dsh-plugin-dev-kb 1.0.9 → 1.1.0

package/kb/site/en/guide/providers.md

@@ -14,21 +14,39 @@ Open **Settings → Models**. The DeepSeek card exposes one API-key field; enter
 
 Keys are write-only. The page receives a redacted descriptor after saving, never the literal secret. The key is stored in `$DSH_HOME/.credentials.yaml`, while settings retain only its credential reference.
 
-## Add a catalog provider
+## Add a built-in provider
 
-Choose **Add provider**, select a provider such as Anthropic or OpenAI, enter its API key, and save. The installed catalog supplies the endpoint, protocol, and model list.
+Choose **Add provider** and pick a provider dsh ships with; the list shows provider ids such as `anthropic`, `openai`, `moonshotai` for Kimi, or `zai` for GLM. Enter its API key and save. The installed catalog supplies the endpoint, protocol, and model list.
 
-Providers with native authentication need their native credentials instead. Bedrock, Vertex, Azure, and Codex use AWS credentials and a region, an ADC project, an `api-version`, and OAuth respectively; filling only the API-key field does not configure them.
+Providers that sign in with OAuth, such as Codex, are not supported here yet.
 
 ## Add a custom provider
 
-Choose **Add a custom provider** for a company gateway, self-hosted server, or provider absent from the installed catalog. Supply a lowercase Provider ID, base URL, API protocol, credential, and at least one model.
+Choose **Add a custom provider** for a company gateway, self-hosted server, or provider absent from the installed catalog. Supply a lowercase Provider ID, base URL, API protocol, credential, and at least one model. The **API protocol** must be the one your gateway speaks, and the form offers three: `openai-completions` for OpenAI Chat Completions, `openai-responses` for the OpenAI Responses API, and `anthropic-messages` for the Anthropic Messages API. A provider speaks one protocol, so a gateway that serves two needs two providers.
 
 ![The custom provider form: Provider ID, display name, base URL, API protocol, and API key](./providers-custom-form.png)
 
 The Provider ID is permanent because requests, saved sessions, model defaults, and credential references use it. To rename a provider, add a new provider and delete the old one. The display name, base URL, protocol, credential, and models remain editable.
 
-Under **Model catalog**, choose **Fetch available models** to query the base URL and credential currently shown in the form. Selecting candidates updates the draft; the provider is not stored until you save. Catalog providers use their installed catalog without a network request.
+### Discover models
+
+Under **Model catalog**, choose **Fetch available models** to ask the endpoint which models it serves. The request uses the base URL, protocol, and key currently in the form, or a saved provider's stored key, and the reply opens a searchable picker: search, tick the models you want, and choose **Add selected**. Nothing is stored until you save or create the provider.
+
+Discovery reads the listing formats common gateways publish, but not every endpoint answers in one of them, so treat it as a convenience rather than a guarantee: when it fails or lists nothing, add the model ids by hand and they work just the same. A built-in provider is always answered from the installed catalog, even when its base URL points at a gateway, so fetch through a custom provider to see what the gateway really serves.
+
+## Select a model
+
+Configured providers appear in the model picker. Selecting a model also makes it the default for new sessions. A session that has already sent a request retains the model recorded in its own log.
+
+If a saved default names a provider that was deleted, the composer displays **Select model** and blocks input until another model is selected.
+
+## Advanced configuration
+
+The generated [plugin configuration catalog](../reference/config-catalog.md) lists every supported field and default for every plugin; [`dsh-llm-pi-ai`](../reference/config-catalog.md#deepseek-aidsh-llm-pi-ai) is the provider section this page configures. The [`dsh-llm-pi-ai`](https://github.com/deepseek-ai/deepseek-harness/blob/master/packages/llm/llm-pi-ai/README.md) and [`dsh-llm-deepseek`](https://github.com/deepseek-ai/deepseek-harness/blob/master/packages/llm/llm-deepseek/README.md) references own direct `settings.yaml` configuration, catalog resolution, reasoning controls, credentials, and adapter errors.
+
+::: tip The form is deliberately small
+The Models page exposes only what a route needs to exist: the API key, display name, base URL, API protocol, and for each model its id, display name, context window, and max output tokens. Every other field — reasoning effort levels, image input, request-compatibility switches, headers, timeouts, retry policy — is set in `$DSH_HOME/settings.yaml`, the same document the page writes. Edit it directly, or, when the browser runs on the same machine as the server, open it with **Open configuration file** in the Settings header; the adapters re-read it on the next request, so nothing needs a restart. The subsections below cover the fields most gateways need.
+:::
 
 ### Image input
 
@@ -66,7 +84,7 @@ llm-pi-ai:
         - id: second-model
 ```
 
-`defaultInput` is a fallback, not an override, and defaults to `[text]`: on a catalog provider it answers only for models the catalog does not describe, so it never removes images from a catalog model that has them. Narrow one of those with that model's own `input`. A catalog provider has no `models` list to put it in, so write it under `modelOverrides`, keyed by model id:
+`defaultInput` is a fallback, not an override, and defaults to `[text]`: on a built-in provider it answers only for models its catalog does not describe, so it never removes images from a catalog model that has them. Narrow one of those with that model's own `input`. A built-in provider has no `models` list to put it in, so write it under `modelOverrides`, keyed by model id:
 
 ```yaml
 llm-pi-ai:
@@ -81,6 +99,48 @@ Every list must name at least one modality except a model's own, where an empty
 
 Both fields state a claim about your endpoint rather than checking it. A model that declares images its endpoint does not serve is not caught here; the provider rejects the request instead.
 
+### Reasoning effort
+
+The model picker offers an **Effort** menu for a model that declares reasoning levels. A built-in provider's models inherit their levels from the installed catalog. A model you enter by hand declares none, so the Effort entry does not appear in the menu and the endpoint's own default decides whether the model thinks. Declare the levels with `reasoningEfforts` in `$DSH_HOME/settings.yaml`:
+
+```yaml
+llm-pi-ai:
+  providers:
+    my-gateway:
+      apiKeyEnv: GATEWAY_API_KEY
+      api: openai-completions
+      baseURL: https://gateway.example/v1
+      reasoning: high
+      models:
+        - id: my-reasoner
+          reasoningEfforts:
+            off:
+            high: high
+            max: max
+```
+
+Each key is a level the menu offers, and its value is the spelling sent on the wire as `reasoning_effort`, so `max: xhigh` renames a level for a gateway with its own vocabulary. Only `off` may stay empty, because for most endpoints not thinking is the parameter's absence. The route's `reasoning` is the level used while a session has picked none; choosing an effort in the picker saves it, with the model, as the default for new sessions.
+
+An `off` left empty sends nothing, which only stops a model that thinks on request; an `off` given a value sends that value as `reasoning_effort` instead. A model that thinks unless told not to — DeepSeek V4 behind an OpenAI-compatible gateway, for example — needs `compat.thinkingFormat: deepseek`, which makes `off` send `thinking: {type: disabled}` and every other level send `thinking: {type: enabled}` beside the effort:
+
+```yaml
+      models:
+        - id: deepseek-v4-pro
+          compat:
+            thinkingFormat: deepseek
+          reasoningEfforts:
+            off:
+            high: high
+            max: max
+```
+
+A built-in provider's model whose gateway does not reason loses its levels with `reasoningEfforts: false` under `modelOverrides`; selecting an effort for it is then refused as `UNSUPPORTED_REASONING_EFFORT`. DeepSeek's own route needs none of this: its models already offer `off`, `low`, `high`, and `max`, and `llm-deepseek.reasoningEffort` sets the default the picker starts from:
+
+```yaml
+llm-deepseek:
+  reasoningEffort: max
+```
+
 ### Request compatibility
 
 A gateway can hold a working key at a reachable address and still refuse every request. pi-ai decides the shape of a request — which role carries the system prompt, which field caps the output, how a thinking level travels — from the endpoint's URL, and an address it does not recognize is addressed as though it were OpenAI itself. Most OpenAI-compatible gateways refuse at least one thing OpenAI accepts.
@@ -117,23 +177,16 @@ Each switch belongs to the protocols that declare it, so a switch valid on one `
 
 Every switch, its accepted values, and the protocols that take it are listed under `PiAiCompatProfile` in the [generated `dsh-llm-pi-ai` configuration reference](../reference/config-catalog.md#deepseek-aidsh-llm-pi-ai) — which is derived from the source, so it cannot fall behind what the adapter accepts.
 
-## Select a model
-
-Configured providers appear in the model picker. Selecting a model also makes it the default for new sessions. A session that has already sent a request retains the model recorded in its own log.
-
-If a saved default names a provider that was deleted, the composer displays **Select model** and blocks input until another model is selected.
-
 ## Troubleshooting
 
 - **`MISSING_CREDENTIAL`** — Store the provider key through the Models page or supply the referenced environment variable.
 - **`UNKNOWN_MODEL`** — Select a configured model or add the missing model to the custom provider.
 - **Fetching available models returns 401** — Check the key. Model discovery calls the OpenAI-compatible `GET /models` endpoint; enter models manually for endpoints that do not provide it.
+- **Fetching available models reports neither a `data` array nor a `models` object** — The endpoint's listing is in a format discovery does not read. Enter the models by hand.
 - **The gateway refuses every request although the key and URL are right** — Its request shape differs from OpenAI's. Start with `compat.supportsDeveloperRole: false` and `compat.maxTokensField: max_tokens` on the route.
 - **Only reasoning models fail** — pi-ai sends their system prompt as the `developer` role, which the gateway rejects. Set `compat.supportsDeveloperRole: false`.
+- **The Effort menu does not appear for a model you entered by hand** — It declares no levels. Add `reasoningEfforts` to the model in `settings.yaml`.
+- **`off` does not stop a DeepSeek model from thinking** — An empty `off` sends no reasoning field at all, and an endpoint that thinks by default keeps thinking. Set `compat.thinkingFormat: deepseek` on the model or the route.
 - **A compat switch is refused as having no value** — A key written with nothing after the colon. Give it a value, or remove the key to keep the installed catalog's.
-- **An image is refused before sending** — The model declares no image modality. Give a custom provider's model `input: [text, image]`; DeepSeek's own chat-completions route is text-only and cannot be configured otherwise.
+- **An image is refused before sending** — The model declares no image modality. Give a custom provider's model `input: [text, image]`; on DeepSeek's own route, select `deepseek-v4-flash-vision-exp`, the model that declares images.
 - **The provider rejects a request carrying an image** — The model declares images its endpoint does not actually serve. Remove `image` from whichever list granted it — the model's `input`, or the route's `defaultInput` — then start a new session: the attached image stays in the session log, so the same request repeats until the session moves off it.
-
-## Advanced configuration
-
-The generated [plugin configuration catalog](../reference/config-catalog.md) lists every supported field and default for every plugin; [`dsh-llm-pi-ai`](../reference/config-catalog.md#deepseek-aidsh-llm-pi-ai) is the provider section this page configures. The [`dsh-llm-pi-ai`](https://github.com/deepseek-ai/deepseek-harness/blob/master/packages/llm/llm-pi-ai/README.md) and [`dsh-llm-deepseek`](https://github.com/deepseek-ai/deepseek-harness/blob/master/packages/llm/llm-deepseek/README.md) references own direct `settings.yaml` configuration, catalog resolution, reasoning controls, credentials, and adapter errors.

package/kb/site/en/guide/schedule.md

@@ -12,6 +12,8 @@ dsh web --patch apps/cli/config/examples/schedule/cordis.yml
 
 The current overlay supports reminders created with a positive whole-number `after_seconds`, an absolute `at` target, or a fixed-rate `every_seconds` interval of at least 300 seconds. The model manages them through `schedule_create`, `schedule_list`, and `schedule_delete`; every result identifies delivery as `session-local`.
 
+With this overlay enabled, a successfully opened Session with active reminders shows a read-only catalog in the conversation header. It lists the complete prompt, scheduled or overdue status, one-time or exact repeating cadence, browser-local target time, and relative time. The sidebar also places a non-interactive alarm after the title of grouped, flat, and search rows when their currently available projection value is non-empty. These surfaces never create, edit, delete, or acknowledge reminders, and a cold Session's cached alarm can be briefly missing or stale.
+
 The browser attaches its IANA zone to each prompt. Time-context tells the model to interpret otherwise-unqualified dates and times in that request's browser zone. This assumption belongs to natural-language interpretation only: `schedule_create.at` must be either a strict RFC 3339 date-time with `Z` or a numeric offset, or `{ date, time, time_zone }` with an explicit `UTC` or IANA Area/Location zone. Schedule does not retain or infer a Session default zone. Daylight-saving gaps are rejected, overlaps choose the first instant, and successful records keep only the resulting UTC target.
 
 The original Session log owns each reminder. A live root Agent waits until it is fully idle, then queues a normal follow-up turn in that conversation. It never steers current work and adds no separate receipt or reminder card. Closing the process or leaving the Session cold stops its in-memory timer without deleting the record; reopening that same Session restores the wait and delivers an overdue reminder. Reading cold history never activates it, and a fork does not inherit its parent's reminders.

package/kb/site/en/reference/agent-lifecycle.md

@@ -39,14 +39,16 @@ sequenceDiagram
   Driver->>Prompt: <code>system-prompt/assemble</code> waterfall
   Driver->>LLM: <code>agent/request</code> waterfall, then <code>llm/stream</code> waterfall
   LLM-->>Driver: StreamChunk*
-  Driver->>Session: <code>assistant/chunk</code>*
-  Session-->>SDK: <code>session/event</code> <code>assistant/chunk</code>*
+  Driver-->>SDK: <code>agent/assistant-stream</code> chunk*
   alt final adapter or terminal in-band request failure
+    Driver->>Session: <code>assistant/attempt</code>
+    Driver-->>SDK: <code>agent/assistant-stream</code> committed end
     Driver->>Session: <code>step/end</code>
     Driver->>Hooks: <code>agent/request-error</code> waterfall
     Hooks-->>Driver: return retry action or preserve the original error
   else model request succeeded
   Driver->>Session: <code>assistant/message</code>
+  Driver-->>SDK: <code>agent/assistant-stream</code> committed end
   Driver->>Tools: classify pending call by executionMode
   loop barriers and bounded rolling pool, reclassify before start
     opt call starts
@@ -75,7 +77,7 @@ sequenceDiagram
   Driver-->>SDK: <code>agent/status</code> idle
 ```
 
-The `assistant/message` event records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history, while the durable event keeps usage and `sourceEventSeqs` listing the exact `assistant/chunk` events, including an explicit empty list.
+The `assistant/message` event records every successful provider call, including content-less and `max-tokens` finishes, and embeds the exact compact timed stream. Empty content stays out of derived history. A failed, retried, cancelled, or stream-error attempt that reaches settlement without a surface message records its stream as `assistant/attempt`. Live `agent/assistant-stream` chunk frames are transient; replay reads either durable settlement, and a hard process loss before settlement leaves no durable attempt stream.
 
 `dsh-compaction-basic` uses `agent/pre-step` for pressure before request derivation and `agent/request-error` only for canonical context overflow. Once either trigger qualifies, optional tool-result pruning runs before summary selection. Recovery works between the closed failed step and failed turn close, and opens a fresh retry turn only when pruning or summarization advances the surface replacement generation; otherwise the original request error remains authoritative.
 

package/kb/site/en/reference/api-gateway.md

@@ -126,13 +126,13 @@ The Connection performs the unified trust check for `/api` before the HTTP bridg
 
 For every call, the Gateway resolves the descriptor and live service from the current registries instead of caching business objects. It requires the fields in `args` to match the descriptor exactly, validates wire values with codecs, resolves objects or receivers through registered lookup or Context providers, invokes the service method targeted by the binding, and validates the return value. A missing provider, unknown identity, binding mismatch, missing or extra argument, schema failure, or missing method fails before entering or after leaving business code.
 
-The lookup provider's `register()` supplies both the stable declaration and the default resolver; `configure()` supplies a resolver owned by Host composition that may execute asynchronously and is scoped to an effect lifetime. Configuration may precede provider mounting; without a provider, invocation still fails with `lookup-unavailable`, and unloading the configuration restores the provider's default policy. The Session Controller owns the standard `agentFor()` semantics for `agent` and `session`: it reuses a live Agent, automatically resumes ordinary cold sessions, deduplicates concurrent resumes, and rejects identities owned by subagent routing; the `session` lookup returns that Agent's Session. Resume failures and ownership fences pass through unchanged as existing RPC errors rather than being collapsed into the Gateway's `internal` error.
+The lookup provider's `register()` supplies both the stable declaration and the default resolver; `configure()` supplies a resolver owned by Host composition that may execute asynchronously and is scoped to an effect lifetime. Configuration may precede provider mounting; without a provider, invocation still fails with `gateway/lookup-unavailable`, and unloading the configuration restores the provider's default policy. The Session Controller owns the standard resolver semantics for `agent` and `session`: it reuses a live Agent, automatically resumes ordinary cold sessions, deduplicates concurrent resumes, and rejects identities owned by subagent routing; the `session` lookup returns that Agent's Session. A resume failure and an ownership fence raise a `RemoteError` carrying their own code, `session/not-found` or `session/agent-busy`, which the Gateway encodes onto the wire unchanged; only an unclassified throw folds into `gateway/internal`.
 
 Unloading a Client contribution removes its descriptors and concrete methods together, aborts its in-flight calls, and makes stale method handles retained by external code reject further calls. A strict endpoint withdrawn on the Host also does not degrade to SRC inference, preventing a hot unload from silently weakening validation.
 
 ## SRC development fallback
 
-When the Host starts from source through `node --import tsx/esm`, it does not execute the Typert compiler plugin. Standard decorator initializers still record the method name and invocation mode in a module-private `WeakMap`, while `TypertRemoteService` or `bindTypertRemote()` supplies the explicit service binding; the Gateway can therefore construct a weaker temporary descriptor without starting a `ts.Program`.
+When the Host starts from source through `node --import tsx/esm`, it does not execute the Typert compiler plugin. Standard decorator initializers still record the method name and invocation mode in a versioned descriptor on the Service prototype, while `TypertRemoteService` or `bindTypertRemote()` supplies the explicit service binding; the Gateway can therefore construct a weaker temporary descriptor without starting a `ts.Program`. The descriptor's stable string property name lets `remoteMethods()` read markers written by another installed copy of the protocol package.
 
 The SRC fallback parses simple parameter names from the live function. When a parameter name matches the `parameter` of a registered lookup, such as `agent` or `session`, it uses the lookup's `agentId` or `sessionId` wire field and resolves the object on the Host; other parameters are checked only for cycle-free, JSON-safe data with no special prototype. `@RemoteScope` directly uses the wire field of a registered Host Context provider. SRC does not read TypeScript types, generate Zod schemas, infer optional parameters, or support destructuring, default values, rest parameters, or duplicate parameter names.
 

package/kb/site/en/reference/capability-seams.md

@@ -18,6 +18,8 @@ flowchart LR
   pkg_tool_fs["tool-fs"]
   pkg_llm_pi_ai["llm-pi-ai"]
   pkg_llm_deepseek["llm-deepseek"]
+  pkg_client_file_upload["client-file-upload"]
+  svc_fileUploads["ctx.fileUploads<br/>Agent-scoped staged file uploads"]
   pkg_llm["llm"]
   svc_llm["ctx.llm<br/>LLM adapter registry"]
   pkg_llm_replay["llm-replay"]
@@ -58,7 +60,6 @@ flowchart LR
   svc_typertGateway["ctx.typertGateway<br/>Typert Host invocation gateway"]
   svc_sessionPersistence["ctx.sessionPersistence<br/>Durable session persistence seam"]
   pkg_session_persistence_jsonl["session-persistence-jsonl"]
-  pkg_session_persistence_sqlite["session-persistence-sqlite"]
   pkg_tool_bash["tool-bash"]
   pkg_hooks_claude_code["hooks-claude-code"]
   pkg_hooks_codex["hooks-codex"]
@@ -128,7 +129,8 @@ flowchart LR
   svc_agentDefaultModel["ctx.agentDefaultModel<br/>Default Agent model selection"]
   pkg_headless["headless"]
   svc_agentLoop["ctx.agentLoop<br/>Concrete loop driver"]
-  pkg_agent_spine_demo["agent-spine-demo"]
+  pkg_base["base"]
+  pkg_sdk_minimal["sdk-minimal"]
   pkg_goal["goal"]
   svc_goals["ctx.goals<br/>Same-session goal domain"]
   pkg_e2b["e2b"]
@@ -166,6 +168,7 @@ flowchart LR
   pkg_code_runtime["code-runtime"]
   svc_codeRuntime["ctx.codeRuntime<br/>Code-execution seam"]
   pkg_code_runtime_worker_thread["code-runtime-worker-thread"]
+  pkg_experimental_code_runtime_python["experimental-code-runtime-python"]
   pkg_fs["fs"]
   svc_fs["ctx.fs<br/>Filesystem provider seam"]
   pkg_fs_local["fs-local"]
@@ -238,6 +241,7 @@ flowchart LR
   pkg_authorization --> svc_authorization
   pkg_bash_local --> svc_shell
   pkg_bash_sandbox --> svc_shell
+  pkg_client_file_upload --> svc_fileUploads
   pkg_client_modules --> svc_clientModules
   pkg_code_runtime --> svc_codeRuntime
   pkg_code_runtime_worker_thread --> svc_codeRuntime
@@ -252,6 +256,7 @@ flowchart LR
   pkg_deepseek_llm_api_extensions --> svc_deepseekLlmApiExtensions
   pkg_e2b --> svc_e2b
   pkg_experimental_agent_team --> svc_agentTeams
+  pkg_experimental_code_runtime_python --> svc_codeRuntime
   pkg_file_reference --> svc_fileReferences
   pkg_file_reference_local --> svc_fileReferences
   pkg_fs --> svc_fs
@@ -285,7 +290,6 @@ flowchart LR
   pkg_session_log_deepseek --> svc_deepseekLlmApiExtensions
   pkg_session_persistence --> svc_sessionPersistence
   pkg_session_persistence_jsonl --> svc_sessionPersistence
-  pkg_session_persistence_sqlite --> svc_sessionPersistence
   pkg_session_projection --> svc_sessionProjections
   pkg_session_projection_cache --> svc_sessionProjectionCache
   pkg_session_query --> svc_sessionQuery
@@ -339,7 +343,8 @@ flowchart LR
   pkg_workspace --> svc_workspaceRegistry
   svc_agentDefaultModel --> pkg_api_session_controller
   svc_agentDefaultModel --> pkg_headless
-  svc_agentLoop --> pkg_agent_spine_demo
+  svc_agentLoop --> pkg_base
+  svc_agentLoop --> pkg_sdk_minimal
   svc_agentTeams --> pkg_experimental_client_ui_agent_team
   svc_agentTeams --> pkg_experimental_tool_agent_team
   svc_agents --> pkg_acp
@@ -366,6 +371,7 @@ flowchart LR
   svc_e2b --> pkg_fs_e2b
   svc_e2b --> pkg_subprocess_e2b
   svc_fileReferences --> pkg_api_session_controller
+  svc_fileUploads --> pkg_api_session_controller
   svc_fs --> pkg_tool_fs
   svc_invariants --> pkg_agent
   svc_invariants --> pkg_agent_loop
@@ -468,6 +474,7 @@ flowchart LR
 | ctx key | Role | Owner | Implementations | Direct consumers | Companion plugins | Note |
 | --- | --- | --- | --- | --- | --- | --- |
 | `ctx.attachments` | `seam` | [`attachment`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/attachment/attachment) | [`attachment-local`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/attachment/attachment-local) | [`api-session-controller`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/api/session-controller), [`tool-fs`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/fs/tool-fs), [`llm-pi-ai`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-pi-ai), [`llm-deepseek`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-deepseek) | - | The host commits accepted images before session events; provider adapters resolve authorized durable references into provider-native content. |
+| `ctx.fileUploads` | `core` | [`client-file-upload`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/client/file-upload) | - | [`api-session-controller`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/api/session-controller) | - | Owns streaming intake, durable storage, and staged receipt lifetime; the Session controller binds receipts to accepted submissions. |
 | `ctx.llm` | `seam` | [`llm`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm) | [`llm-deepseek`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-deepseek), [`llm-pi-ai`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-pi-ai), [`llm-replay`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/test-support/llm-replay) | [`agent-loop`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-loop), [`compaction-basic`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/compaction/compaction-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. |
 | `ctx.deepseekLlmApiExtensions` | `seam` | [`deepseek-llm-api-extensions`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/deepseek-llm-api-extensions) | [`session-log-deepseek`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session/session-log-deepseek), [`plugin-package-inventory-deepseek`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/plugin-package-inventory-deepseek) | [`llm-deepseek`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-deepseek) | - | Plugins prepare independent top-level fields; the official adapter merges them and commits their delivery state after HTTP acceptance. |
 | `ctx.tokenMeter` | `core` | [`token-meter`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/token-meter) | - | [`compaction-basic`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/compaction/compaction-basic) | - | Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements. |
@@ -483,7 +490,7 @@ flowchart LR
 | `ctx.invariants` | `core` | [`invariants`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/runtime-diagnostics/invariants) | - | [`session`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/session), [`agent`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent), [`scope`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/scope), [`agent-loop`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-loop) | - | Companion subpaths register owner-local checks; the service owns selection, uniqueness, child fibers, and package-attributed failures. |
 | `ctx.typert` | `core` | [`typert-registry`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/typert/registry) | - | [`typert-loader`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/typert/loader), [`api-gateway`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/api/gateway) | - | Plugins register live zod contributions directly or through dsh-typert-loader; the API gateway consumes invocation descriptors and providers, while other runtime consumers query schemas and reflection metadata at their own edges. |
 | `ctx.typertGateway` | `core` | [`api-gateway`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/api/gateway) | - | - | - | Associates generated Remote descriptors with live Cordis services, resolves registered identities, and exposes unary calls through the shared Connection RPC carrier. |
-| `ctx.sessionPersistence` | `seam` | [`session-persistence`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session/session-persistence) | [`session-persistence-jsonl`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session/session-persistence-jsonl), [`session-persistence-sqlite`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session/session-persistence-sqlite) | [`agent-loop`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-loop), [`tool-bash`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/shell/tool-bash), [`hooks-claude-code`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/hooks/hooks-claude-code), [`hooks-codex`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/hooks/hooks-codex), [`session-query`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session-query/session-query), [`session-query-sqlite`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session-query/session-query-sqlite), [`message-feedback`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/feedback/message-feedback) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. |
+| `ctx.sessionPersistence` | `seam` | [`session-persistence`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session/session-persistence) | [`session-persistence-jsonl`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session/session-persistence-jsonl) | [`agent-loop`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-loop), [`tool-bash`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/shell/tool-bash), [`hooks-claude-code`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/hooks/hooks-claude-code), [`hooks-codex`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/hooks/hooks-codex), [`session-query`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session-query/session-query), [`session-query-sqlite`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/session-query/session-query-sqlite), [`message-feedback`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/feedback/message-feedback) | - | The JSONL backend persists the SessionEvent vocabulary as one artifact per Session. |
 | `ctx.settings` | `seam` | [`settings`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/settings/settings) | [`settings-file`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/settings/settings-file) | [`api-settings-controller`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/api/settings-controller), [`llm-deepseek`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-deepseek), [`llm-pi-ai`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-pi-ai) | - | Plugins register namespace schemas and resolve layered values; providers store the raw document. The LLM adapters register their entry config as the composition base under the user section; the settings controller serves redacted layered descriptors and writes the user layer. |
 | `ctx.subagentModelSelection` | `core` | [`tool-subagent`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/tool-subagent) | - | [`tool-subagent`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/tool-subagent) | - | Owns the default-off settings namespace that Agent-scoped delegation tools sample when composing a new top-level Session. |
 | `ctx.credentials` | `seam` | [`credentials`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/credentials/credentials) | [`credentials-local`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/credentials/credentials-local) | [`api-settings-controller`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/api/settings-controller), [`llm-deepseek`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-deepseek), [`llm-pi-ai`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/llm/llm-pi-ai) | - | Configuration carries references to secrets; providers own the values. Consumers resolve per operation, so a rotated credential reaches the very next request; the settings controller exposes value-free views and write-only storage. |
@@ -508,7 +515,7 @@ flowchart LR
 | `ctx.skills` | `seam` | [`skill`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/skill/skill) | [`skill-badge`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/skill/skill-badge), [`skill-filesystem`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/skill/skill-filesystem) | [`tool-skill`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. |
 | `ctx.agents` | `core` | [`agent`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent) | - | [`agent-loop`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-loop), [`acp`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/acp/acp), [`subagent-in-process-driver`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-in-process-driver) | - | Owns live Agent handles, the create/resume factory seam, and process-local initiator propagation. |
 | `ctx.agentDefaultModel` | `core` | [`agent-default-model`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-default-model) | - | [`api-session-controller`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/api/session-controller), [`headless`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/bundle/headless) | - | Layers the default ModelSelection through settings so direct and Host-backed Agent entry points share one state owner. |
-| `ctx.agentLoop` | `bundle` | [`agent-loop`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-loop) | - | [`agent-spine-demo`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. |
+| `ctx.agentLoop` | `bundle` | [`agent-loop`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/agent-loop) | - | [`base`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/bundle/base), [`sdk-minimal`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/bundle/sdk-minimal) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. |
 | `ctx.goals` | `core` | [`goal`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/goal/goal) | - | - | - | Folds revisioned objective state from the session log and keeps live continuation activation process-local. |
 | `ctx.e2b` | `core` | [`e2b`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/e2b/e2b) | - | [`fs-e2b`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/e2b/fs-e2b), [`subprocess-e2b`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/e2b/subprocess-e2b) | - | Owns one shared E2B SDK handle, remote working directory, and final sandbox disposition so both fundamental E2B providers inhabit the same Linux runtime. |
 | `ctx.subprocess` | `seam` | [`subprocess`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subprocess/subprocess) | [`subprocess-local`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subprocess/subprocess-local), [`subprocess-e2b`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/e2b/subprocess-e2b) | [`bash-local`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/shell/bash-local), [`bash-sandbox`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/shell/bash-sandbox), [`terminal-bash`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/terminal/terminal-bash), [`lsp-stdio`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/lsp/lsp-stdio), [`subagent-acp`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-acp), [`subagent-codex`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-codex), [`subagent-claude-code`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-claude-code) | - | The bash executors, the PTY shell backend, the LSP host, and the out-of-process ACP, Codex, and Claude Code subagent backends spawn through ctx.subprocess; the service owns process coordinates, tree/session lifetime, stdio dispositions, terminal mechanics, and kill escalation. |
@@ -519,7 +526,7 @@ flowchart LR
 | `ctx.sandboxPolicy` | `core` | [`sandbox-policy`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/sandbox/sandbox-policy) | - | [`bash-sandbox`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/shell/bash-sandbox), [`fs-sandbox`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/fs/fs-sandbox), [`terminal-bash`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/terminal/terminal-bash) | - | The one home for the deployment default mode + workspace root; only the sandboxed executor and provider read the service (the tool layers use the pure `sandbox/mode` fold it also exports). Both enforcing families read it so bash and fs cannot confine to different roots. |
 | `ctx.approval` | `seam` | [`user-approval`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/interaction/user-approval) | - | [`tools`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/tools), [`tool-bash`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/shell/tool-bash), [`acp`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/acp/acp) | - | One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`. |
 | `ctx.permissionPresets` | `core` | [`permission-presets`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/interaction/permission-presets) | - | - | - | User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events. |
-| `ctx.codeRuntime` | `seam` | [`code-runtime`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/code-runtime/code-runtime) | [`code-runtime-worker-thread`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/code-runtime/code-runtime-worker-thread) | [`tools`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for PTC mode). |
+| `ctx.codeRuntime` | `seam` | [`code-runtime`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/code-runtime/code-runtime) | [`code-runtime-worker-thread`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/code-runtime/code-runtime-worker-thread), [`experimental-code-runtime-python`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/experimental/code-runtime-python) | [`tools`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for PTC mode). |
 | `ctx.fs` | `seam` | [`fs`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/fs/fs) | [`fs-local`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/fs/fs-local), [`fs-sandbox`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/fs/fs-sandbox), [`fs-e2b`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/e2b/fs-e2b) | [`tool-fs`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/fs/tool-fs) | [`fs-observation-policy`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/fs/fs-observation-policy) | tool-fs executes read/write/edit through ctx.fs; fs-sandbox fences mutations by the shared sandbox mode; fs-observation-policy contributes observed-state checks through the fs/* event gate. |
 | `ctx.compaction` | `seam` | [`compaction`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/compaction/compaction) | [`compaction-basic`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/compaction/compaction-basic) | [`compaction-basic`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/compaction/compaction-basic) | - | The basic backend consumes post-step pressure and request-error recovery events; there is no model-facing compact tool. |
 | `ctx.subagents` | `seam` | [`subagent`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent) | [`subagent-spawn-in-process`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-spawn-in-process), [`subagent-fork-in-process`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-fork-in-process), [`subagent-acp`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-acp), [`subagent-codex`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-codex), [`subagent-claude-code`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-claude-code), [`subagent-dsh-sdk`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/subagent-dsh-sdk) | [`tool-subagent`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/tool-subagent), [`tool-subagent-control`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/subagent/tool-subagent-control), [`tool-ralph`](https://github.com/deepseek-ai/deepseek-harness/tree/master/packages/workflow/tool-ralph) | - | Providers implement transports; the service also owns optional Activation-based continuation orchestration, tool-subagent selects one-shot or continuable delegation, tool-subagent-control delivers follow-ups, and tool-ralph requires one fresh structured-output route. |