xd:// devices dispatch through the write tool, so a read-only call such
as an lsp navigation matched PREWALK_ACTION_TOOLS and armed the one-way
model hand-off while still reasoning about code shape.
dispatchXdevTool now records the wrapped tool's approval tier on the
XdevDispatch, and the prewalk coordinator only treats a device write as
an implementation action at write/exec tier. Direct edit/write are
unchanged.
Fixes#7312
Catalog summaries of mounted xd:// devices are inlined verbatim into the
system prompt. External devices (MCP servers, plugins) supply that text, and
it was bounded only by character count: a summary of multi-byte script passed
roughly three times the intended budget, and control characters survived into
the prompt where they can forge structure.
Summaries now go through a single sanitize-and-bound step that strips C0/C1
control characters and bounds the result in UTF-8 bytes via the central
truncateHeadBytes helper, so a cut lands on a code point boundary and never
renders a partial code point. The built-in/external distinction is derived
once per entry, and that same boolean both selects the description cap and is
exposed as `dynamic`, so the cap and the flag cannot disagree. The prompt uses
the flag to state that dynamic summaries are untrusted metadata, and the mount
notice says the same for newly appeared devices.
(cherry picked from commit 5989da6235d820bc687779a791e655e6f1b2df0f)
- Replaced the `XdevRegistry` class with the `XdevState` interface and pure helper functions across core and session tools.
- Updated session configurations, tool execution, and renderers to utilize canonical tool map initialization and sharing.
- Adapted unit tests and mocks to use `XdevState` and associated helper functions for permission and dispatch verification.
- Extracted #formatToolExecution into a standalone formatDefaultToolExecution module.
- Updated xdev renderXdevCall and renderXdevResult to use the default card when no mounted renderer exists.
- Added fallback rendering that shows tool label, args, and output with appropriate theming.
- Added integration test verifying generic card renders for mounted tools without bespoke renderers.
- Catch execution errors in XdevRegistry and render them using the mounted tool's error handling.
- Preserve xdev dispatch context when device execution fails.
Settings.get returns raw merged config without element validation, so a
scalar or non-string tools.xdevInlineDevices entry reached Bun.Glob and
threw while building the system prompt. Normalized the allowlist to
string patterns and compiled globs once per render.
- Exempted the handler-less conflict:// scheme from the URI-like guard so parseConflictUri still splices registered blocks.
- Extended the near-miss regression to assert conflict://1 reaches the resolver.
Fixes#6123
- Blocked malformed and unregistered URI-like paths before filesystem resolution.
- Suggested canonical xd:// spelling while preserving explicitly escaped local paths.
- Added regression coverage for xdt://, xd:/, and xd/ near misses.
Fixes#6123
web_search is a discoverable built-in, so with tools.xdev defaulting to
true createTools mounted it under xd:// and dropped it from the top-level
toolset. Models that call web_search directly got "Tool web_search not
found" on default configs. Pin it in XDEV_KEEP_TOP_LEVEL so it stays a
direct-callable tool while other discoverable tools keep mounting.
Fixes#5973
Schema-invalid JSON objects can reach mounted approval functions before xdev dispatch validates their arguments. Fall back to the exec tier when an approval function throws, preserving fail-closed prompting and allowing dispatch to surface its normal schema error.
Added regression coverage for ast_edit payloads containing null paths.
Fixes#5727
The write approval gate discarded a mounted tool's function-valued
approval and never decoded the device JSON payload, defaulting the tier
to exec. Read/write xd:// operations then prompted in non-yolo modes
that permit them.
Now decode valid object payloads and resolve the mounted tool's normal
approval decision via resolveToolTier; malformed JSON, non-object
payloads, and unknown devices still fall back to exec and prompt.
Fixes#5727
Instead of including the xd:// device inventory in the system-prompt signature, mount/unmount events now inject a steered `xdev-mount-notice` message so the system prompt (and its provider cache prefix) stays byte-stable across MCP connects and disconnects. Full device docs are picked up opportunistically on the next unrelated rebuild.
Also caps external (dynamic-mount) device descriptions to 200 chars in `docsAll` to prevent server-controlled prose from consuming prompt budget; built-ins keep their full curated docs, and `read xd://` always returns the untruncated text.
Legacy `discoveryMode: "off"` → `tools.xdev: false` migration is removed; the setting keeps its own default without inference from the deprecated key.
- Added the `xd://` virtual device protocol (`internal-urls/xd-protocol.ts`, `tools/xdev.ts`): tools declaring `loadMode: "discoverable"` are unmounted from the request tools array and driven via `read xd://` (list/docs+schema) and `write xd://<tool>` (execute), gated by the `tools.xdev` setting (default on) and inlined into the system prompt.
- Merged the `irc`, `job`, and `launch` tools into a single `hub` tool (`tools/hub/`, `async/job-manager.ts`): messaging keeps `send`/`inbox`/`list`, job control maps to `wait`/`cancel`/`jobs`, process supervision keeps `start`/`logs`/`stop`/`restart`/`describe` with `ps`, and the unified `wait` races background jobs against peer messages; SDK `IrcTool`/`JobTool`/`LaunchTool` are replaced by `HubTool`.
- Removed the hidden `resolve` tool in favor of the `xd://resolve`/`xd://reject`/`xd://propose` resolution devices, auto-including `write` whenever a deferrable tool or plan mode is present.
- Removed the BM25 tool-discovery system: the `search_tool_bm25` tool, the `tool-discovery` module, the `tools.discoveryMode`/`mcp.discoveryMode`/`mcp.discoveryDefaultServers`/`tools.essentialOverride` settings, per-tool MCP selection, and the `mcp_tool_selection` message type.
- Unified tool presentation on `ToolLoadMode` (`essential`|`discoverable`), replacing the custom-tool `xdev?: boolean` opt-out; custom, extension, MCP, RPC host, image-generation, and TTS tools now default to `discoverable`, and added a `satisfies` predicate to `SoftToolRequirement`.
- Removed the standalone `ssh` command tool and `ssh/ssh-executor` (the `ssh://` read/write/search protocol stays), and made `--tools` address hidden built-ins.
- Updated collab-web to render `xd://` dispatches and `hub` op families, dropped the `search_tool_bm25`/`ssh`/`report-finding` renderers, refreshed tool docs and prompts, and migrated the affected tests and changelogs.
can1357