7"}},"sourceEventSeqs":[19],"surfaceOp":"append"} {"type":"step/end","seq":21,"time":1785730426838,"data":{"turn":1,"step":1}} {"type":"step/start","seq":22,"time":1785730426848,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":23,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/packages/subagent/subagent-claude-code/package.json b/packages/subagent/subagent-claude-code/package.json index 473a37e3d8..e62b68ef3d 100644 --- a/packages/subagent/subagent-claude-code/package.json +++ b/packages/subagent/subagent-claude-code/package.json @@ -22,7 +22,6 @@ "types": "./lib/types/invariant.d.ts", "default": "./lib/invariant.js" }, - "./cordis.patch.yml": "./cordis.patch.yml", "./src/*": "./src/*", "./package.json": "./package.json" }, diff --git a/packages/subagent/subagent-claude-code/tests/subagent-claude-code.spec.ts b/packages/subagent/subagent-claude-code/tests/subagent-claude-code.spec.ts index 889e248983..0fb0e55a98 100644 --- a/packages/subagent/subagent-claude-code/tests/subagent-claude-code.spec.ts +++ b/packages/subagent/subagent-claude-code/tests/subagent-claude-code.spec.ts @@ -290,12 +290,10 @@ describe('task admission and package contracts', () => { const root = fileURLToPath(new URL('..', import.meta.url)) const manifest = JSON.parse(readFileSync(resolve(root, 'package.json'), 'utf8')) as { dependencies?: Record - exports?: Record files?: string[] dsh?: { bundle?: { patch?: string } } } expect(manifest.dsh?.bundle?.patch).toBe('./cordis.patch.yml') - expect(manifest.exports?.['./cordis.patch.yml']).toBe('./cordis.patch.yml') expect(manifest.files).toContain('cordis.patch.yml') expect(manifest.dependencies).toHaveProperty('@anthropic-ai/claude-agent-sdk') expect(manifest.dependencies).not.toHaveProperty('@deepseek-ai/dsh-subagent-codex') diff --git a/packages/subagent/subagent-codex/package.json b/packages/subagent/subagent-codex/package.json index 246f59348e..fd4a3c3611 100644 --- a/packages/subagent/subagent-codex/package.json +++ b/packages/subagent/subagent-codex/package.json @@ -22,7 +22,6 @@ "types": "./lib/types/invariant.d.ts", "default": "./lib/invariant.js" }, - "./cordis.patch.yml": "./cordis.patch.yml", "./src/*": "./src/*", "./package.json": "./package.json" }, diff --git a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts index 05207c419a..4fa001a9f4 100644 --- a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts +++ b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts @@ -269,12 +269,10 @@ describe('task admission and package contracts', () => { const manifest = JSON.parse(readFileSync(resolve(root, 'package.json'), 'utf8')) as { dependencies?: Record peerDependencies?: Record - exports?: Record files?: string[] dsh?: { bundle?: { patch?: string } } } expect(manifest.dsh?.bundle?.patch).toBe('./cordis.patch.yml') - expect(manifest.exports?.['./cordis.patch.yml']).toBe('./cordis.patch.yml') expect(manifest.files).toContain('cordis.patch.yml') expect(manifest.dependencies).toHaveProperty('@deepseek-ai/dsh-sdk-protocol') expect(manifest.peerDependencies).not.toHaveProperty('@deepseek-ai/dsh-sdk-protocol') diff --git a/scripts/check-workspace-constraints.ts b/scripts/check-workspace-constraints.ts index d55ad16401..e11672a055 100644 --- a/scripts/check-workspace-constraints.ts +++ b/scripts/check-workspace-constraints.ts @@ -84,6 +84,11 @@ interface PackageManifest { devDependencies?: Record dependencies?: Record optionalDependencies?: Record + dsh?: { + bundle?: { + patch?: string + } + } } /** One workspace manifest and its repo-relative path. */ @@ -131,12 +136,6 @@ function workspaceManifests(): WorkspaceManifest[] { } const packageFileExtras: Readonly> = { - // Profile bundles publish their dsh.bundle.patch layer beside the lib. - '@deepseek-ai/dsh-base': ['cordis.patch.yml'], - '@deepseek-ai/dsh-web-app': ['cordis.patch.yml'], - '@deepseek-ai/dsh-headless': ['cordis.patch.yml'], - '@deepseek-ai/dsh-subagent-codex': ['cordis.patch.yml'], - '@deepseek-ai/dsh-subagent-claude-code': ['cordis.patch.yml'], '@deepseek-ai/dsh-client-ui-theme': ['lib/styles'], // The Python runtime uses a distinct closed-resolution bin; the public CLI // keeps config-owned bare-package resolution through lib/bin.js. @@ -154,7 +153,12 @@ function sameStringList(actual: readonly string[] | undefined, expected: readonl } function expectedDshPackageFiles(manifest: PackageManifest): readonly string[] { - const extras = manifest.name ? packageFileExtras[manifest.name] ?? [] : [] + const declaredPatch = manifest.dsh?.bundle?.patch + const bundleFiles = declaredPatch === undefined ? [] : [declaredPatch.replace(/^\.\//, '')] + const extras = [ + ...bundleFiles, + ...(manifest.name ? packageFileExtras[manifest.name] ?? [] : []), + ] return [ 'lib/index.js', // Every package publishes its invariant ownership companion as a separate