The Docker recovery scenarios scraped the worker log for "sandbox
workspace brought to its durable snapshot"; since the host and sandbox
restores share one path, the line reads "workspace brought to its
durable snapshot" with the site as a field.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The include error names the partial relative to the run's working
directory, so its `../` run is as long as that directory is deep: eight
on this machine's temp dir, three on the CI runner's. Collapse the run
to a token before the snapshot compares.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The detached cancel test waited for the run's status to read `failed`
and then asserted on the stored `run.lifecycle` record. The projection
concludes the run from Petri's `run.finished` coordinator record, and
the worker stores the platform's terminal lifecycle record a moment
later, so the read raced the write and the assertion failed about once
in thirty runs. Wait for the record itself, and print the stored events
and the run state when the assertion fails.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The host_plugin_ and docker_plugin_ variants ran each scenario under
Fabro's old plugin transport with the provider kinds `host` and
`docker-plugin`, which Petri's Fabro frontend rejects. Under Petri every
provider is already served by a sandbox-driver plugin, so those variants
test nothing distinct. A single docker_ variant replaces them: an
environment with provider `docker` on buildpack-deps:noble, created on
an isolated server, skipping without the sandbox-driver-docker
executable or a daemon with the image unless
FABRO_REQUIRE_SANDBOX_PLUGINS is set.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Every Petri run takes its scope through a sandbox-driver plugin
executable that Petri finds on PATH, so the test jobs need
sandbox-driver-host and sandbox-driver-docker installed at the rev the
workspace pins. The three jobs share one from-source install through an
actions/cache entry keyed on the OS and the rev.
The Linux test job also pre-pulls Petri's default runner image, which
the suite's Docker scenarios leave to Petri: the plugin pulls it on
first use, but a 1 GiB pull inside a run's timeout is a flake.
The stdio plugin job was built for the deleted fabro-sandbox layer. It
becomes the Docker providers job: the `docker_` scenario variants and
the fabro-petri suite, with the fabro-sandbox and fabro-workflow steps
whose tests no longer exist removed.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A live-server scenario runs a one-stage workflow on Docker whose command
writes a file into the workspace, opens an Ask Fabro session on the
finished run, and sends one turn. The session attaches to the container
Petri created, stopped at the run's end, starts it again, and its tool
reads the file inside it; the turn succeeds, the tool's output and the
model's reply carry the file's content, and the twin's follow-up request
shows the model read it from the tool. Ask Fabro's tool policy is
read-only, so the shell tool is hidden from the model and refused; the
turn reads the file with the `read_file` tool, scripted on the twin,
instead of a shell `cat`.
The scenario skips, and says why, without the Docker plugin or a daemon,
as the other Docker scenarios do.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Nothing imports it any more: the Pebble glue lives in
fabro-pebble-sandbox, the server reaches run sandboxes through
sandbox_access, and Petri creates every run sandbox. The crate, its
test-support, its integration tests and every dependency edge go with
it. The `[server.sandbox.providers.<kind>.plugin]` settings stay: the
server still launches a plugin executable through them to attach to a
sandbox of a non-bundled kind.
AGENTS.md names the new crate and the direct-access pattern in place of
`RunSandbox`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Petri creates and owns every run sandbox through the sandbox driver, so
what Fabro still needs around a driver handle is the Pebble glue: the
Environment pebble's coding agent runs its tools through, the exec policy
(stop grace, working directory, StripAll, the termination mapping, the
redacted output tail), pebble's port routes over the driver's preview
URLs, the secret redactor, the path helpers, and a log rendering that
appends a failed command's redacted tail. This crate holds that glue,
moved from fabro-sandbox, over `Arc<dyn Sandbox>` plus a working
directory instead of `RunSandbox`, with a `MockSandbox` double behind
`test-support`.
`fabro exec` creates its host sandbox directly on the driver's Host
provider and activates it; Ask Fabro wraps the attached handle. Both
keep the provider alive beside the sandbox where the session's processes
are the provider's process groups.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Fabro's own DOT parser was left with one job after create-time compile
moved to Petri: walking a workflow's file references for the bundler and
the workflow-version store, and reading a name, a goal and two counts.
Petri's frontend parses the same language, so the parser goes and a small
crate reads the graph through Petri's.
`fabro-dot` is that crate: `WorkflowGraph::parse` over
`petri_frontend_attractor::dot` and its semantic model (defaults applied,
subgraphs flattened, chains expanded), `references(position)` as the one
walker over the static-reference vocabulary (each reference with its node
and position, file references checked to be template-free), and
`normalize_for_graphviz`, the re-emit of Fabro DOT with dotted attribute
keys quoted, which the SVG render needs. It sits beside `fabro-petri`
rather than inside it because `fabro-petri` depends on `fabro-workflow`,
which depends on `fabro-workflow-version`: the version store cannot reach
`fabro-petri` without a cycle, and the bundler should not pull the engine
in to read a graph.
Deleted: `fabro-graphviz`'s lexer, grammar, AST, semantic pass and
`parse_ast` (1,829 lines, plus the `nom` dependency); the DOT model in
`fabro-types::graph` (`Graph`, `Node`, `Edge`, `AttrValue`,
`shape_to_handler_type`), with only `ReferenceKind` kept, moved to
`fabro_types::reference`; `fabro-template`'s `visit_graph_references` and
the `GraphReference`/`GraphPosition` types, with the template-syntax rule
(`validate_static_reference`) kept there; the pull-request body's DOT
fallback summary, which was unreachable because the DOT source only
travels with the run spec whose display graph the summary already reads.
`fabro-graphviz` is now the render alone, over `fabro-dot`.
Parity: the old and new walkers were run over every `.fabro` and `.dot`
file in the repository (118) before the deletion. Every reference set is
identical. Five files differ in what Petri reads more correctly: a
backslash before a newline inside a quoted string is a line continuation
(four files, inline prompt text only), and a node named only by an edge
counts as a node (`test/edge_only_node.fabro`, 3 nodes rather than 2, so
the `fabro validate` snapshot moves). The checked-in bundles' shapes and
references are pinned by a snapshot in `fabro-dot`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The rest of the change whose deletions the previous commit carries (its
`git add` stopped at an already-removed path): `fabro_types::RunGraph`
and the `fabro-petri` builder that reads it off the admitted graph, the
server's create, validate, preflight and render paths on Petri's check
alone, the consumers moved to the new shape, the OpenAPI `RunGraph`
schemas with their parity tests, the regenerated TS client, and the
docs naming Petri's diagnostic codes.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Every run is admitted by Petri, whose check lowers imports, file
references, templates and the model stylesheet, lints the workflow and
pins its models. Fabro then re-parsed the same workflow through its own
legacy pipeline (parse, transforms, structural validation) only to fill
`RunSpec.graph` for the read side. That second pass is gone: the run's
display graph is `fabro_types::RunGraph`, built once in `fabro-petri`
from the admitted graph's metadata (the workflow name and goal from the
graph params; each declared stage's label and handler kind; one edge per
routing arm as written, lowering artifacts left out), and stored on the
spec at create beside the DOT as `graph_source`.
Deleted: `fabro-workflow`'s `pipeline`, `transforms`, `file_resolver`,
`operations::{source, validate}`, `run_materialization` and the legacy
`compile_admitted_run`; the server's `compile_admitted`, the structural
manifest pass, `preflight_model` and the model probe `run_llm_check`
(Petri's admission raises `attractor.model.unknown`); `fabro-graphviz`'s
stylesheet parser; most of `fabro_types::graph` (the DOT model keeps
what the bundler, version registration and template walker read). The
DOT parser stays for the bundler and the SVG render.
`POST /validate`, `POST /preflight`, `POST /graph/render`, `fabro
validate` and `fabro preflight` run on Petri's check alone, so their
diagnostics carry Petri's codes (`attractor.unbound_input`,
`unsupported.template.unbound_input`) where Fabro's
`template_undefined_variable` and `goal_self_reference` were. A refused
workflow's summary still names the DOT as written. The OpenAPI `RunSpec`
schema gains `RunGraph`, `RunGraphNode` and `RunGraphEdge`, reused from
`fabro-types` with parity tests; the TS client is regenerated.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The CLI artifact scenario seeded its run through the deleted upload
route; it now runs a real Petri workflow whose hooks collect the
artifacts, and the fabro artifact list and cp assertions read those.
A real command retry is not producible from a command node (a plain
failure or a timeout routes onward), so the retry dimension of the old
fixture goes; the stage, node, and retry filters, the tree copies, the
cross-stage ambiguity, and the filename collision stay covered. The
archive guard test drops its upload row (the blob write row covers an
octet-stream mutation). A dangling doc comment and two absolute paths
clippy flagged are fixed.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Each edge was checked with rg over the crate's sources outside its
test paths. fabro-cli keeps git2, regex, ulid, and shlex as
dev-dependencies for its integration tests. fabro-automation keeps
chrono, tokio, and tracing: its migrations compile into the crate
through #[path]. petri_testkit was already optional behind fabro-petri's
test-support feature and dual-listed as a dev-dependency. The workspace
loses the agent-client-protocol and AWS entries no crate references;
jsonschema stays for the fabro-api and fabro-tool tests. Cargo.lock
was refreshed by a plain build and only loses entries.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
GET /runs/{id}/checkpoint duplicated what /state serves; the hidden
fabro parse command had no user; records, run_status, outcome, and
usage_rollup in fabro-workflow only re-exported fabro_types. The
importers now name fabro_types directly. format_cost keeps its two
callers (the pull request body and the CLI stage display) and moves to
fabro_types::usage; the usage rollup tests move beside the function in
fabro-types, with test_usage in its test support.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A worker whose server is killed outright retried its control-stream
connect forever at a 5 s capped backoff, so it never finalized, never
stopped its sandbox, and lived until reboot. The worker now tracks the
start of each run of continuous connection failure and gives up after
60 s (10 s once its parent is pid 1), through the existing fatal
control-loss path that interrupts interviews and cancels the run. After
that fatal fires, the runner keeps driving the cancelled pipeline for a
bounded grace so `conclude` can stop the sandbox before the process
exits, instead of dropping the pipeline future mid-flight.
The test harness's stale-daemon reaper only matched `fabro server`
titles bound under `/tmp/.tmp*`, but `TestContext` roots are
`.ft-<label>-*` under `std::env::temp_dir()`, so daemons bound there
were never reaped. The regex now also matches sockets below a `.ft-`
directory component under any parent, and the unit test covers both
roots plus real-looking paths and `.ft-` outside a directory component.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Petri's Fabro frontend refused a bundle naming an environment it did not
declare and every MCP catalog reference, so the fixtures declared
`[environments.local]` and the server's catalogs never reached Petri.
Pin Petri at c874b86, where the frontend reads `[environments.<id>]` and
`[run.environment]` from every settings layer (bundle over project over the
host's layer, key by key), takes the environment a launch selected over the
layers, and resolves `[run.agent.mcps.<name>] id = "..."` against a catalog
the host binds. The server hands Petri its environment catalog as
`[environments.<id>]` tables of the settings layer it already passes, the
intent's environment as the launch's selection (`Launch::environment`, as
the intent overrides the bundle in Fabro's own resolution), and its MCP
catalog as `RuntimeSpec::mcp_catalog_toml`, one inline entry per definition
keyed by id. Offline validation hands Petri the seeded catalog the same
way, so `fabro validate` accepts `[run.environment] id = "local"`.
The fixtures drop the `[environments.local]` tables they carried for this;
the secrets test keeps its own, on purpose. Scenario tests cover a bundle
naming a catalog environment (its image lowered, and run on Docker when the
plugin and a daemon are there), a bundle's own table winning key by key,
the server refusing an unknown environment before Petri, and a catalog MCP
reference whose tool the agent session lists (an echo server under
`test/mcp/`).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The worker control bus was publish-only: the steer and interrupt
endpoints answered 202 once the control was forwarded, and a refusal
showed up only later as a `run.notice` on the run's stream.
A steer or an interrupt now carries a request id. The worker answers it
over the control stream it arrived on with `{request_id, outcome}`,
where the outcome is `delivered` (with the stage's label) or `refused`
(with the code and the reason). The server keeps the outstanding
requests in a registry and waits up to 5 s for the answer: the endpoint
answers 202 `{"outcome":"delivered","stage":…}`, 409 with the refusal's
code (`no_live_turn`, `no_such_stage`, `steer_refused`,
`interrupt_refused`) and message, or 202 `{"outcome":"pending"}` when
the worker gave no answer in time. The `run.notice` record on refusal
stays, under the same code, so a steer to a stage that is not running is
now `no_such_stage` there too. Pause and unpause are unchanged.
The in-process test path answers a steer or an interrupt from the run's
own controls at once. `FABRO_TEST_CONTROL_ACKS_MUTED=1` on the server
mutes the worker's answers, so a test can see the pending fallback.
`fabro steer` prints the worker's answer, and a refusal is its error.
The OpenAPI spec documents the 202 body and the 409 codes; the Rust and
TypeScript clients are regenerated.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Through a real server and its worker: a three-stage run forked at its
first stage continues with the other two on the first stage's restored
file and commits on the new run branch after the source's commits; a
retry of a run whose last stage failed transiently reruns that stage and
succeeds; a rewind archives and supersedes its source, and an archived
run is refused; the timeline lists every checkpoint record with its
commit; a fork at a checkpoint inside a parallel branch is refused and
creates nothing, while one after the join continues.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`fabro timeline <run>` prints the checkpoint table (or JSON); `fabro fork
<run> [target]` and `fabro rewind <run> <target>` make and start the new
run and name it, `--list` showing the timeline instead; `fabro retry
<run>` starts the retry and prints its id. The top-level help snapshot
and the generated CLI reference follow.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The worker's `run.notice` for an interrupt it could not deliver now reads
"Interrupt of stage `gate` refused: the stage has no model turn to
interrupt" (or "Interrupt refused: …" when the control named no stage),
so the web and the CLI can show which stage and why, with the reason as
Petri's `ControlError` spells it. The gate scenario asserts both messages.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Petri 639ce3e added `ControlService::interrupt_firing` and the `LiveTurns`
capability a host installs beside the pause hooks. Fabro now drives it:
`RunControls::interrupt(stage, text)` resolves its stage the way a steer
does (a label, a node name, or the run's one live agent stage) and stops
that stage's current model turn, keeping the session; the text, when
given, is the stage's next input. `engine::run` installs the live-turn set
as a runtime capability, so without it no interrupt could ever land.
The worker maps `run.interrupt` and `run.interrupt_then_steer`, both of
which now carry an optional `stage`, to that call. The control bus is
one-way, so a refusal is recorded the way a refused steer is: a
`run.notice` on the run's stream whose code says why (`no_live_turn` when
Petri refuses a stage with no turn in flight, `no_such_stage`,
`interrupt_refused`).
The server's `POST /runs/{id}/interrupt` and `POST /runs/{id}/steer` with
`interrupt=true` forward the control and answer 202, replacing the 501
`interrupt_unsupported` stub. The interrupt endpoint takes an optional
body (`stage`, `text`), refuses a finished run with 409
`run_not_interruptible`, and forwards an interrupt of a blocked run, since
an agent stage may be running a turn beside the question and the worker
judges each stage itself. `fabro events --pretty` prints the delivered
interrupt and the stage's `attractor.turn.interrupted` report.
Verified on the twin: `fabro steer --interrupt` during a long tool call
ends the turn, the text is the agent's next request, and the stream
carries the `$interrupt` record and the interrupted-turn report; an
interrupt of a gate stage is refused with `no_live_turn` and the gate's
question is untouched.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`dry_run_parallel` and `dry_run_styled` timed out under load in the run
that found the other eight, so they were not recorded with them. Alone they
show the same one-line change: the Start stage's completion now precedes the
run branch line, the order the positioned records give every run.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The Fabro halves of D1, D2 and D3. A stage's `agent_tools` is the union, by
name, of the `attractor.tools` payloads its native sessions record, with
`invoked` flipped by the envelope's `ToolCallStarted`; the payload carries
Petri's origin category, so Pebble's category is `subagent` for a sub-agent
tool and `other` for the rest. A pending question carries each option's
description and preview and the question's context, and its reference as
the review target when Fabro's validation admits it; the interview dock and
the Q&A renderer show the previews beside the descriptions, and the attach
prompt prints both under each choice. The web's command view reads the
script from the node's `meta.script`, the decision renderer the matched
condition from `meta.edges[edge].condition`, and `run events --pretty`
prints the condition on the transition line and one line per session
naming its tool count. The command view notes what the output capture did
not keep, from the final `step.finished` loss metrics.
The web fixtures are recaptured at the pin, so they carry the new facts.
VIEWS.md loses the two gap rows Petri filled and names the sources; the
README's list of what the fold leaves default shrinks to match.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The pin to Petri 639ce3e moves the run's format version from 6 to 7, which
the attach JSON snapshot records. The other eight snapshots had recorded the
run branch and Git identity lines before the Start stage's completion: the
order the clock gave them before "Place the run branch and git identity
records with their checkpoint" positioned the two records after the firing's
finish. That commit refreshed only two files, and these eight already
differed the same way at the commit before the pin bump; they now record the
one order every run produces.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Move the lithos-llm pin from 55add459 to 43a42ac28e9d9bcf40a91abc02be4f12ca274ebb,
and the three Pebble pins from a39f43e to 67c9f48, Pebble `main`, which pins
that same lithos-llm revision so Cargo holds one lithos-llm crate. lithos-llm
`main` (ca19fac) is one commit further; that commit touches only its nightly
workflow, so this pin stays on the revision Pebble unifies with.
The `openai`, `anthropic`, `gemini`, and `openai-compatible` features are
gone upstream; each expanded to `runtime`, which `bedrock` implies, so the
four names leave the fabro-llm feature list. Every other manifest already
names `runtime`.
The catalog schema now names one adapter and many codecs per provider.
`adapter` defaults to `http`, `codecs = [...]` replaces `codec` and defaults
to `["openai-chat"]`, and the loader rejects the old `codec` key and the four
protocol-named adapter ids. Every inline catalog in tests and docs moves to
the new shape: the `openai-compatible` + `openai-chat` pair is dropped as the
default, `adapter = "openai"` + `codec = "openai-responses"` becomes
`codecs = ["openai-responses"]`, and the one test that swaps in a custom
adapter id now adds the line instead of replacing one. The settings
reference, the API schema's `Provider.adapter` description, and the SDK page
describe the new fields; the three `docs/superpowers/plans/` files that show
the old shape are dated, unchecked historical plans and are left as they are.
The implied agent profile for an operator provider that declares none used
to read the removed protocol adapter ids; it now reads the provider's first
codec (Anthropic Messages and Gemini map to their harnesses, the `bedrock`
adapter to Anthropic, everything else to OpenAI), with a test for the codec
path.
Absorbing the rest of the range: OpenRouter and Fireworks now ship enabled,
so the two fabro-llm tests that used OpenRouter as the disabled fixture use
`bedrock-openai`, and the docs and comments that said the two ship disabled
are corrected. The built-in catalog grew past 100 enabled model rows
(Vercel, TypeSafe, and the enabled OpenRouter and Fireworks rosters), so the
pagination shape test walks `page[offset]` to the last page instead of
assuming one page fits.
`cargo update -p` on the four crates also re-resolved a few already-locked
edges to match the lithos-llm lockfile: `windows-sys` 0.61.2/0.60.2 ->
0.59.0 under dirs-sys, errno, nu-ansi-term, quinn-udp, rustix,
rustls-platform-verifier, tempfile, terminal_size, and winapi-util;
`windows-core` 0.61.2 -> 0.62.2 under iana-time-zone; `errno` 0.2.8 ->
0.3.14 under signal-hook-registry; and `indexmap` 2.13.0 as a new public
dependency of lithos-llm. No package version was added or removed.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`run.branch` and `git.identity` are written by the checkpoint that creates
the run branch, before that firing's finish is appended, and carried no
position, so the stream ordered them by the millisecond clock: on either
side of the finish from one run to the next. Both now take that
checkpoint's stage position, and the existing ordering rule places them
after the firing's finish and before its routes, beside its checkpoint
record. The two CLI snapshots that had each recorded one of the two
orders now record the one order every run produces.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`SteerRunRequest` takes an optional `stage`: the label the projection
shows (`node@visit`, or `node/e<execution>@visit` when two executions
share one) or the node's name. The server passes it on the worker control
message; the worker's `RunControls` resolves a label to the live agent
firing and steers that firing, and a node name through Petri's own
live-stage index. Unnamed, the one-live-agent rule stays, and the refusal
now names the live stages by their labels. `fabro steer --stage` sets it.
A controls scenario runs two agent stages side by side, sees the unnamed
steer refused with both named, and steers each apart, one over the API
and one through the flag.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The worker's signal handlers pause and unpause the run through its
`RunControls`, the same path the server's pause and unpause take, so a
signal holds admission, records Petri's `run.paused` and the lifecycle
mirror, and releases it on the unpause. The legacy pause state the plan
named no longer exists in the tree; nothing was left to delete. A controls
scenario sends both signals to a real worker and reads the records back.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Every intra-doc link `cargo doc --workspace --no-deps` warned on now
resolves or is plain code: the private constant and helper, the removed
`InterpString::resolve`, the lithos `Message`, the sandbox-driver facets,
the `RunOptions::git_author` the cutover removed, and the stale
`platform_record_for` paragraph on the platform records. The `[@REF]`
segment of `fabro run`'s help text is allowed as help, not a link. A
`Rustdoc` job runs the same command with `-D warnings`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`run events --pretty` reads the flattened `git.identity` fields, and
shows a `run.diff` record as its summary and an `artifact.collected`
record as its path and size. The snapshot filters redact the base commit a
`Branch:` line names. The CLI snapshots now carry the `Base:` line, the
`run.branch` and `git.identity` stream items, the dry run's simulated
response and the two response files a dry run dumps.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Petri's retention decides whether a released workspace is kept or removed.
Fabro's lifecycle settings decide whether a sandbox keeps running after
the run and whether a delete may remove it; none asks for removal at the
run's end, and the sandbox tab, `fabro cp`, the run's delete and the
sandbox scenarios read the container after the run. So the mapping is
`Retention::Always` for every setting, named once as `engine::RETENTION`
with the reasoning, instead of a per-setting function that released a
finished sandbox.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
No store sits behind `[server.slatedb]` any more: the section leaves the
settings layer, the resolved server settings, the defaults, the API schema,
the TypeScript client, the install wizard and the docs, and `fabro install`
probes the bucket for the `artifacts/` prefix alone. A settings file that
still carries the section is rewritten once at startup by a temporary
migration that removes it with a backup beside the file.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`fabro inspect` lists the stages with their output, response and diff as
the projection holds them; `fabro diff` resolves a patch reference through
the run's blob endpoint; the final output and `dump` decode a plain
reference as text and a `#json` reference as a value. The diff tests run
over a git-backed Petri run again, and the large-output dump tests print
many lines rather than one, since Petri caps a single line at 64 KiB.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The commit that creates a workspace's run branch records `run.branch`
(the base commit, or the first checkpoint in a workspace with no history)
and `git.identity`. Every checkpoint record after the first carries the
stage's diff from its parent commit, with the patch as a text blob. After
the checkpoint record, the transition hook lists the stage's workspace
through the scope's environment, on the host and in a sandbox alike, and
collects every file under `[run.artifacts] include` into the blob table as
an `artifact.collected` record, skipping a file already collected under
the same path and digest. At the run's end the hooks diff the branch's
last checkpoint against its base in the snapshot repository and record
`run.diff`.
`engine::retention` maps the environment's lifecycle settings onto
Petri's workspace retention instead of always keeping every workspace:
`preserve`, `stop_on_terminal = false` and the local provider keep them,
anything else keeps a failed scope's only. The hooks docs no longer name a
redundant link target, so rustdoc passes with warnings denied.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Petri a5906f6 records where each scope's sandbox ran (`scope.acquired`,
`scope.failed`) and how its lease was released (`scope.released`). The
projection folds the root invocation's records into `Run.sandbox`:
`initializing` from `run.started`, `ready` with the `RunSandboxInstance`
(the provider, Petri's `host` as Fabro's `local`, the provider's id, the
image and snapshot, the working directory) from `scope.acquired`, `failed`
from `scope.failed`; the retention outcome is kept in the fold state, since
the view has no field for it. Ask Fabro reconnect and `sandbox cp`,
`preview` and `ssh` reach the run's sandbox again.
A local reconnect designates the recorded working directory again when the
host provider does not know the id: the provider mints a registry-only id
for a workspace path too long for a path-derived one, and that registry
belongs to the run's worker. The stream listing redacts its items the way
the attached stream does, so a client that pages after a stream sees the
same items.
Pins move to Petri a5906f6 (run format 6, engine log v11, event contract
4). The attach stream snapshot is re-recorded with the new record and a
filter for the host provider's minted ids; `sandbox cp` reads an upload
back through the run's workspace, which is no longer the target folder.
Server scenario tests prove the projected instance on the host and Docker
providers.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The TypeScript client's `RunCheckpoint` still carried the legacy
executor's resume fields; regenerating it from the spec gives it the
slim shape (`timestamp`, `current_node`, `git_commit_sha`). The CLI
test helpers that read a run's stream from its directory or the API
are named `run_stream_items`, so nothing but the dropped table's
migration history is still called `run_events`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The CLI's integration tests seeded runs by appending legacy run events
and waited on legacy event names. Now every seeded run is a real dry
run: the fixtures start the run through the CLI, read the run id from
its output and wait for the stream's terminal lifecycle record. Waits,
assertions and snapshots read `RunStreamItem`s (`run.finished`, the
platform `run.lifecycle` record, `derived.parsed.kind == "question"`).
Test changes:
- support.rs: `run_completed_dry_run`, `wait_for_run_finished`,
`wait_for_lifecycle`, `wait_for_stream_item`; the `append_seeded_*`
writers, `wait_for_event_names` and the git-backed seeded fixtures
are gone (the checkpoint patch is not in the projection yet).
- diff.rs keeps only the help test; inspect.rs drops the git-backed
checkpoint test; events.rs, dump.rs, create.rs, attach.rs and
dry_run_examples.rs snapshots are re-recorded over Petri's rendering
with redactions for epoch millis, digests and commit shas.
- run.rs: the remote foreground mock serves stream pages and a run
state with a conclusion and a `report` stage response; the event
history test checks `run.finished` and the terminal lifecycle item.
- runner.rs / attach.rs: question ids containing `#` are percent-encoded
in answer URLs.
Production fixes the ports surfaced:
- petri_worker.rs: a cancelled run exits without reporting a failure.
- runner.rs: resuming a run that already finished fails its precondition
instead of starting a worker.
Left failing on purpose, each bound to a Petri-side gap reported to the
lead rather than to the port: sandbox_cp (4), sandbox_preview and
sandbox_ssh (the projection carries no sandbox instance), the artifact
collection tests in workflow::artifacts and run.rs (no artifact
collection for Petri runs yet), and the two dump blob-ref tests (blob
refs are not visible in the inspect output).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Step 4 of the legacy executor deletion, fourth commit: with no writer
and no reader left, the legacy event log goes.
- `fabro-types`: `run_event` (`EventBody`, `RunEvent` and every props
struct), `EventEnvelope` and the `RunEventDetail*` types are deleted.
What the projection and the API still use moves out of the event
vocabulary: `AgentEventProps`, `AgentSessionActivatedProps`,
`AgentToolsAvailableProps`, `StagePromptProps`, `SessionCapability`
and the coding event names to `agent_props`; `RunNoticeLevel` and
`RunNoticeCode` to `notice`; `InterviewOption` beside the question
types; `RunRunnableSource` beside the run status. `Checkpoint` is
what Fabro records for a Petri run: `timestamp`, `current_node`,
`git_commit_sha`; the conclusion's stage summaries derive from the
projection's stages instead of the checkpoint's node maps.
- `fabro-store`: the Slate bridge (`RunDatabase`, the Slate `Database`,
`keys`, `record`, `EventPayload`) and the reducer (`run_state`) are
deleted. `Database` is the blob table and the run summary store over
one pool; the blob store is SQLite only; the run summary store keeps
the `runs` row a projector writes and lists, and finds the pull
request creation candidates over `platform_records`; `build_summary`
and `projected_usage` live in `run_summary`. The SlateDB dependency
is gone. Test fixtures build the store from its two SQLite stores.
- `fabro-workflow`: the `event` module (the `Event` enum, its
conversion, sink, emitter, redaction, stored fields and names),
`runtime_store`, `StageScope` and the legacy seeding test helpers are
deleted; the tests that seeded legacy runs read platform records or
a projection instead.
- `fabro-sandbox` owns `GitRetryReason`.
- The server builds the store without an object store; the legacy
`POST /runs/{id}/events` tests go, an interrupt answers
`interrupt_unsupported` in the tests as it does in the handler, and
the tests that read a run back through the Slate handle read its
projection or its platform records. The projection folds a block
that lands while the run is paused as the pause's prior block, and a
pause or unpause clears the pending control it answers; a control
request's check-and-append holds a per-run lock so two concurrent
cancels record one request.
- The CLI's final output is the response of the last stage that
produced one; the workflow tests read completed nodes from the
succeeded stages.
- The spec's `RunCheckpoint` carries the three fields the type keeps.
Still failing until the next commits: the CLI tests that seed runs
through `POST /runs/{id}/events` or wait for legacy event names, and
the two Ask Fabro resume tests (the sandbox instance gap).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Step 4 of the legacy executor deletion, third commit: the legacy event
API and every reader of it go, so that the next commits can delete the
event log, its reducer and the types beneath them.
The API:
- `GET /runs/{id}/events` pages the run stream only
(`PaginatedRunStreamList` by `after`); the legacy `since_seq`,
`before_seq` and `order` cursors, the `oneOf` envelope, the legacy
`EventEnvelope`, `PaginatedEventList`, `RunEvent`, `EventSeq`,
`AppendEventResponse` and `RunEventDetailResponse` schemas,
`POST /runs/{id}/events`, `GET /runs/{id}/events/{seq}` and
`GET /runs/{id}/stages/{stageId}/events` are deleted. `GET
/runs/{id}/attach` and `GET /attach` frame `RunStreamItem`s only.
- The Rust and TypeScript clients regenerate; the removed models leave
the TypeScript package.
The readers:
- `fabro-client` drops the legacy run event listing, tail and attach
methods and `RunEventStream`; `list_run_stream_until` bounds a stream
read.
- `fabro-tool`'s `fabro_run_events` lists, searches and details the run
stream: `after` is the exclusive `stream_seq` cursor, `event_id` the
item's id, filters match the item's name and `recorded_at`.
- `fabro-dump` writes the stream to `events.jsonl`; `fabro dump` reads
it.
- The CLI's progress renderer keeps only what the run stream drives:
the legacy event conversion, the sandbox and setup displays and their
styles go. `fabro system events` prints stream items.
- The server's demo mode folds its agent fixture straight into the
session projection and answers the attach stub with a stream item;
the demo stage events endpoint is gone.
- The web app: every run is a Petri run. The legacy event hooks,
renderer props, stage popover summary, run phases derivation and
live-event payload handling are deleted or ported to `RunStreamItem`;
toasts and board refreshes read the stream's platform records.
- Tests: the legacy API round trips and pagination tests are deleted;
the CLI's MCP, attach and system event mocks serve stream pages; the
CLI test helpers read stream items.
Still failing until the later commits: the CLI tests seeded through
`POST /runs/{id}/events`, the server tests over the legacy store, and
the legacy type tests.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Step 4 of the legacy executor deletion, second commit. Ask Fabro's
sessions were the last writer of `run_events`: a session's creation, its
turns and their messages, tool calls and endings went into the run's
legacy event log, keyed by the run's sequence. They now have a log of
their own.
- `run_session_events` (migration `2026091802`): one row per session
event, numbered per session from 1, with the owning run, the turn, the
event name and its properties. `RunSessionEventStore` appends under the
write lock, lists a session from a sequence, names a session's owner
from its creation event, deletes a run's sessions with the run, and
publishes each committed event to its subscribers.
- `fabro_types::SessionEvent`: `seq`, `session_id`, `run_id`, `ts` and a
flattened body (`event` naming the kind, `properties` its fields), with
the same event names and property shapes the legacy events carried,
so the web app and the CLI read the same JSON. The property structs
move to `session_event`; `run_event::session` re-exports them under
their old names until the legacy event log goes.
- The API: `GET /sessions/{id}/events` pages `PaginatedSessionEventList`
by the session's own sequence, `GET /sessions/{id}/attach` replays and
streams `SessionEvent` frames (subscribed before the replay, so no
event falls between the two), the turn stream carries the same frames,
and an interrupt answers with the recorded event. The session
projection folds `SessionEvent`s; the legacy `find_session_owner` over
`run_events` is gone.
- The CLI's `run ask` and the web app's session stream read
`SessionEvent`; the web runtime no longer accepts the nested legacy
envelope shape.
The two session resume tests in the server keep failing for a reason
this commit does not touch: Ask Fabro reconnects to the run's sandbox
from the projection's sandbox instance, which the Petri projection does
not carry yet (`VIEWS.md`, the `scope.acquired` gap).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Step 4 of the legacy executor deletion, first commit of several: step 4
spans commits because the legacy event log and its consumers cannot go
in one compiling change. This commit moves every writer off `run_events`;
the reducer, `EventBody`, the Slate bridge and the API's event types
still exist for the readers the next commits port or delete.
Writers:
- The server records a run's lifecycle (submitted, runnable, starting,
running, blocked, paused, control requests and effects, the terminal
status), its title, parent link, archive state, notices and pull
request state as platform records (`fabro_store::platform_records`),
through the new `server::run_records` module. Every append wakes the
projector and waits for its pass, so the read that follows a write
holds the record.
- Pull request creation is recorded as `pull_request.requested`,
`pull_request.created`, `pull_request.failed`, `pull_request.linked`
and `pull_request.unlinked`; the projection folds them into the run's
pull request and creation state.
- Answers to questions are recorded as `interview.answered` with the
answering principal and the answer text; the interview adapter no
longer posts legacy `interview.*` events (`QuestionSink` is now an
optional observer).
- The worker (`fabro run __run-worker`) records its lifecycle, notices
and pause state over `HttpPlatformRecords`; `HttpRunStore` for the
legacy event log and the worker's `run_store` are gone.
- `persist_created_run` appends `run.created` and `run.submitted`.
Readers:
- A stream follower (`server::stream_follower`) follows each live run's
stream (Petri events and platform records), folds lifecycle records
into the in-memory run state, forwards items to the global attach
broadcast, and syncs blocked and paused from the projection.
- Slack posts questions from the projection's pending interviews,
finishes them on `interview.answered` or `question_expired`, and sends
lifecycle notifications with `notification.sent` dedupe.
- `GET /runs/{id}/events` and the attach endpoints serve only the run
stream; the per-event, per-stage and `POST /runs/{id}/events`
endpoints and their tests are deleted.
- `Database::load_run_projection` reads the Petri projection only.
Deleted with the writers:
- The SQLite blob and run-history activation migrations and their
legacy Slate imports (`legacy_blob_import`, `legacy_run_history_import`,
the activation backup): a greenfield server has no Slate history to
import, and the run-history verification refused to start a server
whose runs have no legacy events.
- `fabro-workflow`'s `operations::archive` and `operations::run_store`.
- The server's legacy-event unit tests and the CLI's `HttpRunStore` tests.
The in-process answer transport is now set after the starting and
running records land, not gated on the live status still being
`Starting` (the records already moved it).
The manifest validation test for a `run.agent.mcps.<name>` catalog
reference now expects `unsupported.workflow_toml.run.agent.mcps.reference`:
Petri's Fabro frontend has no server catalog to resolve it against.
Legacy readers still fail their tests until the next commits: the
reducer and Slate tests in fabro-store, the fabro-workflow create tests
that read the run back through the legacy store, the CLI tests seeded
through `POST /runs/{id}/events`, the CLI's legacy attach and render
paths, the sessions API, the OpenAPI conformance test, and the web
fixtures.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Petri judges a workflow at admission, so Fabro's lint rules go:
`fabro-validate` (its 35 rules and the `LintRule` trait) is deleted, and
with it `fabro-acp` (only a rule and two legacy executor tests used it),
the model-resolution transform, the legacy `create`, `compile_create_run`
and `materialize_create_run` stages, and `fabro-graphviz`'s `condition`
and `fidelity` modules. `Diagnostic`, `RelatedDiagnostic` and `Severity`
move to `fabro_types::diagnostic`, the one shape every diagnostic takes.
Validation is now the same question the create handler asks. A new
server module, `petri_check`, builds Petri's check request from a
workflow bundle and the run's settings (every workflow of the bundle at
its bundle-relative path, the inputs, the run variables, the launch),
runs the check, and maps the diagnostics; Fabro adds one rule of its
own, `fabro.model.no_ready_provider`, refusing a model node when no
provider is ready. Admission, the validate and preflight endpoints and
the offline `fabro validate` all go through it:
- `validate_prepared_manifest` runs Fabro's structural pass (parse and
transform, whose diagnostics stay) and then Petri's check, on the
blocking pool from the handlers;
- the offline `validate_manifest` checks with no model client and with
an unbound input as a warning (`CheckRequest.unbound_is_warning`), so
a workflow validates before its inputs exist; a collected workflow
before upload checks with unbound inputs as errors, as before;
- preflight resolves each LLM node's selector against the ready
providers and the catalog for its probe, as the deleted transform did,
and no longer probes a model Petri refused;
- the graph render endpoint needs only the structural pass;
- a run manifest now carries its `[run.goal] file`, which Petri reads
from the bundle as it does for a version.
The transforms keep the authored model selector (`sonnet` stays
`sonnet`): Petri pins the catalog model in the admitted graph, not in
the graph Fabro displays or in the settings snapshot. Tests assert that,
and the CLI's validate, preflight and graph snapshots carry Petri's
diagnostics (`attractor.no_start`, `attractor.undeclared_node`,
`attractor.bad_on_failure`, ...) in place of the lint rules' text.
Known gaps, Petri's side: a `workflow.toml` whose `[run.environment]`
names an environment the server catalog defines but the file does not
is refused (`unsupported.workflow_toml.run.environment`), as admission
already refused it; an unbound input inside an included template
partial is a render error rather than the unbound-input warning.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`fabro-mcp` held two things after the legacy executor went: the mapping
from Fabro's MCP server settings to the servers pebble starts, which
only `fabro exec` still uses, and a stdio MCP client the tests of
Fabro's own MCP server speak through. The mapping is now
`fabro-cli`'s `mcp_servers` module and the client its test support's
`McpStdioTestClient`; the crate is deleted. Its `config` module was a
re-export of `fabro_types::settings::run`, which callers import directly.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
