Chat-completion passthrough to the cheap/local model — cheapest way to offload a small mechanical task. Pass prompt (+ optional system) for one-shot completions, or messages for a full OpenAI-style conversation (few-shot examples, multi-turn).

Summarize files or text with the local model. File contents are read server-side and NEVER enter your context — only the summaries come back. Prefer this over reading large files yourself.

Extract structured data from text/files with the local model. Optionally validate output against a JSON schema (one automatic retry on invalid output).

Classify text/file content into one or more labels with the local model.

Decision-model scoring (ollama /v1/systemone — clef / clef-flash / nimble / tev). Scores 1–64 TYPED questions about a state in ONE forward pass and returns calibrated probabilities per option — no text generation, no output parsing, no retries. Prefer over classify when a decision model is available: you get real probabilities instead of parsed JSON. Question types: 'choice' (criteria maps option keys→descriptions, null uses the key), 'score' (numeric scale), 'noul' (true/false). Requires an ollama provider running a decision model; a normal chat model returns an error. State is read server-side — files never enter your context.

Run one instruction over many files with the local model (batch job). output='report': get per-file results. output='stage_writes': the model rewrites each file and every change is staged as a diff for your review — NOTHING hits disk until you commit_write.

Embed text/files with an embedding model on the local provider — for semantic dedup, clustering, or find-similar work that generation can't do. Needs an embedding model (e.g. nomic-embed-text, embeddinggemma) — check list_models capabilities. Returns raw vectors; cosine-similarity them yourself.

Estimate token counts for text/files (chars/4 heuristic — ±20% vs a real tokenizer; for input sizing, not billing). Use before run_local_agent/summarize to check fit vs num_ctx.

Delegate a low-complexity task to the LOCAL SUBAGENT: the cheap model runs its own tool loop (read_file, list_dir, search_files, stage_write, whitelisted run_command, plus any registered dynamic tools) entirely server-side. File contents and intermediate steps never enter your context — you get back a compact final answer + staged-write op ids to review. Use for mechanical, monotonous, or bulk work: finding things, transforming files, answering questions over many files. Do NOT delegate work needing real reasoning, security judgment, or architecture decisions.

Have the local model rewrite/create ONE file per your instruction, staged for review. Returns an op id + diff. Nothing is written until commit_write. Use for mechanical rewrites where the file content shouldn't flow through your own context.

Like propose_write, but the local model emits SEARCH/REPLACE hunks instead of the whole file — much more reliable on large files and small models. Server applies the hunks and stages the result as a normal op (same diff/commit flow).

Stage a file DELETION for review — nothing touches disk until commit_write. The diff shows all lines removed; uncommit_write restores the file afterwards. Use for dead-code cleanup instead of emptying a file with propose_write.

List pending staged writes (proposed changes not yet on disk).

Show the unified diff for a staged write op.

Switch the server's write posture. 'propose' (default): staged writes only — commit_write is refused; you apply diffs with your own tools. 'write': commit_write applies staged ops to disk. persist=true also writes the choice to the server config file.

Apply a staged write to disk (atomic: tmp+rename). Call only AFTER reviewing the diff with get_diff. Refuses if the file changed since it was staged — pass force=true to overwrite anyway. Only works when write_mode is 'write' — do NOT call it in 'propose' mode (it refuses and the permission prompt would just show an opaque op_id). path and summary are REQUIRED because the user's approval prompt only shows tool args — make them say exactly what is being written. Pass ops: [{op_id, path, summary}] instead to commit a batch in ONE approval — use it for map_files stage_writes output so the user sees the whole set at once.

Run a whitelisted command against a staged write WITHOUT touching the target file: the op's content is materialized to a temp file in the same directory (import/path resolution matches the real file), '{file}' in argv is replaced by the temp path (appended if absent), and the command runs under the command_whitelist. Use it to typecheck/lint a staged op before commit_write — running a checker on the original path sees the OLD on-disk content, not the stage. restore_paths lists files the command may rewrite (e.g. an auto-updated lint baseline) — snapshotted before, restored after. The temp file is always removed.

Drop a staged write op without applying it.

List recently committed writes (last 20) — for revert_write.

Undo a committed write: stages a NEW op restoring the pre-commit content (goes through normal review — commit_write applies it).

One-call undo of a committed write — restores the pre-commit content atomically (deletes files the commit created), no re-staging/re-commit needed. Refuses if the file changed since the commit unless force:true. Requires write_mode 'write' — in 'propose' mode use revert_write + commit_write for the reviewed path.

List models available on a provider. For ollama providers includes size, parameter count, quantization and capabilities — use this plus get_system_resources to pick the biggest model that fits VRAM.

Report host RAM + GPU VRAM and currently-loaded models. Only works for LOCAL ollama providers — returns {unavailable: true} for remote/openai-type providers. Use before picking a model or num_ctx for heavy jobs. Includes ollama_gpu: which GPU(s) the ollama server is pinned to (env) or observed using (runner process device fds).

Download a model on an ollama provider (e.g. 'qwen2.5-coder:7b'). Runs as a background job — returns a job_id; poll progress with get_job. Only for ollama providers.

Search the public ollama registry (ollama.com) for models to pull_model. Returns name, description, capability chips (tools/thinking/vision), available parameter sizes, and whether the family is already installed. Requires internet access.

List pullable tags for a model in the ollama registry (e.g. model 'gemma4' -> e4b, 12b, 26b, ...). With include_sizes=true, fetches each tag's download size from the registry manifest API (one request per tag). Requires internet access.

Download a model from Hugging Face via the hf CLI (for llama.cpp/TabbyAPI/vLLM-style servers where pull_model doesn't apply). Runs as a background job — poll with get_job. e.g. repo 'bartowski/Qwen2.5-Coder-7B-Instruct-GGUF' with include 'Q4_K_M'.

Get status/progress of a background job (e.g. a model pull).

List background jobs (most recent first).

Sleep for a number of seconds (max 600), then return. With job_id, returns early as soon as that job reaches done/error — use to poll pull_model/run_local_agent without busy-looping get_job.

Steer a running background job: pause (halt between agent steps), resume, cancel (aborts in-flight work too), or inject (append an operator instruction the local agent sees on its next step — for course-correcting a run_local_agent mid-flight).

Analyze installed models against detected hardware and recommend a default_model for a provider. Prefers tool-calling models that fit the target GPU's free VRAM (or free RAM for CPU-only). With apply=true, writes the pick to the provider's default_model in the config file AND applies it live to this server.

Permanently delete a model from an ollama provider (DELETE /api/delete). Irreversible — the model must be re-pulled to restore. Refuses to delete the provider's default_model or a currently-loaded model unless force=true.

Bulk-delete old models from an ollama provider. dry_run=true (default) only reports candidates. Always keeps: keep[] ids, the provider default_model, currently-loaded models, and the keep_recent most recently modified others. With dry_run=false, deletes the rest.

Unload a model from VRAM on an ollama provider (frees memory immediately).

Session totals: local LLM calls, tokens consumed on the cheap model, and delegated_bytes (bytes of file content processed server-side that never entered your context — i.e. the savings).

Show this server's config: providers (sanitized), allowed_roots, feature flags, limits. Call this first if unsure what's configured.

Register a NEW tool that the local model can call during run_local_agent (persists for this server session; persist=true saves it across restarts). kind='shell': an executable + argv template with ${param} placeholders (execFile, no shell). kind='js': a JS function body run in node:vm as (body)(args). Requires LOCAL_LLM_DYNAMIC_TOOLS=1 on the server.

Remove a runtime-registered dynamic tool.

List runtime-registered tools available to the local agent.

Show which commands the local agent's run_command tool may execute (argv-level whitelist, no shell).

Add/remove commands the local agent may run. Writes the server config file — prefer tight allow_args over broad access. This tool should stay in Devin's 'ask' permissions.