35 lines
22 KiB
JSON
35 lines
22 KiB
JSON
{"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 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 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":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\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</available_skills>\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 <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n</system-reminder>"}],"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\":\"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\":\"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\":\"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":"<skill_content name=\"editing-cordis-compositions\">\n<skill_resources>\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</skill_resources>\n\n<skill_instructions>\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: $.<field> missing required value`);\n- a row that never activated (`N row(s) did not activate: <id>: waiting for <service>`);\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) [<name>]; 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 \"<name>\" has been registered at <Owner>`. 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\nThe Claude Code provider is an optional Profile Bundle. Install it only in Profiles that need it, then restart the Profile so its Host registers the provider:\n\n```sh\ndsh plugin --profile <name> add @deepseek-ai/dsh-subagent-claude-code\ndsh plugin --profile <name> remove @deepseek-ai/dsh-subagent-claude-code\n```\n\nThe Bundle owns Claude Code 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 the package withdraws the 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. The Claude Code row becomes available only when its Bundle is installed; the Codex row still requires a deployment whose Host composition registers that provider and whose `PATH` supplies `codex`. The Claude Code Bundle installs and exclusively uses the matching platform CLI selected by its pinned Agent SDK; it does not inspect or fall back to a host `claude`, and a missing optional payload fails the first delegation. Neither installing the Claude Code Bundle nor composing either preset row starts a product, authenticates an account, selects a model, probes credentials, or manages native product settings.\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</skill_instructions>\n</skill_content>"}],"isError":false}],"role":"user","id":"487d970e-9e85-4637-8b56-788e8cc00362"}},"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"}}}
|
|
{"type":"assistant/chunk","seq":24,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The skill is loaded."}}}
|
|
{"type":"assistant/chunk","seq":25,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
|
{"type":"assistant/chunk","seq":26,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"DONE"}}}
|
|
{"type":"assistant/chunk","seq":27,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The skill is loaded."}}}}
|
|
{"type":"assistant/chunk","seq":28,"time":1784903324956,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
|
{"type":"assistant/chunk","seq":29,"time":1785498773786,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}}}}
|
|
{"type":"assistant/chunk","seq":30,"time":1785730426852,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
|
{"type":"assistant/message","seq":31,"time":1785730426853,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The skill is loaded."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"abdbdc3b-06a3-4b5f-b807-15d6566154a0"},"usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}},"sourceEventSeqs":[23,24,25,26,27,28,29,30],"surfaceOp":"append"}
|
|
{"type":"step/end","seq":32,"time":1785730426853,"data":{"turn":1,"step":2}}
|
|
{"type":"turn/end","seq":33,"time":1785730426853,"data":{"turn":1,"reason":{"kind":"completed"}}}
|