diff --git a/AGENTS.md b/AGENTS.md index 9845119bd..524542707 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -50,7 +50,7 @@ The OpenAPI spec at `docs/api-reference/fabro-api.yaml` is the source of truth f Fabro is an AI-powered workflow orchestration platform. Workflows are defined as Graphviz graphs, where each node is a stage (agent, prompt, command, conditional, human, parallel, etc.) executed by the workflow engine. ### Rust crates (`lib/crates/`) -- **fabro-cli** — CLI entry point. Commands: `run`, `exec`, `serve`, `validate`, `parse`, `cp`, `model`, `doctor`, `install`, `ps`, `system prune`, `llm` +- **fabro-cli** — CLI entry point. Commands: `run`, `exec`, `serve`, `validate`, `parse`, `cp`, `model`, `doctor`, `install`, `ps`, `system prune` - **fabro-workflow** — Core workflow engine. Parses Graphviz graphs, runs stages, manages checkpoints/resume, hooks, retros, and human-in-the-loop interactions - **fabro-agent** — AI coding agent with tool use (Bash, Read, Write, Edit, Glob, Grep, WebFetch). `Sandbox` trait abstracts execution environments - **fabro-server** — Axum HTTP server. Routes for runs, sessions, models, completions, usage. SSE event streaming. Demo mode via header diff --git a/docs/administration/deploy-server.mdx b/docs/administration/deploy-server.mdx index c946b27f5..a5919397a 100644 --- a/docs/administration/deploy-server.mdx +++ b/docs/administration/deploy-server.mdx @@ -125,7 +125,7 @@ Or use the `--server-url` flag: fabro --server-url https://fabro.example.com:3000/api/v1 model list ``` -This applies to commands like `fabro model list`, `fabro llm chat`, and `fabro exec`. See [User Configuration](/reference/user-configuration#mode) for the full options including mTLS setup. +This applies to commands like `fabro model list`, `fabro model test`, and `fabro exec`. See [User Configuration](/reference/user-configuration#mode) for the full options including mTLS setup. ## Next steps diff --git a/docs/changelog/2026-03-02.mdx b/docs/changelog/2026-03-02.mdx index 5ce901351..94cad1f13 100644 --- a/docs/changelog/2026-03-02.mdx +++ b/docs/changelog/2026-03-02.mdx @@ -20,7 +20,7 @@ Persistent chat sessions with SQLite storage. Start a conversation with an agent -- `fabro llm chat` command for interactive multi-turn conversations with any configured model +- Introduced interactive CLI chat sessions via the now-removed `fabro llm chat` command diff --git a/docs/changelog/2026-03-07.mdx b/docs/changelog/2026-03-07.mdx index c6a3a4d1c..6799c39d9 100644 --- a/docs/changelog/2026-03-07.mdx +++ b/docs/changelog/2026-03-07.mdx @@ -7,12 +7,7 @@ date: "2026-03-07" Fabro now exposes a `POST /completions` endpoint for single-turn LLM completions. You can use it for structured output via JSON Schema, one-off prompts, or building custom frontends on top of Fabro's model routing. Streaming uses Anthropic-style SSE events (`message_start`, `content_block_delta`, `message_stop`, etc.), so you get tokens as they're generated rather than waiting for the full response. -The CLI's `fabro llm` commands can now target the server instead of calling providers directly: - -```bash -fabro llm prompt "Summarize this file" --server-url http://localhost:3000 -fabro llm chat --server-url http://localhost:3000 -``` +At the time of this release, the CLI's `fabro llm` commands could target the server instead of calling providers directly. That CLI namespace has since been removed. ## Two new sandbox providers: exe.dev and Sprites @@ -63,13 +58,12 @@ To migrate, regenerate your TypeScript client and update any direct API calls. - New `POST /completions` endpoint for single-turn LLM completions with SSE streaming and structured output via JSON Schema - New `GET /models` endpoint exposes the full LLM model catalog with pagination - New `POST /models/{id}/test` endpoint for testing model connectivity in server mode -- Session endpoints for interactive LLM chat via `fabro llm chat --server-url http://localhost:3000` +- Session endpoints for interactive LLM chat; the old `fabro llm chat` CLI wrapper has since been removed - Verification API reorganized: `/verifications` split into `/verification/criteria` and `/verification/controls` -- `fabro llm prompt --server-url ` routes prompts through the Fabro server -- `fabro llm chat --server-url ` enables interactive chat sessions through the server +- This release added `fabro llm prompt/chat --server-url`, but the `fabro llm` CLI namespace was later removed - `fabro model list --server-url ` fetches the model list from the Fabro server - Added `--goal` arg to `fabro run start` to override the workflow goal from the command line - Turn and tool-call counts now display correctly in non-TTY mode diff --git a/docs/reference/cli.mdx b/docs/reference/cli.mdx index 2cdb0a54b..3629d9649 100644 --- a/docs/reference/cli.mdx +++ b/docs/reference/cli.mdx @@ -33,6 +33,8 @@ output_format = "text" model = "claude-sonnet-4-5" ``` +`[exec]` config applies to `fabro exec`. `[llm]` sets the default workflow model/provider for commands like `fabro run` and `fabro preflight`. + CLI flags always override `user.toml` values, which override hardcoded defaults. --- @@ -255,44 +257,6 @@ Permission levels control which tools are auto-approved: `read-only` allows read --- -## `fabro llm prompt` - -Send a one-shot prompt to an LLM. Accepts a prompt as an argument, via stdin, or both (stdin is prepended). - -```bash -fabro llm prompt "Explain quicksort in one paragraph" -echo "Summarize this:" | fabro llm prompt -fabro llm prompt "Translate to French" -m claude-sonnet-4-5 -o temperature=0.3 -fabro llm prompt -S '{"type":"object","properties":{"name":{"type":"string"}}}' "Extract the name from: John Smith" -``` - -| Argument / Flag | Description | -|---|---| -| `[PROMPT]` | The prompt text (also accepts stdin) | -| `-m, --model ` | Model to use | -| `-s, --system ` | System prompt | -| `--no-stream` | Do not stream output | -| `-u, --usage` | Show token usage | -| `-S, --schema ` | JSON schema for structured output (inline JSON string) | -| `-o, --option ` | Generation options: `temperature`, `max_tokens`, `top_p`, or provider-specific keys | - -## `fabro llm chat` - -Start an interactive multi-turn chat session. In server mode, the session is backed by the Fabro server's session endpoints. - -```bash -fabro llm chat -fabro llm chat -m claude-opus-4-6 -s "You are a helpful coding assistant" -fabro llm chat --server-url http://localhost:3000/api/v1 -``` - -| Flag | Description | -|---|---| -| `-m, --model ` | Model to use | -| `-s, --system ` | System prompt | - ---- - ## `fabro model list` List available LLM models from the built-in catalog. Running `fabro model` with no subcommand also lists models. diff --git a/docs/reference/user-configuration.mdx b/docs/reference/user-configuration.mdx index bd27dc48f..33646a08b 100644 --- a/docs/reference/user-configuration.mdx +++ b/docs/reference/user-configuration.mdx @@ -118,14 +118,15 @@ Tools outside the permission level are interactively prompted (if a TTY is prese ## `[llm]` section -Defaults for `fabro llm prompt` and `fabro llm chat`. +Defaults for workflow model selection in commands like `fabro run` and `fabro preflight`. | Key | Description | Values | Default | |---|---|---|---| | `model` | Model name | Any model ID from `fabro model list` | Per provider | +| `provider` | Provider name | `"anthropic"`, `"openai"`, `"gemini"`, etc. | Auto-inferred from model/catalog | -The `[llm]` section only sets the default model. Use `[exec]` to configure provider, permissions, and output format for `fabro exec`. +Use `[exec]` to configure provider, permissions, and output format for `fabro exec`. Use `[llm]` for workflow-oriented defaults. ## `[log]` section