> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fabro.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Shared-checkout parallelism, Fireworks, and resume history

<Warning>
  **Parallel branches now share one checkout, and `join_policy` was removed.** Remove `join_policy` from parallel nodes; fan-out now waits for every branch. Keep file-writing branches read-only or assign disjoint paths, and update fan-in logic to consume `parallel.results` instead of a selected branch workspace or `parallel_results.json`.
</Warning>

## Shared-checkout parallel execution

Parallel branches now run concurrently in the run's existing sandbox and working directory instead of creating branch-specific Git worktrees. Each branch still receives isolated context updates, returned in outgoing-edge order under `parallel.results`, while a prompted fan-in can synthesize the complete typed result array. Promptless fan-in nodes act as barriers and never select, restore, or merge workspace state.

## Fireworks AI

Fireworks AI is now an opt-in built-in provider with a curated serverless catalog for Kimi, DeepSeek, GLM, MiniMax, Qwen, and GPT-OSS models. The integration uses the existing OpenAI-compatible path, supports cached-input accounting, and works with the normal provider login, secret storage, diagnostics, and model-testing flows.

```toml title="settings.toml" theme={"languages":{"custom":["/languages/dot.json","/languages/fabro.json"]}}
[llm.providers.fireworks]
enabled = true
```

## Resumed stages keep their history

When a run resumes after a node was cancelled or lost mid-flight, the replay now starts a new stage execution such as `work@2` instead of clearing and reusing `work@1`. The earlier execution keeps its events, session, output, timing, billing, and terminal state, and the stage UI links the new execution back to the one it resumed from.

## More

<Accordion title="API">
  * `GET /api/v1/runs/{id}/events` now supports descending cursor pagination with `order=desc` and `before_seq`; `fabro run events --tail` uses it to fetch only the newest events
  * Completion usage now reports disjoint input, output, reasoning, cache-read, and cache-write token buckets
  * Model responses now advertise exact `controls.reasoning_effort` values, and completion requests—including structured completions—validate and forward reasoning effort with a `400` response for unsupported values
</Accordion>

<Accordion title="Fixes">
  * Event history scans now use seek-based pagination with bounded cursors, avoiding full-history work and incorrect results for oversized sequence values
  * Preflight now prefers providers that are actually ready while preserving explicit provider pins and useful diagnostics for unavailable offerings
  * OpenAI-compatible agent providers now receive compatible file-edit and tool schemas
  * Large values inside parallel branch results now stay available to fan-in prompts through normal artifact storage
</Accordion>

<Accordion title="Improvements">
  * Added `claude-opus-5` to the first-party Anthropic model catalog; the `opus` and `claude-opus` aliases now resolve to Opus 5
  * Added `gpt-sol`, `gpt-terra`, and `gpt-luna` aliases for GPT-5.6 offerings
  * Added portable `glm`, `glm52`, `glm5.2`, `deepseek`, and `deepseek-flash` aliases across direct and OpenRouter offerings
</Accordion>