nodmix 2026.5.25

package/docs/cli/infer.md

@@ -0,0 +1,364 @@
+---
+summary: "Infer-first CLI for provider-backed model, image, audio, TTS, video, web, and embedding workflows"
+read_when:
+  - Adding or modifying `nodmix infer` commands
+  - Designing stable headless capability automation
+title: "Inference CLI"
+---
+
+`nodmix infer` is the canonical headless surface for provider-backed inference workflows.
+
+It intentionally exposes capability families, not raw gateway RPC names and not raw agent tool ids.
+
+## Turn infer into a skill
+
+Copy and paste this to an agent:
+
+```text
+Read https://docs.nodmix.ai/cli/infer, then create a skill that routes my common workflows to `nodmix infer`.
+Focus on model runs, image generation, video generation, audio transcription, TTS, web search, and embeddings.
+```
+
+A good infer-based skill should:
+
+- map common user intents to the correct infer subcommand
+- include a few canonical infer examples for the workflows it covers
+- prefer `nodmix infer ...` in examples and suggestions
+- avoid re-documenting the entire infer surface inside the skill body
+
+Typical infer-focused skill coverage:
+
+- `nodmix infer model run`
+- `nodmix infer image generate`
+- `nodmix infer audio transcribe`
+- `nodmix infer tts convert`
+- `nodmix infer web search`
+- `nodmix infer embedding create`
+
+## Why use infer
+
+`nodmix infer` provides one consistent CLI for provider-backed inference tasks inside Nodmix.
+
+Benefits:
+
+- Use the providers and models already configured in Nodmix instead of wiring up one-off wrappers for each backend.
+- Keep model, image, audio transcription, TTS, video, web, and embedding workflows under one command tree.
+- Use a stable `--json` output shape for scripts, automation, and agent-driven workflows.
+- Prefer a first-party Nodmix surface when the task is fundamentally "run inference."
+- Use the normal local path without requiring the gateway for most infer commands.
+
+For end-to-end provider checks, prefer `nodmix infer ...` once lower-level
+provider tests are green. It exercises the shipped CLI, config loading,
+default-agent resolution, bundled plugin activation, and the shared capability
+runtime before the provider request is made.
+
+## Command tree
+
+```text
+ nodmix infer
+  list
+  inspect
+
+  model
+    run
+    list
+    inspect
+    providers
+    auth login
+    auth logout
+    auth status
+
+  image
+    generate
+    edit
+    describe
+    describe-many
+    providers
+
+  audio
+    transcribe
+    providers
+
+  tts
+    convert
+    voices
+    providers
+    status
+    enable
+    disable
+    set-provider
+
+  video
+    generate
+    describe
+    providers
+
+  web
+    search
+    fetch
+    providers
+
+  embedding
+    create
+    providers
+```
+
+## Common tasks
+
+This table maps common inference tasks to the corresponding infer command.
+
+| Task                          | Command                                                                                       | Notes                                                 |
+| ----------------------------- | --------------------------------------------------------------------------------------------- | ----------------------------------------------------- |
+| Run a text/model prompt       | `nodmix infer model run --prompt "..." --json`                                              | Uses the normal local path by default                 |
+| Run a model prompt on images  | `nodmix infer model run --prompt "Describe this" --file ./image.png --model provider/model` | Repeat `--file` for multiple image inputs             |
+| Generate an image             | `nodmix infer image generate --prompt "..." --json`                                         | Use `image edit` when starting from an existing file  |
+| Describe an image file or URL | `nodmix infer image describe --file ./image.png --prompt "..." --json`                      | `--model` must be an image-capable `<provider/model>` |
+| Transcribe audio              | `nodmix infer audio transcribe --file ./memo.m4a --json`                                    | `--model` must be `<provider/model>`                  |
+| Synthesize speech             | `nodmix infer tts convert --text "..." --output ./speech.mp3 --json`                        | `tts status` is gateway-oriented                      |
+| Generate a video              | `nodmix infer video generate --prompt "..." --json`                                         | Supports provider hints such as `--resolution`        |
+| Describe a video file         | `nodmix infer video describe --file ./clip.mp4 --json`                                      | `--model` must be `<provider/model>`                  |
+| Search the web                | `nodmix infer web search --query "..." --json`                                              |                                                       |
+| Fetch a web page              | `nodmix infer web fetch --url https://example.com --json`                                   |                                                       |
+| Create embeddings             | `nodmix infer embedding create --text "..." --json`                                         |                                                       |
+
+## Behavior
+
+- `nodmix infer ...` is the primary CLI surface for these workflows.
+- Use `--json` when the output will be consumed by another command or script.
+- Use `--provider` or `--model provider/model` when a specific backend is required.
+- Use `model run --thinking <level>` to pass a one-shot thinking/reasoning level (`off`, `minimal`, `low`, `medium`, `high`, `adaptive`, `xhigh`, or `max`) while keeping the run raw.
+- For `image describe`, `audio transcribe`, and `video describe`, `--model` must use the form `<provider/model>`.
+- For `image describe`, `--file` accepts local paths and HTTP(S) image URLs. Remote URLs use the normal media-fetch SSRF policy.
+- For `image describe`, an explicit `--model` runs that provider/model directly. The model must be image-capable in the model catalog or provider config. `codex/<model>` runs a bounded Codex app-server image-understanding turn; `openai-codex/<model>` uses the OpenAI Codex OAuth provider path.
+- Stateless execution commands default to local.
+- Gateway-managed state commands default to gateway.
+- The normal local path does not require the gateway to be running.
+- Local `model run` is a lean one-shot provider completion. It resolves the configured agent model and auth, but does not start a chat-agent turn, load tools, or open bundled MCP servers.
+- `model run --file` accepts image files, detects their MIME type, and sends them with the supplied prompt to the selected model. Repeat `--file` for multiple images.
+- `model run --file` rejects non-image inputs. Use `infer audio transcribe` for audio files and `infer video describe` for video files.
+- `model run --gateway` exercises Gateway routing, saved auth, provider selection, and the embedded runtime, but still runs as a raw model probe: it sends the supplied prompt and any image attachments without prior session transcript, bootstrap/AGENTS context, context-engine assembly, tools, or bundled MCP servers.
+- `model run --gateway --model <provider/model>` requires a trusted operator gateway credential because the request asks the Gateway to run a one-off provider/model override.
+- Local `model run --thinking` uses the lean provider-completion path; provider-specific levels such as `adaptive` and `max` are mapped to the closest portable simple-completion level.
+
+## Model
+
+Use `model` for provider-backed text inference and model/provider inspection.
+
+```bash
+nodmix infer model run --prompt "Reply with exactly: smoke-ok" --json
+nodmix infer model run --prompt "Summarize this changelog entry" --model openai/gpt-5.4 --json
+nodmix infer model run --prompt "Describe this image in one sentence" --file ./photo.jpg --model google/gemini-2.5-flash --json
+nodmix infer model run --prompt "Use more reasoning here" --thinking high --json
+nodmix infer model providers --json
+nodmix infer model inspect --name gpt-5.5 --json
+```
+
+Use full `<provider/model>` refs to smoke-test a specific provider without
+starting the Gateway or loading the full agent tool surface:
+
+```bash
+nodmix infer model run --local --model anthropic/claude-sonnet-4-6 --prompt "Reply with exactly: pong" --json
+nodmix infer model run --local --model cerebras/zai-glm-4.7 --prompt "Reply with exactly: pong" --json
+nodmix infer model run --local --model google/gemini-2.5-flash --prompt "Reply with exactly: pong" --json
+nodmix infer model run --local --model groq/llama-3.1-8b-instant --prompt "Reply with exactly: pong" --json
+nodmix infer model run --local --model mistral/mistral-medium-3-5 --prompt "Reply with exactly: pong" --json
+nodmix infer model run --local --model mistral/mistral-small-latest --prompt "Reply with exactly: pong" --json
+nodmix infer model run --local --model openai/gpt-4.1 --prompt "Reply with exactly: pong" --json
+nodmix infer model run --local --model ollama/qwen2.5vl:7b --prompt "Describe this image." --file ./photo.jpg --json
+```
+
+Notes:
+
+- Local `model run` is the narrowest CLI smoke for provider/model/auth health because, for non-Codex providers, it sends only the supplied prompt to the selected model.
+- Local `model run --model <provider/model>` can use exact bundled static catalog rows from `models list --all` before that provider is written to config. Provider auth is still required; missing credentials fail as auth errors, not `Unknown model`.
+- For Mistral Medium 3.5 reasoning probes, leave temperature unset/default. Mistral rejects `reasoning_effort="high"` plus `temperature: 0`; use `mistral/mistral-medium-3-5` with default temperature or a non-zero reasoning-mode value such as `0.7`.
+- `openai-codex/*` local probes are the narrow exception: Nodmix adds a minimal system instruction so the Codex Responses transport can populate its required `instructions` field, without adding full agent context, tools, memory, or session transcript.
+- Local `model run --file` keeps that lean path and attaches image content directly to the single user message. Common image files such as PNG, JPEG, and WebP work when their MIME type is detected as `image/*`; unsupported or unrecognized files fail before the provider is called.
+- `model run --file` is best when you want to test the selected multimodal text model directly. Use `infer image describe` when you want Nodmix's image-understanding provider selection and default image-model routing.
+- The selected model must support image input; text-only models may reject the request at the provider layer.
+- `model run --prompt` must contain non-whitespace text; empty prompts are rejected before local providers or the Gateway are called.
+- Local `model run` exits non-zero when the provider returns no text output, so unreachable local providers and empty completions do not look like successful probes.
+- Use `model run --gateway` when you need to test Gateway routing, agent-runtime setup, or Gateway-managed provider state while keeping the model input raw. Use `nodmix agent` or chat surfaces when you want the full agent context, tools, memory, and session transcript.
+- `model auth login`, `model auth logout`, and `model auth status` manage saved provider auth state.
+
+## Image
+
+Use `image` for generation, edit, and description.
+
+```bash
+nodmix infer image generate --prompt "friendly lobster illustration" --json
+nodmix infer image generate --prompt "cinematic product photo of headphones" --json
+nodmix infer image generate --model openai/gpt-image-1.5 --output-format png --background transparent --prompt "simple red circle sticker on a transparent background" --json
+nodmix infer image generate --prompt "slow image backend" --timeout-ms 180000 --json
+nodmix infer image edit --file ./logo.png --model openai/gpt-image-1.5 --output-format png --background transparent --prompt "keep the logo, remove the background" --json
+nodmix infer image edit --file ./poster.png --prompt "make this a vertical story ad" --size 2160x3840 --aspect-ratio 9:16 --resolution 4K --json
+nodmix infer image describe --file ./photo.jpg --json
+nodmix infer image describe --file https://example.com/photo.png --json
+nodmix infer image describe --file ./receipt.jpg --prompt "Extract the merchant, date, and total" --json
+nodmix infer image describe-many --file ./before.png --file ./after.png --prompt "Compare the screenshots and list visible UI changes" --json
+nodmix infer image describe --file ./ui-screenshot.png --model openai/gpt-4.1-mini --json
+nodmix infer image describe --file ./photo.jpg --model ollama/qwen2.5vl:7b --prompt "Describe the image in one sentence" --timeout-ms 300000 --json
+```
+
+Notes:
+
+- Use `image edit` when starting from existing input files.
+- Use `--size`, `--aspect-ratio`, or `--resolution` with `image edit` for
+  providers/models that support geometry hints on reference-image edits.
+- Use `--output-format png --background transparent` with
+  `--model openai/gpt-image-1.5` for transparent-background OpenAI PNG output;
+  `--openai-background` remains available as an OpenAI-specific alias. Providers
+  that do not declare background support report the hint as an ignored override.
+- Use `image providers --json` to verify which bundled image providers are
+  discoverable, configured, selected, and which generation/edit capabilities
+  each provider exposes.
+- Use `image generate --model <provider/model> --json` as the narrowest live
+  CLI smoke for image generation changes. Example:
+
+  ```bash
+  nodmix infer image providers --json
+  nodmix infer image generate \
+    --model google/gemini-3.1-flash-image-preview \
+    --prompt "Minimal flat test image: one blue square on a white background, no text." \
+    --output ./nodmix-infer-image-smoke.png \
+    --json
+  ```
+
+  The JSON response reports `ok`, `provider`, `model`, `attempts`, and written
+  output paths. When `--output` is set, the final extension may follow the
+  provider's returned MIME type.
+
+- For `image describe` and `image describe-many`, use `--prompt` to give the vision model a task-specific instruction such as OCR, comparison, UI inspection, or concise captioning.
+- Use `--timeout-ms` with slow local vision models or cold Ollama starts.
+- For `image describe`, `--model` must be an image-capable `<provider/model>`.
+- For local Ollama vision models, pull the model first and set `OLLAMA_API_KEY` to any placeholder value, for example `ollama-local`. See [Ollama](/providers/ollama#vision-and-image-description).
+
+## Audio
+
+Use `audio` for file transcription.
+
+```bash
+nodmix infer audio transcribe --file ./memo.m4a --json
+nodmix infer audio transcribe --file ./team-sync.m4a --language en --prompt "Focus on names and action items" --json
+nodmix infer audio transcribe --file ./memo.m4a --model openai/whisper-1 --json
+```
+
+Notes:
+
+- `audio transcribe` is for file transcription, not realtime session management.
+- `--model` must be `<provider/model>`.
+
+## TTS
+
+Use `tts` for speech synthesis and TTS provider state.
+
+```bash
+nodmix infer tts convert --text "hello from nodmix" --output ./hello.mp3 --json
+nodmix infer tts convert --text "Your build is complete" --output ./build-complete.mp3 --json
+nodmix infer tts providers --json
+nodmix infer tts status --json
+```
+
+Notes:
+
+- `tts status` defaults to gateway because it reflects gateway-managed TTS state.
+- Use `tts providers`, `tts voices`, and `tts set-provider` to inspect and configure TTS behavior.
+
+## Video
+
+Use `video` for generation and description.
+
+```bash
+nodmix infer video generate --prompt "cinematic sunset over the ocean" --json
+nodmix infer video generate --prompt "slow drone shot over a forest lake" --resolution 768P --duration 6 --json
+nodmix infer video describe --file ./clip.mp4 --json
+nodmix infer video describe --file ./clip.mp4 --model openai/gpt-4.1-mini --json
+```
+
+Notes:
+
+- `video generate` accepts `--size`, `--aspect-ratio`, `--resolution`, `--duration`, `--audio`, `--watermark`, and `--timeout-ms` and forwards them to the video-generation runtime.
+- `--model` must be `<provider/model>` for `video describe`.
+
+## Web
+
+Use `web` for search and fetch workflows.
+
+```bash
+nodmix infer web search --query "Nodmix docs" --json
+nodmix infer web search --query "Nodmix infer web providers" --json
+nodmix infer web fetch --url https://docs.nodmix.ai/cli/infer --json
+nodmix infer web providers --json
+```
+
+Notes:
+
+- Use `web providers` to inspect available, configured, and selected providers.
+
+## Embedding
+
+Use `embedding` for vector creation and embedding provider inspection.
+
+```bash
+nodmix infer embedding create --text "friendly lobster" --json
+nodmix infer embedding create --text "customer support ticket: delayed shipment" --model openai/text-embedding-3-large --json
+nodmix infer embedding providers --json
+```
+
+## JSON output
+
+Infer commands normalize JSON output under a shared envelope:
+
+```json
+{
+  "ok": true,
+  "capability": "image.generate",
+  "transport": "local",
+  "provider": "openai",
+  "model": "gpt-image-2",
+  "attempts": [],
+  "outputs": []
+}
+```
+
+Top-level fields are stable:
+
+- `ok`
+- `capability`
+- `transport`
+- `provider`
+- `model`
+- `attempts`
+- `outputs`
+- `error`
+
+For generated media commands, `outputs` contains files written by Nodmix. Use
+the `path`, `mimeType`, `size`, and any media-specific dimensions in that array
+for automation instead of parsing human-readable stdout.
+
+## Common pitfalls
+
+```bash
+# Bad
+nodmix infer media image generate --prompt "friendly lobster"
+
+# Good
+nodmix infer image generate --prompt "friendly lobster"
+```
+
+```bash
+# Bad
+nodmix infer audio transcribe --file ./memo.m4a --model whisper-1 --json
+
+# Good
+nodmix infer audio transcribe --file ./memo.m4a --model openai/whisper-1 --json
+```
+
+## Notes
+
+- `nodmix capability ...` is an alias for `nodmix infer ...`.
+
+## Related
+
+- [CLI reference](/cli)
+- [Models](/concepts/models)

package/docs/cli/logs.md

@@ -0,0 +1,65 @@
+---
+summary: "CLI reference for `nodmix logs` (tail gateway logs via RPC)"
+read_when:
+  - You need to tail Gateway logs remotely (without SSH)
+  - You want JSON log lines for tooling
+title: "Logs"
+---
+
+# `nodmix logs`
+
+Tail Gateway file logs over RPC (works in remote mode).
+
+Related:
+
+- Logging overview: [Logging](/logging)
+- Gateway CLI: [gateway](/cli/gateway)
+
+## Options
+
+- `--limit <n>`: maximum number of log lines to return (default `200`)
+- `--max-bytes <n>`: maximum bytes to read from the log file (default `250000`)
+- `--follow`: follow the log stream
+- `--interval <ms>`: polling interval while following (default `1000`)
+- `--json`: emit line-delimited JSON events
+- `--plain`: plain text output without styled formatting
+- `--no-color`: disable ANSI colors
+- `--local-time`: render timestamps in your local timezone
+
+## Shared Gateway RPC options
+
+`nodmix logs` also accepts the standard Gateway client flags:
+
+- `--url <url>`: Gateway WebSocket URL
+- `--token <token>`: Gateway token
+- `--timeout <ms>`: timeout in ms (default `30000`)
+- `--expect-final`: wait for a final response when the Gateway call is agent-backed
+
+When you pass `--url`, the CLI does not auto-apply config or environment credentials. Include `--token` explicitly if the target Gateway requires auth.
+
+## Examples
+
+```bash
+nodmix logs
+nodmix logs --follow
+nodmix logs --follow --interval 2000
+nodmix logs --limit 500 --max-bytes 500000
+nodmix logs --json
+nodmix logs --plain
+nodmix logs --no-color
+nodmix logs --limit 500
+nodmix logs --local-time
+nodmix logs --follow --local-time
+nodmix logs --url ws://127.0.0.1:18789 --token "$NODMIX_GATEWAY_TOKEN"
+```
+
+## Notes
+
+- Use `--local-time` to render timestamps in your local timezone.
+- If the implicit local loopback Gateway asks for pairing, closes during connect, or times out before `logs.tail` answers, `nodmix logs` falls back to the configured Gateway file log automatically. Explicit `--url` targets do not use this fallback.
+- When using `--follow`, transient gateway disconnects (WebSocket close, timeout, connection drop) trigger automatic reconnection with exponential backoff (up to 8 retries, capped at 30 s between attempts). A warning is printed to stderr on each retry, and a `[logs] gateway reconnected` notice is printed once a poll succeeds. In `--json` mode both the retry warning and the reconnect transition are emitted as `{"type":"notice"}` records on stderr. Non-recoverable errors (auth failure, bad configuration) still exit immediately.
+
+## Related
+
+- [CLI reference](/cli)
+- [Gateway logging](/gateway/logging)