Main merged the sandbox-driver adoption (#849) in a later form than this
branch was stacked on: the driver's own exec types replace fabro-sandbox's,
shell quoting moved to fabro-util, the sandbox lifecycle collapsed, and the
driver's events are stored as run events. This branch had deleted
`fabro-agent` and put the coding agent, the environment adapter, and the
steering hub on pebble.
The resolution takes main's sandbox API and re-applies pebble on top: the
`RunSandbox` `Environment` adapter moves to `pebble_environment.rs` (main's
`environment.rs` is the sandbox spec) and runs commands through `ExecSpec`
and `ExecControls`, feeding pebble's output sink from the driver's; the
driver-era `sandbox.*` names leave the known-event list, as on main, so a
stored event with that name and no driver shape is `Unknown` rather than an
error; `program_exit_code` matches pebble's non-exhaustive termination; the
Docker and Daytona smokes use main's constructor and credentials; the
remaining `fabro_agent` paths point at fabro-sandbox.
Pebble's `mcp` feature pins sandbox-driver, and the preview-url trait
objects only cross when both sides name one revision, so pebble moved to
main's `a92c0db6` (lithoscomputer/pebble#10) and fabro pins that pebble
revision until it lands on pebble main.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
RunSandbox grew its lifecycle methods one adopter at a time and ended up
with several names for each step. Reconnecting from a run record had
four entry points (reconnect, reconnect_for_run,
reconnect_for_run_with_events, reconnect_driver_for_run) that all
forwarded to the last one. Bringing a sandbox back had two (start and
activate) over the same make_ready, and releasing it had two (delete and
cleanup) over the same release. Two more methods had no callers at all:
set_autostop_interval, which nothing set after the driver took over
lifecycle timers, and resume_setup_commands, which resume stopped using
when checkout moved to the git facet.
There is now one of each. reconnect_for_run takes the record, the
provider access, an optional run id, and an optional event context;
callers that need none pass None. activate is the single "make usable"
step: a running sandbox only learns its platform when it has not yet, a
stopped or paused one is started and its Bash verified, and resume calls
it like every access-time caller. delete is the single release; for a
designated host directory it frees the handle and leaves the directory in
place, as cleanup did. The tests and server call sites follow the
renames; behavior is unchanged except that resuming an already running
sandbox no longer re-runs the Bash probe.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Replace fabro's hand-written agent loop with pebble's `CodingAgent` and
delete the `fabro-agent` crate.
Workflow: `PebbleBackend` builds one agent per stage over `RunSandbox`,
binds the stage's hooks as tool middleware, the interviewer as the
human-input provider, and a durable `EventSink` that writes every agent
event through the run event log before the agent goes on. Full-fidelity
threads continue across stages through `export`/`resume_from_export`.
Model failover takes the session record after the failed prompt and
continues it on the next route with `ResumeMode::UseModel`, so no tool
effect repeats. The steering hub targets pebble's control handle, with
a steering lease holding completion open while a human is paired.
Events: `EventBody::Agent` carries pebble's `CodingAgentEvent` envelope;
the per-variant bodies, the transcript projection, and the fabro-only
context-window, tool-summary, and skill types are gone in favor of
pebble's. The OpenAPI schemas, generated Rust and TypeScript clients,
and web readers follow.
Ask Fabro: the session runs a `CodingAgent` under a read-only permission
policy and a system prompt transform. Its conversation lives in a new
`run_session_records` table and resumes on the recorded model with the
event cursor advanced past the run log.
`fabro exec` builds the same agent over a local sandbox with pebble's
permission middleware and an interactive approval service.
The catalog fills in `metadata.agent.profile` for operator providers
that declare none, so pebble's lookup is the one resolution path.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
SandboxOptions was an intermediate between the environment's settings and
the driver's SandboxSpec that mirrored the spec field for field: image
and Dockerfile for the source, cpu and byte sizes for the resources,
auto-stop for the timers, plus the two clone fields. Every provider
overlay then read the options a second time to fill the spec.
The environment now maps onto the driver spec once, in
sandbox_spec_for_environment, and the overlays read the spec: Docker
takes its image from the source and clears the timers it cannot honor,
Daytona takes its snapshot inputs from the source and resources and its
auto-stop from the timers. A plugin gets the spec trimmed to the network
and timer capabilities it declares. The snapshot carries the resources a
Daytona sandbox is sized by, so the overlay clears them from the spec
the sandbox is created with; the driver refuses them there, which the
options path never reached in a live run.
The clone selectors, depth, and skip flag travel as one CloneRequest
beside the spec instead of five loose parameters and two option fields,
so provider_sandbox takes six arguments instead of nine. The two helpers
that read environment settings for a local run, its working directory
and its unresolved variables, become methods on RunEnvironmentSettings
in fabro-types, where the settings live.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Both sides rewrote the same crates. This branch replaced fabro's sandbox
layer with the sandbox driver: one RunSandbox, no Sandbox trait, driver
events consumed directly, MockSandbox over the driver's doubles. Main
replaced fabro's LLM layer with lithos-llm: fabro-model deleted, the
catalog and provider ids from lithos, credentials through the lithos
CredentialProvider, clients built with build_client.
Every conflict was one of those two renames meeting in an import list or
a signature, so the rule was mechanical: sandbox names resolve to this
branch, LLM names to main. Where main's newer code still used the old
sandbox API — new session tests over Arc::new(MockSandbox), the SDK
example's LocalSandbox, test fakes typed as Arc<dyn Sandbox> — it is
ported to RunSandbox and the mock helper. Where this branch still used
fabro-model or Client::from_source, main's replacement stands. One
combined future in the CLI runner crossed clippy's size budget and is
boxed at its call.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
fabro-types no longer re-exports the lithos catalog and request types
(ProviderId, ModelId, ModelHandle, Message, ContentPart, TokenCounts,
Cost, Speed, ReasoningEffort, ReasoningOutput, and the rest). Every
crate that uses them depends on lithos-llm and names them there, and
the fabro-api progenitor replacements point at the lithos paths.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
fabro-auth defined its own `CredentialSource` trait beside the lithos
`CredentialProvider`, with a parallel `ResolveError` and an adapter between
them, because lithos had no way to ask which providers a store can serve
right now. It does now: `credentials::readiness`, `ClientBuilder::build_ready`,
and `CredentialError::Unusable`.
- The vault, SQL vault, API-key, and extra-headers stores implement
`CredentialProvider` directly. Material that is present but unusable (an
expired token with no refresh, a wrong-typed vault entry, a header secret
that did not resolve, a store read failure) is `CredentialError::Unusable`
with the operator-facing reason; its `Display` replaces
`auth_issue_message`. `is_configured` is the cheap presence check.
- `fabro_llm::build_client` calls `build_ready`; `FabroClient::auth_issues`
carries `CredentialError`. `fabro_llm::configured_providers` replaces the
per-store `configured_providers` method.
- `CredentialSource`, `ResolvedCredentials`, `lithos_credentials`,
`ResolveError`, and `auth_issue_message` are deleted. Twenty files that
held `Arc<dyn CredentialSource>` hold `Arc<dyn CredentialProvider>`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Fabro carried its own Sandbox trait long after every implementation
became a thin layer over the sandbox driver: one production type
implemented it, a delegation macro forwarded it, and each consumer crate
kept hand-written fakes of its thirty methods for tests. The trait
existed to be mocked, and the mocks pinned behavior that no provider
had — canned walk listings that ignored the traversal root, opaque
provider paths, activation failures with no lifecycle behind them.
There is now one sandbox type. RunSandbox keeps fabro's semantics — path
resolution against the run's working directory, the Bash exec policy,
git setup and push, credential refresh — as inherent methods over the
driver's exec, filesystem, search, and git facets, and every consumer
takes Arc<RunSandbox>. The directory, grep, and walk types are the
driver's own, re-exported from fabro-sandbox. The exec policy reports
the provider's measured duration rather than its own clock.
Tests script a sandbox through fabro-sandbox's MockSandbox: a struct of
fields (seeded files, the result every command returns, the platform,
a runtime directory) that hands out a RunSandbox over the driver's
scripted doubles and reads back what the code did — commands, timeouts,
environment, term stops, writes, deletes, existence probes. The
hand-written fakes in fabro-agent, fabro-acp, fabro-hooks,
fabro-workflow, and fabro-server are gone; the one wrapper a git
integration test still needs sits at the driver level, hiding a path
from a real Host sandbox. The refresh-ahead loop takes the refresh as a
closure so its schedule is tested without a sandbox at all.
The driver pin moves to the testing-crate stack head, which gained the
double behavior these ports needed: retention caps on scripted output,
canned walks narrowed to the requested base, upload and download on the
memory filesystem, and recorders for deletes, existence probes, and
term stops. One test that modelled a provider handing back opaque object
paths from a walk is removed: the driver contract has no such thing.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Fabro's policy layer restated the lithos built-ins under `metadata.fabro`:
enabled flags, credentials, display facts, probe and small-default roles,
and agent profiles. lithos-llm now carries every one of those as a core
field or under the shared `metadata.agent` namespace, so the layer and its
typed view go:
- Delete `fabro-policy.toml` and `FABRO_POLICY_TOML`. The catalog is the
lithos built-ins plus the operator's `[llm]` overlay, nothing between.
- Delete `fabro_types::catalog_policy`. `enabled`, `stands_in_for`,
`api_key_url`, `family`, the cutoffs, `estimated_output_tps`,
`small_default`, and `probe` are read from lithos accessors; the agent
profile and `reasoning_by_default` come from `metadata.agent`, which
Pebble reads too.
- `catalog::provider`, `enabled_providers`, and `listed_providers` return
the lithos `CatalogProvider` directly; `ModelEntry` loses its policy
field and gains `agent_profile()`.
- Test fixtures move `[providers.x.metadata.fabro] enabled = true` onto
the provider table, drop `credentials` lists in favor of the secret name
lithos derives from the provider id, and spell `agent_profile` as
`metadata.agent.profile`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
lithos-llm now owns which named secrets each provider reads and how they
shape into its auth scheme, including a derived `<PROVIDER>_API_KEY` for
operator-defined providers. Fabro's job shrinks to supplying the store:
`VaultCredentialSource` hands lithos a lookup that reads the process
environment, then the vault, under the same conventional names.
What Fabro still adds on top: the Codex OAuth credential in the vault,
refreshed and persisted when it expires; `{{ secrets.NAME }}` tokens in a
provider's `default_headers`, resolved against the vault and re-sent as
credential headers; and OpenAI organization and project headers from the
environment.
Deleted with the `metadata.fabro.credentials` list: `CredentialRef`,
`CredentialResolver`, `EnvCredentialSource` (now
`VaultCredentialSource::environment_only`), and the `env_var_names` /
`expected_vault_secret_name` helpers, replaced by `secret_names` and
`expected_secret_name` over the lithos table. `openai-codex` joins the
first-party provider id constants.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Three copies of the same mapping turned an environment into a sandbox:
Docker had its own options type built from the environment, Daytona a
config type with its own network enum and minute-and-gigabyte units,
and plugin kinds a third options type, each with its own spec builder,
constructor, and attach function, and the run spec had a variant per
provider carrying them. The mapping now runs once. SandboxOptions is
what any environment asks of any provider; options_from_environment
builds it, and one base spec carries the source, name, labels,
variables, resources, and network policy. Docker and Daytona are
overlays on that spec: Docker fixes its working directory, supplies the
default image, and pulls; Daytona replaces the source with the snapshot
it ensures from the same image or Dockerfile, fixes its working
directory and name, and sets the timers. The snapshot's content-addressed
name is unchanged, since the identity still hashes the image or
Dockerfile and the resources in whole gigabytes.
SandboxSpec has two variants, Local and Provider, and the worker and
the server preflight build the Provider one without knowing which kind
it is; provider_sandbox and attach_provider_sandbox connect any kind
through the single construction function and lay the repository out
where that kind keeps it. The per-provider constructors, the config
module, and the environment mapping module are gone, and the SDK
reference and the integration tests use the one constructor.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Workflow LLM handlers build lithos requests, bill from lithos usage and
cost, and classify failures from lithos `ErrorKind`. Model resolution and
fallback use the fabro-llm selection and catalog helpers. Validation
rules read the lithos catalog, and store fixtures use the new
`BilledModelUsage` shape.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Fabro's Docker provider kind now maps onto the sandbox-driver Docker
provider instead of its own bollard implementation. Fabro keeps what is
its own: the clone decision and repository layout, the GitHub App push
credentials embedded in origin, git retry classification, the managed
labels that gate destructive operations, and the run-facing events.
- `clone.rs` performs fabro's clone over the driver `Git` and `Exec`
facets. An exact commit goes through the driver's pinned clone; a tag
pin runs fabro's init/fetch/attach sequence through `Exec` so the
fully qualified tag ref is the only revision consulted. Network
failures retry through `git_retry`, which now classifies driver errors
(exec output, provider retryability) and never replays an operation
whose outcome is unknown.
- `DriverSandbox` gains a pending-create state, a `RepoWorkspace` with
push-credential state, path resolution against the cloned working
directory, git lifecycle methods, image-pull progress mapped from
driver events, and an embedded terminal over the driver `Pty` facet.
- `docker.rs` builds the driver `SandboxSpec` (image, `/workspace`,
fabro labels, env, cpu/memory, network policy, run name) and attaches
by persisted container id, refusing containers without fabro's labels.
- Inventory, details, diagnostics, terminal, and reconnect run over the
driver: a `DriverInventoryProvider` lists by fabro's managed label and
projects `SandboxStatus` into fabro's inventory and details shapes.
- The bollard-based `docker.rs`, `provider/docker.rs`, Docker terminal,
Docker error variants, the `docker` cargo feature, and the bollard and
tar dependencies are gone. The Docker integration tests, the agent
shell test, the workflow artifact test, and the driver benchmark run
against the driver-backed sandbox.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
SandboxSpec::Local and run reconnect now build a DriverSandbox over the
sandbox-driver Host provider instead of fabro's own LocalSandbox, which
is deleted. fabro_sandbox::local_sandbox designates the working
directory (created when missing, never removed), creates the Host handle
in a per-process registry, and learns the platform up front. A local
sandbox reports no provider id: it is its directory, which the run
record already carries, so reconnect rebuilds the handle over that
directory rather than by id.
The credential filter for explicit environment variables and the Bash
readiness probe now come from the exec layer and the driver's activate
helper. Test call sites move to the async constructor; test factories
that must stay synchronous share the parent session's sandbox handle.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A failed node with an effective `succeed` policy and no explicit recovery
route now finishes as `succeeded` and follows normal success routing. The
original failure stays on the outcome so the stage.completed event and the
checkpoint keep the diagnostic, and the outcome notes record which scope
promoted it.
- OnFailure gains a Succeed variant; Node::on_failure resolves the
deprecated auto_status=true attribute as an alias, with an explicit
on_failure winning
- The core executor applies the policy before the lifecycle observes the
result, so the recorded outcome, context keys, goal gates, events, and
routing all see the effective outcome; this replaces AutoStatusLifecycle
- Explicit routes take priority: a matching condition, preferred label,
suggested next node, or handler jump keeps the outcome failed. A failed
outcome takes an unconditional edge only under route, so under succeed
any edge selection is an explicit route
- succeed applies only to failed, matching exit; the auto_status alias no
longer promotes partially_succeeded
- Parallel branches promote after their retry loop, so a failed succeed
branch counts as succeeded in the parent aggregate
- Validation accepts succeed and adds an auto_status_deprecated warning
that suggests on_failure="succeed"
- Document the policy table, semantics, and deprecation; add a changelog
entry
Closes#807
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A node can now set its own on_failure attribute to override the
graph-level failed-node routing policy in either direction: a
best-effort node can keep route inside an exit graph, and a critical
node can exit while the rest of the graph keeps the default. An absent
node attribute inherits the graph policy.
- Node::on_failure returns Option<OnFailure> so absence means inherit
- Graph::resolve_on_failure(node_id) is the single resolution point,
returning ResolvedOnFailure { policy, scope } so the executor's
end-of-run message names the scope that stopped routing
- The core Graph trait method becomes resolve_on_failure(node_id); the
graph-scope failure message is unchanged
- The failed-human-gate fallthrough block stays independent of a
node-level route override
- Validation now accepts and value-checks node-level on_failure (it
previously warned that node placement had no effect) and keeps the
edge-placement warning with updated wording
- Document precedence in transitions, failures, and the DOT reference,
and extend today's changelog entry
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Chraa21RK7i2KqHdZSJLb8
- Dedup Diagnostic construction in the on_failure_valid rule
- Use the shared node_with_attrs test helper
- Drop an executor test that duplicated existing retry-target coverage
- Build on_failure integration test graphs from DOT and share a run
harness, exercising the parser path for valid on_failure values
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J6MnJri6oSEMZaYeADY5dP
Use /tmp/fabro/runtime for both Docker and Daytona instead of
provider-specific roots. A writable /tmp inside the sandbox is already
a dependency (commit-message files, exec stop-files), it needs no
root-level mkdir for non-root container users, and it makes the two
providers uniform.
The trailing runtime path component stays load-bearing: materialized
blobs at runtime/blobs/{hash}.json are recognized as managed blob
references and normalized back to blob:// in durable context.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012Kmn5jyrdpyCdvcfvmEDvA
Remote prompt-value materialization wrote demoted values to
{working_directory}/.fabro/blobs inside the repository checkout, so a
later checkpoint could commit them and leak them into the run pull
request.
Give each sandbox a run-scoped runtime directory outside the source
checkout as part of the Sandbox contract:
- Sandbox::runtime_directory() names the directory; host-local
sandboxes return None because the engine owns a host-side runtime
directory (RunScratch) for those runs.
- Docker creates /fabro/runtime at initialize with umask 077 and
uploads runtime files with mode 0600.
- Daytona creates /home/daytona/fabro/runtime with mode 0700.
- Both remote materialization paths in fabro-workflow share one
materialization-path helper built on the new contract. The paths keep
the runtime/blobs suffix, so durable context still normalizes to
blob://sha256/... references.
- Local materialization now writes owner-private directories and files
on Unix.
Regression coverage: an integration test runs remote-style prompt
demotion against a real git checkout, then a real checkpoint commit,
and asserts the checkout stays clean, the agent-facing file is
readable, and a deleted materialized file is recreated from the
durable blob store. A real-Docker test verifies the runtime directory
and blob file permissions inside a container.
Fixes#798
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012Kmn5jyrdpyCdvcfvmEDvA
test_blob_store was a process-wide OnceLock singleton over one in-memory
SQLite connection, so content-addressed rows written by one test were
visible to every other test in the same process. nextest's
process-per-test model masked the bleed, but plain cargo test failed
(8/24 in fabro-workflow-version) because negative existence assertions
became order-dependent.
test_blob_store now builds a fresh isolated in-memory store per call,
and test_database gives every database its own blob authority.
Reopen-style tests that model one durable blob authority across several
store handles use the new test_blob_store_at, which keeps the blob table
in a SQLite file beside the store directory, plus
test_database_with_blobs to share it explicitly.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Blob activation cleanups:
- Reuse fabro-db's append_to_path, remove_file_if_exists, and
set_private_permissions instead of local duplicates.
- Return the store directly from activate_blob_storage; the report
wrapper existed only to be logged internally and then discarded.
- Collapse compute_disk_preflight to return the required free bytes
instead of echoing its inputs back through a struct.
- Deduplicate the "exactly one ok row" PRAGMA integrity_check protocol
into one executor-generic helper used by the backup and live checks.
- Skip re-validating a freshly published backup; the staging copy was
validated immediately before the atomic rename, so only a
concurrently published file needs its own validation.
- Replace the manual anyhow wrapping plus duplicate error log in
serve.rs with a plain .context(), matching other startup errors.
- Extract the disk-candidate enumeration in resource_sampler.rs that
available_space_for_path had copy-pasted from sample_disk_resources.
Test fixture cleanups:
- Route all hand-assembled Database::new(..., test_blob_store()) test
fixtures (32 sites) through fabro_store::test_support::test_database,
and make that helper infallible instead of returning an unconditional
Ok.
- Install the test blob schema from fabro_db::BLOBS_MIGRATION_SQL via a
test-support-gated optional dependency instead of a four-level
relative include_str! into fabro-db's migrations directory.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Apply the cleanup findings from a four-angle review (reuse,
simplification, efficiency, altitude) of the demotion change:
- Share one size gate: serialized_if_over now backs both offload_value
and demote_value_for_prompt, restoring the cheap short-string and
scalar pre-checks so per-node demotion no longer serializes every
small value just to measure it.
- Stop re-writing blobs every node: materialize_value_bytes writes the
sandbox file directly from the in-hand bytes and short-circuits on the
content-addressed file's existence, so an already-demoted value costs
one existence probe instead of a store round-trip per node visit. The
local file write is shared with materialize_blob_ref.
- Demote over the resolved snapshot map instead of re-snapshotting a
Context copy, making the context and outcome loops symmetric and
saving a full deep clone per node; the fidelity lifecycle builds the
Context after the pass.
- Skip the pass entirely for Full and Truncate fidelities (nothing
renders context values), except parallel nodes whose branch stash may
render at a richer fidelity.
- Build is_preamble_hidden_key on is_engine_internal_key instead of
restating its prefixes, and call it directly from the preamble
renderer rather than through a wrapper.
- Document that outcome updates are demoted wholesale and that
BranchWorkItem.item carries the prompt-ready (possibly demoted) item;
drop the item rebinding and redundant test assertions; restore the
local integration test's confinement assertion and make the remote
one non-vacuous.
Skipped by choice: unifying the crate's several truncation helpers and
rendering the marker through the "See:" pointer family (cross-module
coupling out of proportion to the preview cosmetics), per-branch
demotion inside parallel.results (wholesale demotion is what bounds the
total), and cross-node demotion memoization (the file-existence
short-circuit already reduces repeats to a stat).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FH8Jj9Y4E4Tu5g1jwDtHAb
Compact and summary preambles render workflow context values and stage
outputs with no per-value size limit. A late-run node inherits everything
the run has accumulated, and one oversized value (a join result, a jobs
list, a single-line command emit) can push the composed prompt past the
model's context window. A security-review run failed exactly this way:
its dedupe stage assembled a ~1.8M-token prompt against a 1M-token model
limit, made almost entirely of accumulated context the agent never
needed inline.
Reuse the existing blob machinery at the last mile. Before the preamble
builders run, any resolved context or outcome value whose serialized
JSON exceeds 8KB is persisted as a content-addressed blob, materialized
as a real file in the sandbox, and replaced with a small marker holding
a preview, the byte count, and the file path. The agent reads the file
if it needs the data. for_each items get the same treatment at fan-out
with a more generous 64KB budget, since the item is the branch's work
assignment; branch labels still come from the full item. Keys the
preamble never renders are left alone, and a value that fails to demote
stays inline and is logged: demotion bounds prompt size, it does not
gate execution.
The two downstream-resolution integration tests asserted that resolving
text values writes no files; demotion now legitimately materializes the
oversized response for preamble use, so they instead pin that resolution
returned the full inline text and that nothing is written outside the
sandbox blob directory.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FH8Jj9Y4E4Tu5g1jwDtHAb
build_branch_plan read the runtime array before run_branches looked at
`simulated`, so every for_each workflow failed under --dry-run with
"for_each source '...' was not found in workflow context". Nothing had
populated the key yet: upstream LLM nodes take Handler::simulate, which
returns no context updates.
A dry run now stands in one placeholder item when the source is absent or
unusable, and simulates the template target once. Graph-shape mistakes
still fail, since catching those is the point of a dry run.
Also from review:
- ITEM_FENCE_PREFIX replaces the bare "untrusted-" literal that
render_item_data and its test each spelled out.
- ItemRecordingHandler no longer guesses an item label by substring
search. Nothing asserted it, and the third item's label "2" matched
stray hex from the random fence tag about two thirds of the time.
- The twin test reads keys::PARALLEL_RESULTS instead of the raw string.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Simplification pass over the for_each branch. No behavior change.
Share what was duplicated:
- Node::prompt_or_label replaces the "prompt, else label" fallback that
agent, prompt, and the for_each item injector each wrote out.
- context::lookup_flat replaces the "exact key, then strip context."
lookup that condition.rs had twice and the for_each source had again.
- is_llm_handler_type replaces the inline agent/prompt match, so the
runtime and the for_each_contract rule agree by construction.
- find_join_node now takes branch ids, so a for_each fan-out passes its
template target instead of needing find_join_for_target.
- collect_events moves to test_support; parallel and integration tests
shared one copy already.
- One ScriptedHandler replaces four test handlers that differed only in
what they returned.
Straighten the branch retry loop:
- Reserve the branch scope once before the loop instead of guarding it
with an Option, which removes three expect() calls.
- acquire_branch_permit and backoff_or_cancel replace the cancel-aware
select! blocks the loop repeated verbatim.
- Keep the match arms in Executor::execute_with_retry order so the two
loops stay easy to compare.
Drop redundant state:
- BranchPlan::is_for_each derives from template_target_id.
- for_each_contract checks node type before source shape, so one
mistake reports one diagnostic.
Prove the new wire fields survive the OpenAPI boundary: the fabro-api
round-trip fixture now carries index and item_label.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Restore the documented SDK env credential facade without reintroducing run fallback behavior. Fail closed on GitHub permission resolution, require worker storage at the CLI boundary, and align interpolation names and generated docs.
`ModelResolutionOptions` was a field-for-field duplicate of the existing
public `ModelResolutionTransform`, down to a verbatim copy of its `new()`.
`pipeline::transform` then unpacked one to rebuild the other, cloning the
catalog Arc and the eligible-provider set on the way.
- Delete `ModelResolutionOptions`. `TransformOptions.model_resolution` now
holds an `Option<ModelResolutionTransform>` directly, so the TRANSFORM
step is `resolution.apply(graph)?` with no rebuild and no clones. This
is consistent with `custom_transforms`, which already holds transforms.
- Add `ModelResolutionTransform::catalog()` so the VALIDATE step can reach
the same catalog for its lint rules. That is the only new code needed.
- Drop `CatalogScope` from `operations::validate`, which was a third copy
of the same fields. The three entry points now hand a partially built
transform to `validate_resolving_models`, which completes it with the
workflow's default provider once the workflow is resolved.
- Extract `validate_child_workflow` in `manager_loop`, collapsing two
near-identical validate-and-unwrap blocks.
- Point the transform tests at their own `transform_options()` helper via
struct-update syntax instead of respelling all seven fields, and drop a
HashSet -> Vec -> HashSet round trip from the create test helper.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Follow-up cleanup on the catalog-free validation split. Same behavior,
fewer parallel code paths.
- Make the catalog an explicit `Option<&Catalog>` on `pipeline::validate`
instead of a `validate` / `validate_with_catalog` pair, so each call
site states whether catalog rules run.
- Collapse `preprocess_and_validate`, `preprocess_and_validate_structural`,
and `preprocess` into one function that takes `TransformOptions`. Its
`model_resolution` field is now the single source of truth for catalog
awareness, which drops a 12-argument signature and the
`too_many_arguments` allow.
- Replace the duplicated resolve-and-preprocess block in
`operations::validate` with one `validate_in_scope` helper, and drop the
HashSet -> Vec -> HashSet round trip on the catalog path.
- Extract `configured_default_provider`, previously duplicated between
`operations::create` and `operations::validate`.
- Delete `validate_manifest_with_environment_defaults`, which had no
callers outside its own module.
- Share the `server-model.fabro` fixture between the two CLI tests instead
of inlining it twice. The validate test now asserts the rendered output
through the usual snapshot helper, which also removes a hand-rolled
`std::fs::write` and its clippy allow.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
`EnvCredentialSource` resolved provider credentials from the process
environment. It had no production entry point of its own — it was only
ever reached as the `None` arm of an `Option<Vault>` in three places:
`build_llm_source`, `configured_providers_for_start`, and
`configured_providers_from_process_env`.
That optional vault is not a state the product can be in. Every run has a
server behind it, the server always spawns workers with `--storage-dir`
(`worker_runtime.rs`), and `SqlVaultCredentialSource` backs both the
server and the CLI. So the fallback only served to silently degrade
credential resolution to whatever the worker process happened to have in
its environment.
Make the vault required across the run path — `RunOptions`,
`StartServices`, `build_llm_source`, `tool_secrets_from_configured_sources`,
`vault_token_lookup`, and the CLI GitHub helpers — so the invariant is
enforced by types rather than assumed. A worker spawned without
`--storage-dir` now fails with a clear message instead of quietly
continuing without a vault.
`configured_providers_from_process_env` had no callers at all and is
deleted. `AgentApiBackend::new_from_env` was public but only ever called
from its own tests; it is deleted too.
Test-only credential sources move to a feature-gated
`fabro_auth::test_support`, wired through dev-dependencies so they never
link into production builds. The CLI worker tests now pass
`--storage-dir`, matching what the server actually does.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The DOT parser created a node for every edge endpoint, and nothing
recorded whether a node came from a declaration or was synthesized from
an edge. The edge_target_exists rule only checked whether the node id
was present in the graph, which was always true by then, so a misspelled
endpoint became an attribute-free node that defaulted to shape=box — an
LLM stage. Validation emitted a prompt_on_llm_nodes warning and exited 0.
Node now carries `implicit`, set only when the parser synthesizes the
node from an edge endpoint. A declaration anywhere in the workflow
clears it, so order does not matter and subgraph declarations count.
Node::new leaves it false, so programmatic construction and graphs
deserialized from older checkpoints read as declared.
edge_target_exists treats an endpoint as valid only when it exists and
is declared, reporting each undeclared node once. The near-identical
missing-source and missing-target branches collapse into one path. The
import transform copies the flag onto spliced nodes so an edge-only node
inside an imported fragment is caught too.
parse_and_validate_human_gate had two edge-only nodes and now declares
them; it was an instance of the bug rather than a casualty of the fix.
No shipped workflow, docs example, or CLI fixture relied on the old
behavior.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
