Turtle
38c7a9fbf4
* feat(release): publish package source, declaration maps, and documentation Every release member publishes its TypeScript source and the declaration maps that resolve into it, and @deepseek-ai/dsh publishes the repository Markdown documentation staged from docs/ at prepack time. The ./src/* export most members already declared now resolves for an installed consumer, and a consumer editor follows a declaration to the implementation. Bundled JavaScript maps stay unpublished; the vendored family and the Desktop runtime file policy are unchanged. Rationale: .agents/notes/implemented/process/2026-10-08-published-source-and-docs.md * feat(release): publish JavaScript maps and compress bundles Every emitted JavaScript map ships beside the bundle it describes, and the workspace build and the client preset compress bundles without mangling identifiers. The documentation payload now mirrors the website publication manifest and is removed again by `postpack`; Desktop and the Python executable exclude the published source, documentation, and maps; `clean` removes a staged copy. Typert's publication contract gains the Remote declaration map. * fix(release): keep node bundles readable for the worker image The browser worker image lowers `yield*` only as a whole statement and rewrites `for await` loops by their source layout, so compressed node-side entries either fail that lowering or lower to unparseable code. Only the browser bundles keep compression, which removes about a third of their text. The bundle-purity assertion now matches the module-loader call regardless of the quote style compression picks, and the release-pack fixture exercises the installed package's new documentation requirement. * feat(release): publish the whole documentation tree `@deepseek-ai/dsh` copies `docs/` in full instead of the website's page set: the maintainer documents, the generated migration records, the translation guidelines, and the `*.i18n.yaml` consistency records ship with the installed package, so the documentation's own links resolve without a checkout. * feat(release): publish the upgrade guides with the documentation The staged documentation keeps the website's page set and adds every `docs/upgrade-guide/` document, which is what an installed reader consults when a released change breaks something. The rest of the maintainer tree stays out. * test(release): expect source and maps in master's new payload cases * feat(release): keep installed docs and source readable in Desktop Desktop keeps the published src/ and docs/ trees inside app.asar, and every model shell call receives DSH_INSTALL_DIR and DSH_NODE_EXECUTABLE so an agent can read them through Electron's Node mode. Staging also generates docs/upgrade-guide/README.md, an index of the upgrade guides grouped by the release they upgrade from. Minified client bundles print string literals with backticks: the worker image packer now recognizes those chunk requests, client license banners are prepended after minification so their text survives, and the affected artifact tests accept either quote. * test(desktop): read archived docs through the Windows PowerShell form Regenerate the config catalog for the shifted shell-env source line. * test(desktop): wait for the GUI-subsystem Electron process from PowerShell * build(release): publish source and maps from the message-quotes package * build(release): publish source and maps from packages new on master * build(release): publish source and maps from the tool-office package
description, kind
| description | kind |
|---|---|
| Share per-Session browser ownership and MCP activation across experimental browser providers. | package-library |
@deepseek-ai/dsh-experimental-browser-use-runtime
English | 中文
Summary
Browser providers use this library to reuse a browser across one Session's turns and close its resources when that Session's runtime is disposed. Operations for one Session run in order, while isolated Sessions can proceed independently. Attachment mode reserves one external browser for a single Session. The library also connects provider-owned MCP servers and discovers their tools before the Session's first model request.
Table of Contents
- Use this package
- Understand the implementation
- Further Exploration
- Model Experience
- Known Limitations and Deferred Work
- Dev Note
Use this package
This public experimental library is a dependency of the browser providers. It has no plugin entry or mount configuration. The browser-use service remains independent of the library.
Native providers construct SessionResources from the package root, supplying resource acquisition and cleanup callbacks. Calls pass the exact live Agent to run(); stale owners and a second owner of an exclusive attachment fail before acquisition. Canceling an acquisition wait leaves initialization available to other callers in the same Session; Session disposal aborts and awaits that initialization. Providers keep their registration until dispose() finishes.
MCP providers use mountSessionMcp from @deepseek-ai/dsh-experimental-browser-use-runtime/mcp, supplying their fixed server name, executable, arguments, and ownership policy. The mounting context must provide workingDirectory. Acquisition uses the working-directory service to validate or recover the current directory and set the MCP server process's initial directory. Retained servers keep that directory when the Session later selects another. The helper awaits one scoped client startup and discovery attempt within each future Agent's agent/created event. Agent creation or resume completes after discovery, before queued input runs; a successful client remains owned by that Session across turns.
A busy attachment skips startup permanently for that live activation while its other work continues. Releasing the attachment does not retry skipped activations; a newly created or resumed Agent can acquire it. Startup failure or cancellation rejects Agent creation or resume and triggers creation rollback, including client cleanup. Reconnection is disabled. Loading or reloading a provider applies only to future Agent activations.
Callers can inspect prompt assembly and scoped tool definitions after awaited Agent creation or resume completes.
Browser tools and resource requests targeting this server use the same queue and require the calling Session's own connection. Other MCP servers remain usable. Inherited server instructions are omitted without ownership; the shared server-name inventory keeps its normal scope behavior.
Understand the implementation
Implementation internals — click to expand
The resource manager keys ownership by live Agent identity and joins operation cancellation with owner disposal. Each resource has one acquisition promise and one operation queue. Failed acquisition releases its reservation only after the provider callback rolls back acquired resources.
Disposed-cause cancellation starts resource cleanup before AgentHandle waits for idle. Cleanup closes resources before waiting for running operations, allowing connection teardown to interrupt upstream APIs without abort support. A failed close rejects disposal and retains ownership. Agent-scoped cleanup prevents a resumed Session with the same durable id from inheriting a previous browser.
The MCP helper connects within serial agent/created; AgentLoop holds queued input and owns creation rollback. Prompt assembly reads the initialized catalog. The helper retains the provider registration through resource cleanup and uses the MCP client for transport, schema discovery, result conversion, and durable image admission.
Further Exploration
- Browser use — provider selection and Session ownership.
- MCP client — discovery, cancellation, and result admission.
- Browser ownership decision — registration-only service and resource lifetime.
Model Experience
Indirectly, through provider-owned browser tools discovered before model request assembly and through working-directory recovery; providers and the MCP client own tool descriptions, schemas, results, and image behavior, while the directory service owns directory context.
KV Cache effect
Discovered tool schemas and provider guidance determine request-prefix changes; ordinary browser resource reuse does not alter those schemas. Directory recovery appends user context without replacing the system-prompt prefix.
Known Limitations and Deferred Work
Providers remain responsible for the browser operations they supply.
- MCP activation — providers do not adopt existing live Agents; a busy attachment is not retried within that activation.
- Attachment scope — exclusive ownership applies to one resource manager, not separate providers, processes, or external browser clients.
- Cancellation — abort signals and connection closure cannot undo browser actions already delivered. An upstream operation that ignores both can delay cleanup.
- Recovery — a failed close retains ownership; this manager does not retry disposal or restore browser state from the Session log.
- Shared host runtimes — a profile installs this package beside the dsh installation, so
@deepseek-ai/dsh-scopeand@deepseek-ai/dsh-mcp-clientstay peer dependencies. A dependency edge ships a seconddsh-scopecopy whose scope tags host registries cannot read: each Agent's MCP tools would register in the global tool layer and the second Agent's creation would fail.
Dev Note
Working context for maintainers — click to expand
None.