diff --git a/.claude/skills/changelog/watermark b/.claude/skills/changelog/watermark index 6d7216bae..a443028b4 100644 --- a/.claude/skills/changelog/watermark +++ b/.claude/skills/changelog/watermark @@ -1 +1 @@ -45ff3da4e05c7c67c909d7b860c7764b34e6a342 +ed651dcd571699e92162cf657b8eca42d7a6d6b1 diff --git a/docs/changelog/2026-03-19.mdx b/docs/changelog/2026-03-19.mdx index b8075bb45..6567f1ab8 100644 --- a/docs/changelog/2026-03-19.mdx +++ b/docs/changelog/2026-03-19.mdx @@ -1,5 +1,5 @@ --- -title: "Provider login and auto-detect default provider" +title: "Provider login, auto-detect provider, and fabro wait" date: "2026-03-19" --- @@ -17,12 +17,26 @@ For OpenAI, this launches the browser-based OAuth PKCE flow with an automatic fa The CLI now checks which providers have API keys configured and automatically selects the best available one, using precedence order Anthropic > OpenAI > Gemini. Previously, running commands without an explicit `--provider` flag always defaulted to Anthropic, which caused errors for users who only had OpenAI or Gemini keys configured. +## `fabro wait` + +A new `fabro wait` subcommand blocks until a workflow run reaches a terminal state and exits with a code reflecting the outcome — analogous to `docker wait`. Accepts a run ID prefix or workflow name, with an optional `--timeout` flag and `--json` output mode for scripting. + +```bash +fabro wait abc123 --timeout 300 +``` + ## More - Default Anthropic model changed from `claude-opus-4-6` to `claude-sonnet-4-6` -- Removed OpenSSL runtime dependency — the CLI binary no longer dynamically links against `libssl` or `libcrypto`, so it runs on machines without OpenSSL v3 installed +- Removed OpenSSL runtime dependency — the CLI binary no longer dynamically links against `libssl` or `libcrypto` - Added `--web-url` flag to `fabro install` for specifying the web UI base URL for OAuth callbacks +- `fabro ps` now strips markdown headings and "Plan:" prefix from the GOAL column for cleaner output + + + +- Node-level `model` attributes are now validated against the model catalog at parse time, with missing aliases surfaced as warnings +- `reasoning_effort` is now mapped to Anthropic's `output_config.effort` parameter @@ -32,6 +46,8 @@ The CLI now checks which providers have API keys configured and automatically se -- Fixed OAuth callback URLs missing from CLI-generated GitHub App manifests, which caused OAuth login failures in the web UI -- Fixed OpenAI multi-turn conversations failing because `store: false` was incorrectly set for all Responses API requests instead of only the Codex endpoint +- Fixed agent sessions ignoring node-level `model` and `provider` attributes set in stylesheets +- Fixed `fabro upgrade` failing with "No such file or directory" +- Fixed OAuth callback URLs missing from CLI-generated GitHub App manifests +- Fixed OpenAI multi-turn conversations failing because `store: false` was incorrectly set for all Responses API requests diff --git a/docs/changelog/2026-03-20.mdx b/docs/changelog/2026-03-20.mdx new file mode 100644 index 000000000..9ff6053d7 --- /dev/null +++ b/docs/changelog/2026-03-20.mdx @@ -0,0 +1,35 @@ +--- +title: "Composable run lifecycle: create, start, attach" +date: "2026-03-20" +--- + +## `fabro create` / `start` / `attach` + +`fabro run` has been decomposed into three composable primitives following the Docker-style lifecycle model. `fabro create` allocates the run directory, `fabro start` spawns the detached engine process, and `fabro attach` tails progress with live rendering and handles human-in-the-loop interactions. `fabro run` remains the all-in-one command — it now composes these three steps internally, and `--detach` simply skips the attach step. + +This enables new automation patterns: create a run, start it in the background, and attach later — or script CI pipelines that create and start without ever attaching. + +```bash +fabro create my-workflow --goal "Implement feature X" +fabro start +fabro attach +``` + +## More + + +- Added Linux ARM64 (`aarch64-unknown-linux-gnu`) release target +- `fabro logs` and `fabro attach` now show tool details for `spawn_agent`, `use_skill`, `list_dir`, and all remaining agent tools +- Subagent IDs now use short hex strings instead of UUIDs for readability + + + +- `StageStarted` events are now emitted on retry attempts for better observability +- Added bundled `implement-issue` workflow for implementing GitHub issues via `fabro run implement-issue` +- Added bundled `gh-triage` workflow for checking open PRs and issues via `gh` CLI +- Model aliases in graph nodes are now resolved to canonical IDs at parse time + + + +- Updated `tar` crate to 0.4.45 (security fix) + diff --git a/docs/changelog/2026-03-21.mdx b/docs/changelog/2026-03-21.mdx new file mode 100644 index 000000000..fdf2c64e9 --- /dev/null +++ b/docs/changelog/2026-03-21.mdx @@ -0,0 +1,33 @@ +--- +title: "Anthropic fast mode and deep model testing" +date: "2026-03-21" +--- + +## Anthropic fast mode + +You can now enable Anthropic's fast mode for up to 2.5x faster output from Claude Opus 4.6 by setting `speed: fast` in your workflow stylesheet. This is useful for latency-sensitive stages where throughput matters more than cost. + +```dot +graph { + graph [stylesheet="speed=fast"] +} +``` + +## `fabro model test --deep` + +Model validation now supports a `--deep` flag that runs multi-turn tool-use conversations to verify that a provider handles the full agent loop correctly — not just single-turn completions. Tests run concurrently with a progress bar. + +```bash +fabro model test --deep +``` + +## More + + +- Fixed workflow TOML config being lost when running in detach mode +- Fixed edge `thread_id` precedence to match documented fidelity behavior +- Fixed Sonnet 4.5 `reasoning_effort` parameter error by converting to the thinking API format +- Fixed OpenAI reasoning round-trip losing encrypted content by setting `store: false` +- Fixed OpenAI provider incorrectly omitting `store: true` from requests +- Suppressed stderr output noise in detach and create modes + diff --git a/docs/changelog/2026-03-22.mdx b/docs/changelog/2026-03-22.mdx new file mode 100644 index 000000000..272eb8a9b --- /dev/null +++ b/docs/changelog/2026-03-22.mdx @@ -0,0 +1,15 @@ +--- +title: "fabro resume subcommand" +date: "2026-03-22" +--- + +## `fabro resume` + +Resuming workflows previously required constructing a `fabro run --run-branch fabro/run/` invocation manually. The new `fabro resume` subcommand accepts a run ID or prefix directly, matching the ergonomics of `fabro rewind` and `fabro fork`. Checkpoint-file-based resumption is also supported. + +```bash +fabro resume abc123 +fabro resume --checkpoint path/to/checkpoint.json --workflow workflow.fabro +``` + +The unified foreground run path now uses the `create` → `start` → `attach` lifecycle internally, ensuring consistent behavior whether you run, resume, or rewind a workflow. diff --git a/docs/changelog/2026-03-23.mdx b/docs/changelog/2026-03-23.mdx new file mode 100644 index 000000000..e3d47ecda --- /dev/null +++ b/docs/changelog/2026-03-23.mdx @@ -0,0 +1,30 @@ +--- +title: "Unlimited tool rounds and workflow syntax improvements" +date: "2026-03-23" +--- + +## Unlimited agent tool rounds + +Agent stages no longer have an artificial cap on tool rounds per input or subagent turns. Previously, the default limits could cause agents to stop mid-task on complex operations. Both `max_tool_rounds_per_input` and subagent `max_turns` now default to unlimited, so agents run until they complete their work or hit the context window. + +## More + + +- Condition expressions now support quoted strings: `edge [label="status == \"ready\""]` +- `"end"` and `"End"` are now recognized as exit node identifiers alongside `"END"` +- Edge selection now falls back to the default edge when no condition matches, instead of erroring +- `default_max_retries` attribute renamed to `max_retries` on graph-level stylesheets +- Removed `error_policy` and `k_of_n`/`quorum` attributes from parallel nodes — parallel stages now always wait for all branches + + + +- Subagents are now automatically cleaned up when a session closes, preventing orphaned background processes +- All 5xx HTTP status codes from LLM providers are now classified as retryable server errors +- Request timeouts from LLM providers are now treated as non-retryable by default to avoid redundant retries on slow requests + + + +- Fixed workflow slug lookup failing for split and resumed runs +- Fixed split run metadata being lost across engine restarts +- Fixed split run lifecycle lookup returning stale state + diff --git a/docs/changelog/2026-03-26.mdx b/docs/changelog/2026-03-26.mdx new file mode 100644 index 000000000..170451a22 --- /dev/null +++ b/docs/changelog/2026-03-26.mdx @@ -0,0 +1,23 @@ +--- +title: "Pull request pipeline stage and resume reliability" +date: "2026-03-26" +--- + +## Pull request pipeline stage + +Workflows can now automatically create pull requests as part of the run pipeline. When a workflow finishes with code changes, the new `pull_request` pipeline stage creates a PR on the target repository with the run's diff, title, and description — no manual `gh pr create` step needed. This integrates with the existing GitHub App authentication and respects the workflow's git configuration. + +## More + + +- `fabro resume` now rejects already-succeeded runs with a clear error instead of silently restarting them +- Resume now validates the checkpoint file before cleaning up state, preventing partial cleanup on corrupt checkpoints +- `fabro attach` now detects early init failures and rolls back partial worktree state automatically +- Added restore operation that rebuilds runtime state from the checkpoint when resuming interrupted runs + + + +- Fixed resume creating unnecessary worktrees and failing to keep the sleep inhibitor alive +- Fixed git checkpoint options not being threaded through to the resume path +- Fixed verification regressions introduced by the runtime initialization refactor + diff --git a/docs/changelog/2026-03-27.mdx b/docs/changelog/2026-03-27.mdx new file mode 100644 index 000000000..e833e63dd --- /dev/null +++ b/docs/changelog/2026-03-27.mdx @@ -0,0 +1,30 @@ +--- +title: "fabro config show, preflight subcommand, and storage-dir" +date: "2026-03-27" +--- + +## `fabro config show` + +A new `fabro config show` command displays the fully resolved configuration for a workflow, showing how CLI flags, environment variables, project config, and workflow defaults are layered together. This makes it easy to debug configuration issues without guessing which layer is winning. + +```bash +fabro config show my-workflow +``` + +## `fabro preflight` + +Preflight validation has been extracted from `fabro run --preflight` into its own top-level command. This makes it easier to validate a workflow before running it, especially in CI pipelines where you want a separate validation step. + +```bash +fabro preflight my-workflow +``` + + +**`--run-dir` renamed to `--storage-dir`.** The `--run-dir` CLI flag has been renamed to `--storage-dir` to better reflect its purpose as the base storage directory. Runs are now created under `/runs/` automatically. The `data_dir` config key is also renamed to `storage_dir` (a serde alias preserves backward compatibility for config files). + + +## More + + +- Added `goal_file` and `labels` fields to workflow configuration for specifying goals from files and tagging runs with metadata + diff --git a/docs/changelog/2026-03-28.mdx b/docs/changelog/2026-03-28.mdx new file mode 100644 index 000000000..8eb54037e --- /dev/null +++ b/docs/changelog/2026-03-28.mdx @@ -0,0 +1,24 @@ +--- +title: "File-based workflow imports" +date: "2026-03-28" +--- + +## Workflow imports + +Workflows can now import subgraphs from other `.fabro` or `.dot` files, enabling reuse of common patterns across workflows. Imported graphs are merged into the parent workflow at parse time, with node name prefixing to avoid collisions. This replaces the previous `graph_merge` approach with a more flexible file-based import system. + +```dot +graph { + graph [import="shared/review-loop.fabro"] +} +``` + +## More + + +- Detached engine processes now have descriptive OS-level process titles (visible in `ps` and activity monitors) + + + +- Fixed a panic when checking if a process is alive on systems where PID values exceed `i32::MAX` + diff --git a/docs/changelog/2026-03-29.mdx b/docs/changelog/2026-03-29.mdx new file mode 100644 index 000000000..e6e82bdcf --- /dev/null +++ b/docs/changelog/2026-03-29.mdx @@ -0,0 +1,18 @@ +--- +title: "Store dump export command" +date: "2026-03-29" +--- + +## `fabro store dump` + +A new `fabro store dump` command exports the contents of the run store to a human-readable format for debugging and inspection. This is useful for diagnosing issues with run state, verifying data integrity after migrations, or extracting run data for external analysis. + +```bash +fabro store dump +``` + +## More + + +- Fixed store migration gaps affecting retro agent data, finalize commits, engine failure records, and hydration tolerance + diff --git a/docs/docs.json b/docs/docs.json index 3db7ea916..039397008 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -273,6 +273,14 @@ "group": "March 2026", "icon": "clock-rotate-left", "pages": [ + "changelog/2026-03-29", + "changelog/2026-03-28", + "changelog/2026-03-27", + "changelog/2026-03-26", + "changelog/2026-03-23", + "changelog/2026-03-22", + "changelog/2026-03-21", + "changelog/2026-03-20", "changelog/2026-03-19", "changelog/2026-03-18", "changelog/2026-03-17",