LLM CLI Gateway

Show Personal Agent Config state without exposing baseline paths or local machine binding values.

Synchronize, verify, compile, and atomically activate a Personal Agent Config release. It never pushes.

Ask provider CLIs whether they agree or disagree with a claim (starts validation jobs).

Run a Cursor Agent request synchronously (auto-defers to a pollable job past the sync deadline when async jobs are enabled; otherwise runs to completion). Default `cli` uses headless print mode (`cursor-agent --print`); gated `acp` uses native `cursor-agent acp` and accepts prompt, model, a gateway ACP session, and a registered workspace alias.

Start a Cursor Agent CLI request as a durable background job. Poll with llm_job_status, collect with llm_job_result.

Run a Cognition Devin CLI request synchronously (auto-defers to a pollable job past the sync deadline when async jobs are enabled; otherwise runs to completion). Headless print mode (`devin -p`).

Start a Cognition Devin CLI request as a durable background job. Poll with llm_job_status, collect with llm_job_result.

Explain the selected Personal Agent Config release and context provenance without returning local paths or instruction text.

Run a Google Antigravity CLI (`agy`) request through the Gemini-compatible gateway tool synchronously (when async jobs are enabled, auto-defers to a pollable job past the sync deadline; otherwise runs to completion). Requires exactly one of prompt or promptParts.

Start a Google Antigravity CLI (`agy`) request as a durable background job through the Gemini-compatible gateway tool. Poll with llm_job_status, collect with llm_job_result.

Run an xAI Grok API request synchronously through the Responses API. Requires exactly one of prompt or promptParts. Registered only when [providers.xai] is configured and its API-key env var is present.

Run an xAI Grok CLI request synchronously (when async jobs are enabled, auto-defers to a pollable job past the sync deadline; otherwise runs to completion). Requires exactly one of prompt or promptParts.

Start an xAI Grok CLI request as a durable background job. Poll with llm_job_status, collect with llm_job_result.

Collect a VALIDATION job's normalized provider output — distinct from llm_job_result, which returns raw provider request job output.

Check a VALIDATION job's status (jobs started by validate_with_models/ask_model/etc.) — distinct from llm_job_status, which tracks provider request jobs.

List models and capabilities for every available provider CLI (takes no arguments; complements per-provider list_models).

List models, aliases, and defaults for one provider (claude|codex|gemini|grok|mistral|devin|cursor, or an enabled API provider name), or omit cli to list all providers. API providers are returned under an `apiProviders` array.

Cancel a running gateway async or deferred-sync job by jobId.

Retrieve captured stdout/stderr for a gateway async or deferred-sync job by jobId. Use rawOutput:true with independent stream offsets for resumable pages.

Check lifecycle status and bounded privacy-safe normalized progress for a gateway async or deferred-sync job by jobId.

Wait briefly for privacy-safe normalized progress on an owned async job. When the MCP request carries a progress token, notifications are emitted only while this watch request remains active.

Report gateway process health: async-job manager state, the resolved durable persistence configuration, and flight-recorder health on that configured engine.

List recent persisted requests (sync and async) newest-first WITHOUT a correlation id, to find one. Returns metadata only; pass a returned correlationId to llm_request_result for the prompt/response, or a returned asyncJobId to llm_job_status.

Read back any persisted request (sync or async) from the flight recorder by correlationId, including prompt and response. Local callers can also include the linked complete job record.

Run a Mistral Vibe CLI request synchronously (when async jobs are enabled, auto-defers to a pollable job past the sync deadline; otherwise runs to completion). Requires exactly one of prompt or promptParts. Defaults to --agent accept-edits (auto-accepts file edits; dangerous ops such as shell stay gated).

Start a Mistral Vibe CLI request as a durable background job. Poll with llm_job_status, collect with llm_job_result.

List provider CLI admin operations (auth status, model list, mcp list, plugin list, doctor, etc.) available on the installed CLIs, projected from runtime discovery. Read-only.

Execute a MUTATING provider CLI admin operation (mcp add/remove, login/logout, plugin install/remove, session delete/archive, ...). Disabled unless [admin] allow_mutating_cli_admin_ops=true; routed through approval and audited.

Execute a READ-ONLY provider CLI admin operation (from provider_admin_list) and return redacted output. Rejects mutating operations.

Return the detailed read-only contract for exactly one declared provider CLI subcommand.

Probe declared provider subcommand --help surfaces and return compact drift rows without raw help output.

Return a compact, filterable read-only catalog of declared provider CLI subcommands without flags or raw help.

Report provider tool/feature capabilities and discovered local skill/tool integrations for claude|codex|gemini|grok|mistral|devin|cursor|grok_api, or an enabled API provider name.

Compare installed provider CLI versions against their contracted targets, and optionally check whether a newer version is published. Reports which providers drifted and which can be upgraded, plus the exact upgrade command for each.

Challenge a plan, answer, or document for risks and failure modes via provider CLIs (starts validation jobs).

Capture one complete, immutable Git evidence artifact, fence it as untrusted data, and start independent read-only provider reviews. Includes committed, staged, unstaged, and untracked changes without truncation.

Least-cost routing: pick the cheapest eligible (provider, model) candidate that meets the caller's quality tier, capability, and budget constraints, then dispatch it through the normal provider path. Returns the provider response plus a `routing` block (chosen candidate, cost estimate + basis/confidence, rejections, reroutes). Registered only when [least_cost].enabled is true.

Async least-cost routing: select the cheapest eligible (provider, model) candidate synchronously, enqueue it for background execution, and return a pollable job handle plus the `routing` block. Poll with llm_job_status, collect with llm_job_result. Registered only when [least_cost].enabled is true and async jobs are enabled.

Ask one provider CLI to review an answer (starts a validation job; poll job_status, collect job_result).

Delete all gateway session records, optionally scoped to one provider. The tool result confirms record deletion; worktree cleanup observers run asynchronously and may still be in progress. Worktree cleanup runs per session on the processing host for file-backed and PostgreSQL session managers. Both managers stage a caller-hidden cleanup tombstone before cleanup runs and retain a failed removal for retry by the host that owns the worktree, finalizing the record only once Git no longer registers the worktree, read back rather than inferred from the recorded path being absent. File-backed TTL evi…

Create a gateway session record for a provider. NOTE: this is gateway bookkeeping (a plain UUID), not a provider-native session; Codex resume needs a real Codex UUID.

Delete a gateway session record by ID. The tool result confirms record deletion; worktree cleanup observers run asynchronously and may still be in progress. Worktree cleanup runs on the processing host for file-backed and PostgreSQL session managers. Both managers stage a caller-hidden cleanup tombstone before cleanup runs and retain a failed removal for retry by the host that owns the worktree, finalizing the record only once Git no longer registers the worktree, read back rather than inferred from the recorded path being absent. File-backed TTL eviction uses the same tombstone retry path. De…

Get one gateway session record by session ID, including recent request history when available.

List gateway session records and the active session per provider, optionally filtered by provider.

Set or clear the active session for a provider; the active session is used when a request omits sessionId.

Run an explicit judge model over validation results. General validation uses caller-supplied terminal results; review_changes rebuilds its question and results from the owned durable run.

Return the gateway's declared provider CLI contracts; with probeInstalled true, diff against installed --help surfaces to detect flag drift.

Ask two or more provider CLIs to independently validate a question. Starts validation jobs — poll with job_status, collect with job_result (not llm_job_*).

Retrieve the canonically hashed immutable receipt of a terminal cross-LLM validation run by validationId. Returns minted | pending | expired_unminted (no receipt exists and none can be minted) | verification_failed (a stored receipt does not verify against its run) | not_found (own-or-not-found).

Create a remote HTTP/OAuth workspace alias by creating a new local folder or git repo under a configured allowed root. Not for stdio/local provider path access. Requires LLM_GATEWAY_WORKSPACE_ADMIN=1 and OAuth scope workspace:admin.

Inspect a registered remote HTTP/OAuth workspace alias. Does not list files. Not needed for stdio/local provider calls; do not use workspace_* tools to fix local path access.

List registered workspace aliases for remote HTTP/OAuth provider calls. Does not browse files. Stdio/local callers should not use workspace_* tools to fix provider path access; pass local workingDir/addDir/includeDirs directly.

Register an existing local Git repo as a remote HTTP/OAuth workspace alias. Not for stdio/local provider path access. Requires LLM_GATEWAY_WORKSPACE_ADMIN=1 and OAuth scope workspace:admin.