Merge branch 'docs/update-models-and-cli-reference'

.claude/skills/docs/watermark

@@ -1 +1 @@
-d6fdeb81353d3bdf86a87fc499a2a5889206524b
+45ff3da4e05c7c67c909d7b860c7764b34e6a342

docs/core-concepts/models.mdx

@@ -14,7 +14,8 @@ No single model is best at everything. Fabro lets you assign the right model to
 | Model | Provider | Aliases | Context | Cost (in/out per Mtok) | Speed |
 |---|---|---|---|---|---|
 | `claude-opus-4-6` | anthropic | `opus`, `claude-opus` | 1M | $15.00 / $75.00 | 25 tok/s |
-| `claude-sonnet-4-5` | anthropic | `sonnet`, `claude-sonnet` | 200K | $3.00 / $15.00 | 50 tok/s |
+| `claude-sonnet-4-6` | anthropic | `sonnet`, `claude-sonnet` | 200K | $3.00 / $15.00 | 50 tok/s |
+| `claude-sonnet-4-5` | anthropic | | 200K | $3.00 / $15.00 | 50 tok/s |
 | `claude-haiku-4-5` | anthropic | `haiku`, `claude-haiku` | 200K | $0.80 / $4.00 | 100 tok/s |
 | `gpt-5.2` | openai | `gpt5` | 1M | $1.80 / $14.00 | 65 tok/s |
 | `gpt-5-mini` | openai | `gpt5-mini` | 1M | $0.20 / $2.00 | 70 tok/s |
@@ -37,12 +38,12 @@ Each provider requires its own API key set via environment variable (e.g. `ANTHR
 
 ## Default models
 
-When no model is specified, the `fabro exec` command uses a default model based on the provider:
+When no model or provider is specified, Fabro auto-detects the provider by checking which API keys are configured, using precedence order Anthropic > OpenAI > Gemini. If no keys are found, it falls back to Anthropic. Each provider has a default model:
 
 | Provider | Default model |
 |---|---|
-| `anthropic` | `claude-opus-4-6` |
-| `openai` | `gpt-5.2-codex` |
+| `anthropic` | `claude-sonnet-4-6` |
+| `openai` | `gpt-5.4` |
 | `gemini` | `gemini-3.1-pro-preview` |
 | `kimi` | `kimi-k2.5` |
 | `zai` | `glm-4.7` |

docs/reference/cli.mdx

@@ -143,7 +143,7 @@ fabro exec "Refactor the auth module" --permissions full --auto-approve
 | Argument / Flag | Description | Default |
 |---|---|---|
 | `<PROMPT>` | Task prompt (required) | — |
-| `--provider <PROVIDER>` | LLM provider | `anthropic` |
+| `--provider <PROVIDER>` | LLM provider | Auto-detected from configured API keys (see [default models](/core-concepts/models#default-models)) |
 | `--model <MODEL>` | Model name | Per provider (see below) |
 | `--permissions <LEVEL>` | Permission level: `read-only`, `read-write`, or `full` | `read-write` |
 | `--auto-approve` | Skip interactive prompts; deny tools outside permission level | — |
@@ -690,14 +690,34 @@ fabro asset cp <RUN_ID>:report.html ./output    # specific file
 
 When copying all assets in flat mode, filenames must be unique across nodes. Use `--tree` or `--node` to disambiguate.
 
+## `fabro provider login`
+
+Re-authenticate with an LLM provider without re-running the full install wizard. Useful when tokens expire or when switching accounts.
+
+```bash
+fabro provider login --provider openai
+fabro provider login --provider anthropic
+```
+
+| Flag | Description |
+|---|---|
+| `--provider <PROVIDER>` | LLM provider to authenticate with (required) |
+
+For OpenAI, this launches a browser-based OAuth PKCE flow with an automatic fallback to manual API key entry. All other providers prompt for an API key with validation. Credentials are merged non-destructively into `~/.fabro/.env`.
+
 ## `fabro install`
 
 Interactive setup wizard that walks you through configuring API keys and validating your environment. Runs `fabro doctor` with live probes after setup to validate the configuration.
 
 ```bash
 fabro install
+fabro install --web-url https://fabro.example.com
 ```
 
+| Flag | Description | Default |
+|---|---|---|
+| `--web-url <URL>` | Web UI base URL for OAuth callback endpoints | `http://localhost:5173` |
+
 ---
 
 ## `fabro secret set`