Commit graph

1169 commits

Author SHA1 Message Date
Scott Werner
c2d6dc4a92 Align run-tool creation with server admission 2026-09-12 10:57:46 -06:00
Scott Werner
c67c60eeba Create run tools from immutable workflow versions 2026-09-12 10:57:22 -06:00
Scott Werner
410651d781 Bound workflow packaging depth and reject invalid supplied configs 2026-09-12 10:15:29 -06:00
Scott Werner
d5dec0fffb Add content-based workflow version registration tools 2026-09-12 10:15:19 -06:00
Bryan Helmkamp
957fc97c5c
Merge origin/main into pebble-agent-loop
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>
2026-09-12 09:40:00 -06:00
Bryan Helmkamp
18a3c4741e
Run agent stages, Ask Fabro, and fabro exec on pebble's CodingAgent
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>
2026-09-11 14:19:15 -06:00
Bryan Helmkamp
d986fc9751
Keep the sandbox driver's events whole as run events
A bridge translated the driver's events into thirteen lifecycle variants
of fabro's own (start, stop, and delete phases, image pulls, snapshot
builds) and dropped everything else the driver reported, pairing an image
pull's first progress report with the create's completion to invent a
duration. The driver's event is now stored as the run event itself, under
a name derived from it: subject, action, and phase (sandbox.stop.completed,
sandbox.create.progress for an image pull, snapshot.create.started), or
<subject>.state and <subject>.notice. Every operation the driver performs
on the run's sandbox lands on the run, including creates and state
observations the bridge skipped. The CLI reads image pulls and snapshot
builds from the driver's event for its setup progress and pretty output,
the thirteen variants and their props go, and a run stored under the old
names still reads as an unknown body. Checkpoint file numbers in a dump
shift because the run records more events before each checkpoint.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-11 13:32:54 -06:00
Bryan Helmkamp
5588ae3648
Run the agent's MCP servers and the service listing through the driver's services facet
The agent launched a sandbox MCP server with its own setsid wrapper and
PID handling, polled ss for the port in a shell loop, and read a fixed log
file for failures; the server listed a sandbox's services with its own ss
and procfs scripts and parsers, and told the API which one it had used.
The driver's services facet now does both: the agent spawns the server as
a service, waits for the port, reads the service's logs on failure, and
stops it on cancellation; the server lists the driver's listening ports,
grouped by port with the process names the sandbox can give. The
discovery source leaves the API and the web panel's iproute2 tip goes
with it.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-11 13:18:02 -06:00
Bryan Helmkamp
29e7e77c75
Let the Daytona provider cache images as snapshots instead of fabro
Fabro named Daytona snapshots by an HMAC of the image or Dockerfile, the
resources, and the API key, ensured them through the driver's snapshot
service before every create, and threaded that work through a create
plan so the sandbox could learn the snapshot it came from. The driver's
Daytona provider now does this inside create: an image or Dockerfile
spec is built once into a snapshot named by its inputs under the API key
and reused for the same inputs, with the build reported through the
create's events. Fabro's overlay only fixes the working directory,
names the run, sets the timers, and falls back to Daytona's default
snapshot; the sandbox reads the snapshot it came from off the driver's
status after the create. The snapshot identity module, the ensure step,
the create plan, and fabro-sandbox's hashing dependencies go. Snapshot
names change from fabro-<uuid> to the driver's sandbox-driver-<hex>, so
existing snapshots are rebuilt once.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-11 13:11:16 -06:00
Bryan Helmkamp
d24042ba64
Put the driver's sandbox status on the API instead of a projection
Fabro projected the driver's status into its own state enum, resource,
network, and timestamp types for the run sandbox and inventory endpoints,
losing the provider's state string, the network policy, the sandbox kind,
and the driver's own vocabulary along the way. The API now carries the
driver's SandboxStatus itself: SandboxDetails is fabro's run record beside
the status, SandboxInfo is the provider beside the status, and the
OpenAPI schema describes the driver's types (state, resources in the
units the driver reports, the network policy, the sandbox kind, workspace
ownership) which fabro-api reuses through with_replacement with round
trip tests proving identity and JSON parity. The projection types and
their conversion go; the web sandbox page and summary panel read the
status directly, and the TypeScript client is regenerated.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-11 13:07:00 -06:00
Bryan Helmkamp
7d9d2bf5f3
Run fabro's git plumbing through the driver's verbs
Fabro assembled its own hardened git command lines (maintenance, hooks,
fsmonitor, path quoting, signing, the file transport, external diff
drivers) in three crates and parsed raw diff, numstat, cat-file, and log
output itself. The driver's git facet now carries fetch, rev-parse,
ancestry, diff entries, numstat, patch, log, blob sizes and contents,
config, untracked files, and stage-all, hardened by default and typed, so
the checkpoint commit, the run diffs, the Run Files listing and blob
reads, the commit log, the fork fetch, the agent's changed-files
detection, and the git identity setup go through it. The parsers and the
command prefixes go; the per-run capability probe keeps its own plumbing
script. Checkpoint commits never run repository hooks now, so
skip_git_hooks and commit_timeout are accepted for compatibility only.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-11 12:55:39 -06:00
Bryan Helmkamp
370a6c96d5
Give the checkout its GitHub credentials through the driver's store
The GitHub App token reached the agent's git commands through the origin
URL: after the clone fabro ran `git remote set-url origin` with the
token embedded, then tracked which generation the URL carried, held an
embed lease across every push so a refresh could not rewrite the URL
mid-operation, re-embedded on the first auth-shaped push failure in
case the agent had rewritten origin, and redacted the URL out of every
log line and output tail. The token showed in `git remote -v` and
`.git/config`.

The driver now installs ambient credentials for a checkout: one
credential-store line beside the checkout and a `credential.helper`
entry pointing at it, with the remote URL untouched. Fabro's part is
`credentials.rs`: the token source, one mint for the clone, one resolve
per push operation, and the facet call. The clone carries the token per
call and installs it afterwards; the ACP refresh tick rewrites the store
instead of the URL; fabro's own pushes pin one resolved token for the
whole operation and pass it per call, so nothing is ever re-embedded and
a retry after replication lag presents the same token by construction.

Gone with the URL: `push_credentials.rs`, `redact.rs`, the lease and
drift repair in `git_push`, `RefreshOutcome`, and the `credential_action`
and `refresh_error` fields on push attempt events. Stored events that
carry those keys still read. A failed store install after the clone now
fails setup, where a failed `set-url` used to be logged and repaired by
the first push. The one remaining caller of the URL redactor, the
server's repository probe, uses `DisplaySafeUrl::redact_in`.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-11 10:02:01 -06:00
Bryan Helmkamp
2e8d6b8a3d
Merge origin/main into the sandbox-driver adoption
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>
2026-09-10 13:37:11 -06:00
Bryan Helmkamp
619cb44e3c
Import lithos-llm types directly instead of through fabro-types
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>
2026-09-10 10:03:08 -06:00
Bryan Helmkamp
fa3e485c95
Name built-in providers through lithos catalog::builtin
lithos-llm now ships the built-in provider ids and constructors, so
fabro-types drops its provider_ids module and every caller uses
lithos_llm::catalog::builtin directly. The crates that name a provider
now depend on lithos-llm themselves.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-10 09:48:37 -06:00
Bryan Helmkamp
87e1e3a00f
Replace fabro-llm helper modules with lithos-llm equivalents
Delete fabro-llm's attachments, reasoning, and structured modules and
the LlmError newtype and ErrorFacts trait. lithos-llm now provides all
of them: InlineLocalFiles under the local-files feature, ReasoningOutput
with Response::reasoning(), Client::complete_object, and the retry,
auth, cancel, and failover predicates directly on Error and ErrorData.
fabro-llm keeps only failure_signature_hint, which is Fabro's own loop
detection policy.

Store ErrorData directly in the agent and workflow error enums, boxed
where the variant would otherwise dominate the enum size. Repin
lithos-llm to a1e3fd3 for these additions.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-10 09:41:20 -06:00
Bryan Helmkamp
3510d5081d
Implement the lithos CredentialProvider trait directly
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>
2026-09-10 09:16:39 -06:00
Bryan Helmkamp
3f721dd032
Consume the sandbox driver's events directly in the workflow
Fabro-sandbox carried its own SandboxEvent enum and a callback for it.
The run sandbox wrapped every lifecycle call to emit a start, completed,
or failed variant with its own clock, and re-described the driver's
create-time progress as snapshot events through an observer that lived
next to the run sandbox. The workflow then converted that enum to the
wire. The driver already reports every operation it performs, so the
enum was a second, hand-maintained copy of that stream.

The workflow now observes the driver's events directly. A run's sandbox
is created or attached with a driver EventContext whose observer is the
new SandboxEventBridge in the workflow's event module. The bridge turns
the driver's start, stop, and delete operations, its image pull inside a
create, and its snapshot builds into the workflow's SandboxLifecycle
events, stamping fabro's provider name so the run keeps recording
`local` rather than the driver's `host`. The pipeline emits the
initializing, ready, and failed events itself around bringing the sandbox
up, since that composite step — create, activate, prepare the workspace
— is the pipeline's, not the driver's. Fabro-sandbox emits no events of
its own any more; the run sandbox gained console_url for the ready
event, and a local sandbox can be created with an event context.

The wire keeps every name the CLI reads. Two families go: the cleanup
events, which only the server's manifest validation could have produced
and it passed no callback, and the git clone events, which nothing read
and whose facts the sandbox.initialized event and tracing already carry.
The ready event drops the cpu and memory fields no provider ever
populated. Daytona snapshot events now come from the driver's ensure
call, so a snapshot that already exists and is active reports nothing
rather than a creating-and-ready pair that did no work.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-10 00:37:42 -06:00
Bryan Helmkamp
6e874aff5b
Retire the fabro Sandbox trait for one concrete RunSandbox
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>
2026-09-10 00:14:42 -06:00
Bryan Helmkamp
7ef09968f2
Document the catalog overlay without the metadata.fabro namespace
The `[llm]` reference now describes `enabled`, `api_key_url`,
`stands_in_for`, `small_default`, `probe`, `family`, and the cutoffs as
lithos fields, the coding harness under `metadata.agent`, and the secret
names lithos derives for operator-defined providers. Secret-bearing
headers go in `default_headers` as `{{ secrets.NAME }}` tokens. The
integration guides enable a provider with `enabled = true` on its table.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-09 23:26:48 -06:00
Bryan Helmkamp
6dfc96d3fd
Resolve provider secrets through lithos conventional credentials
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>
2026-09-09 23:00:08 -06:00
Bryan Helmkamp
0c569638fe
Map an environment onto one sandbox spec for every provider
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>
2026-09-09 22:41:09 -06:00
Bryan Helmkamp
5b035d3f75
Name plugins by their configured kind and drop out-of-process bundled kinds
sandbox-driver PR #9 removes the check that a plugin's declared kind match
the configured one: an operator who configures a path and pins its
checksum has already chosen the executable, so the configured kind is
fabro's name for whatever it serves. With that in the driver, fabro no
longer needs plugin settings on a bundled kind to reach Docker over the
wire. Bundled kinds reject plugin keys again, `connect_provider` links a
bundled kind in-process and launches everything else, and the CLI
scenarios run the Docker executable under the non-bundled `docker-plugin`
kind. The driver pin moves to the PR head until it merges.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-09 20:13:50 -06:00
Bryan Helmkamp
030e653abf
Run plugin providers end to end and gate them in CI
Closes the sandbox-driver adoption: any provider a sandbox-driver plugin
executable serves can now host a fabro run, and fabro's own bundled
providers can be served the same way.

- `SandboxSpec::Plugin` builds a normalized driver spec from the
  environment (image or Dockerfile source, or a provider-managed
  directory; resources; network policy; labels; env) and lays fabro's
  repository checkout out inside the provider's working directory. The
  layout is recorded on the run through the new `workspace_layout` trait
  method.
- Plugin settings on a bundled kind (`[server.sandbox.providers.docker]
  path = ...`) serve that kind out of process through the driver's
  executable; the config layer no longer rejects them.
- `ProviderAccess` carries the server's provider settings and the vault's
  Daytona credentials to every reconnect: run resume, sandbox details,
  terminals, previews, and the worker's start path. The worker receives
  the settings through `StartServices`. No "plugin not wired" errors
  remain.
- The CLI worker requires GitHub credentials only when a repository will
  be cloned; a `none` target on a clone-based provider creates an empty
  workspace and needs none.
- fabro-db tracks its migrations directory so a new migration file
  recompiles the crate; the environment provider migration had been
  silently missing from stale builds. Environment store 500s now log
  their cause.
- The CLI workflow scenarios run against `host-plugin` (the driver's
  Host executable under the non-bundled `host` kind) and `docker-plugin`
  (the bundled `docker` kind served over stdio), each on an isolated
  server, printing the server log on failure. A live Daytona gate runs
  the native git clone over the JSON-RPC wire. A new CI job runs the
  plugin scenarios and the driver-backed Docker integration tests with
  the plugin executables built.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-09 19:54:57 -06:00
Bryan Helmkamp
28d4242df0
Route Daytona sandboxes through the sandbox driver
The `daytona` provider kind now maps onto the sandbox-driver Daytona
provider instead of fabro's own SDK client. Fabro keeps what is its own:
the HMAC-named snapshot built from the environment's image or Dockerfile,
the explicit 120 minute auto-stop default, the managed labels that gate
destructive operations, the clone decision and layout, and push
credentials. The driver creates the sandbox, clones natively, and serves
exec, files, search, terminal, SSH, preview, and VNC through its facets.

- `daytona.rs` builds the driver `SandboxSpec` (snapshot source,
  `/home/daytona/workspace`, labels, timers, network policy, run name),
  ensures the snapshot through the driver `SnapshotProvider`, attaches by
  persisted id with fabro's label guard, and probes credentials through
  the provider health check under fabro's 20 second budget.
- `DriverSandbox` gains a create plan that settles the spec right before
  the provider call, records the snapshot a sandbox came from, and
  reports the provider console URL on `Ready`.
- Terminals use the driver `Pty` facet; the server's SSH, preview, and
  VNC endpoints use the `SshAccess`, `PreviewUrls`, and `Vnc` facets
  through the driver-typed reconnect. The preview endpoint now answers
  for every provider with a preview facet, so the local sandbox returns
  its loopback URL.
- Daytona credentials travel as `DaytonaCredentials` built from the
  vault key plus configured URL and organization; nothing reads the
  process environment implicitly. The inventory registry uses the shared
  `DriverInventoryProvider`.
- The SDK-based `daytona/mod.rs`, `provider/daytona.rs`, the Daytona
  terminal, the `daytona` cargo feature, and the direct daytona-sdk,
  git2 (in fabro-sandbox), tungstenite, and rustls dependencies are
  gone. The live Daytona tests run against the driver-backed sandbox.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-09 19:14:13 -06:00
Bryan Helmkamp
5f49cdf9da
Delete fabro-model and document the lithos catalog overlay
fabro-model's ids and billing rollup now live in fabro-types, and its
pricing, catalog, provider TOMLs, and legacy index are replaced by the
lithos built-in catalog plus the Fabro policy layer.

Regenerate the configuration reference for the `[llm]` overlay and
`metadata.fabro`, and rewrite the SDK, models, and integration docs for
the lithos provider and model shapes.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-09 17:26:57 -06:00
Bryan Helmkamp
75e5f34c0d
Expose lithos request and response shapes through the API, server, CLI, and web
The OpenAPI spec adopts the lithos request, response, content part,
tool, usage, and cost schemas. The completions endpoint returns the
lithos `Response` JSON verbatim and SSE carries lithos `StreamEvent`s
verbatim. The models and providers endpoints serve the fabro-types
catalog views, and the install and model-test flows probe providers
through fabro-llm.

The CLI builds its catalog from the operator overlay, drives `fabro exec`
through the server gateway adapter, and parses reasoning effort with the
shared controls. The web app reads content parts as lithos-tagged
objects. The TypeScript client is regenerated.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-09 17:26:57 -06:00
Bryan Helmkamp
3d33935fba
Route Docker sandboxes through the sandbox driver
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>
2026-09-09 17:07:51 -06:00
Bryan Helmkamp
80bc51c40e
Open sandbox provider identity to plugin kinds
SandboxProviderKind is now a validated string newtype instead of a
closed enum. The bundled kinds (local, docker, daytona) keep their
constants and a BundledProvider enum for the code paths that still
dispatch on them; any other well-formed sandbox-driver kind name is
accepted and names a plugin executable. EnvironmentProvider is gone:
environment settings carry SandboxProviderKind directly, and
is_clone_based is replaced by a workspace policy where local runs in a
designated directory and every other provider clones.

Server sandbox policy is keyed by kind. [server.sandbox.providers.<kind>]
accepts the bundled kinds with `enabled` and any plugin kind with its
launch settings (path, sha256, dev, args, env, inherit_env); bundled
kinds reject the plugin keys and a kind with no entry is disabled. The
OpenAPI schema, generated Rust and TypeScript clients, web settings
pages, and docs follow. The environments table drops its provider CHECK
enumeration in favour of the kind name rules so a plugin environment
can be stored.

Bundled-only code paths (run start, preflight, reconnect, terminal,
details) now fail with an explicit message for a plugin kind until the
driver construction function lands in the next step.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-09 15:17:32 -06:00
Bryan Helmkamp
b6482910e5
Remove expired startup secret migrations 2026-09-05 14:05:48 -04:00
Scott Werner
ab7cbeb4ae
Merge pull request #839 from fabro-sh/codex/remove-playground
Remove unsupported workflow playground
2026-09-04 11:18:00 -04:00
Scott Werner
f1b569d9e6 Remove unsupported workflow playground 2026-09-03 12:04:35 -04:00
Scott Werner
c5010c0b33 Simplify the Local pull-request admission check
Use the shared clone-based provider predicate and rely on the settings
resolver dropping disabled pull-request settings instead of re-checking
the enabled flag. List the new intent-lane error code in the OpenAPI
description, trim the acceptance tests to what they actually prove, and
fold the docs note into the existing requirements sentence.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-03 11:43:29 -04:00
Scott Werner
18cb752b61 Reject automatic pull requests for Local runs 2026-09-02 17:15:52 -04:00
Scott Werner
e3cbc31ca1 Harden CLI run target identity 2026-09-02 12:59:04 -04:00
Scott Werner
ccfd23104d Harden CLI run intent creation 2026-09-01 17:08:34 -04:00
Scott Werner
2507a0075f Create CLI runs from immutable workflow intents 2026-09-01 16:14:34 -04:00
Scott Werner
0fd4714da7
Merge pull request #825 from swerner/codex/automation-workflow-sources
Add independent workflow sources to automations
2026-09-01 12:22:20 -04:00
Scott Werner
5af791c812 Align remote workflow selectors with run targets 2026-08-31 17:13:20 -04:00
Scott Werner
39c018c430 Harden automation workflow source handling 2026-08-31 13:45:08 -04:00
Scott Werner
b61d309aa3
Merge pull request #827 from fabro-sh/codex/run-intent-registration-spine
Add RunIntent registration support
2026-08-31 13:44:08 -04:00
Scott Werner
05fb173767
Merge pull request #823 from fabro-sh/codex/sqlite-run-history-activation
Activate atomic SQLite run history storage
2026-08-31 12:53:11 -04:00
Scott Werner
c68e67c841 Harden SQLite activation and run history consistency 2026-08-31 12:19:16 -04:00
Scott Werner
03f81d1f25 Add independent workflow sources to automations 2026-08-30 13:14:11 -04:00
Scott Werner
e87130ae23 Require a server-managed environment for automations
Automations now store an environment_id that must reference an enabled
Docker or Daytona environment. Each trigger fire resolves the current
environment definition and snapshots its settings into the run, and
deleting an environment still referenced by an automation is rejected
with a conflict.

Existing automations are backfilled conservatively: a compatible
environment named default is selected when present, otherwise the sole
compatible environment. Anything ambiguous is left incomplete and cannot
run until an operator selects an environment in the web UI.

Scheduler failures are recorded on the automation as last_error and
cleared after the next successful scheduled run.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-30 09:58:13 -04:00
Scott Werner
1a1c5ab29d Add RunIntent registration support 2026-08-28 20:40:38 -04:00
Scott Werner
f073684227 Activate atomic SQLite run history storage 2026-08-28 15:18:25 -04:00
Bryan Helmkamp
b34f2b8207
Allow Daytona snapshots from Docker images 2026-08-27 15:02:50 -04:00
Scott Werner
a65c4ff779 Migrate automations to canonical run targets 2026-08-26 17:35:36 -04:00
Scott Werner
fbba98defd Add tag support to Git run targets 2026-08-26 11:16:37 -04:00