Pebble's stream is the agent event contract. The run's own agent.mcp.ready,
agent.mcp.failed, and agent.mcp.disconnected events, which mirrored pebble's
McpServer* events, are gone with their props, the sink arms that emitted
them, and their conversion and naming entries; pebble's stored
agent.mcp.server.* events are the only record and feed the stage's fold.
The sink no longer mirrors RouteFailover onto agent.failover either: an
agent stage's moves are pebble's agent.route.failover. The event is now
prompt.failover, emitted only by a one-shot prompt stage that walks its
fallback plan itself, and its props are trimmed to the two routes, the
attempt, and the error; nothing read the rest.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
An agent stage that failed billed nothing: the backend returned a bare
error and the outcome built from it carried no usage. A terminal failure
now becomes the stage's failed outcome from the same fold that bills a
completed stage, with the tree's usage, the rows by model, the files it
wrote, and its active time; stage.failed carries billing and
billing_by_model and the store keeps both. Cancellation and retryable
failures still go up as the error.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
One usage rule: a stage's usage is its session tree's, the root and every
subagent, live and at completion. The worker's event sink folds pebble's
SessionProjection over the events it records and the stage's billing and
files come from that fold at stage end, so the completed values are what
the run showed live. The store's live usage is the fold's tree usage, and
completion brings the catalog's price for the same tokens instead of
resetting them to the root's.
Fabro keeps catalog pricing: the root at its route, each descendant at its
own route where the catalog knows it and at the root's otherwise, a
provider-reported cost standing in where pebble has one. The rows travel
as billing_by_model on stage.completed and the stage projection, and the
billing rollup splits by_model by them.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Pebble's SessionProjection reads ProcessingEnd to complete a prompt and mark
the session idle, so a projection rebuilt from the run's log needs it: one
small event per prompt. The four pebble events the sink mirrored onto
fabro's own agent.failover and agent.mcp.* are now stored verbatim as well,
so the fold sees the route moves and the MCP outcomes; the mirrors stay
until every reader is on the projection.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Resolve conflicts between the metadata-branch removal and the
sandbox-driver adoption on main:
- fabro-sandbox docker.rs, sandbox.rs, daytona/mod.rs: take main's driver
rewrite. The Sandbox trait is gone, so the PR's push_token_source
removal now applies to RunSandbox instead; drop that accessor and the
RepoCredentials::source helper that only served it.
- run_metadata.rs: keep deleted. Main's edits there were adaptations to
the driver API and the run git identity field.
- lifecycle/git.rs, finalize.rs: keep the PR's removal of metadata
snapshots and write_finalize_commit; carry main's RunSandbox,
GitRetryPolicy, git_identity, local_sandbox, and test catalog changes.
- sandbox_git.rs: take main's version and drop the shadow_sha parameter
and Fabro-Checkpoint trailer.
- git_integration.rs: remove meta_branch from the new git identity test.
- Cargo.toml: main's dependency set with fabro-dump kept as a
dev-dependency.
- checkpoints.mdx: keep both the git identity paragraph and the durable
execution state section.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The existing failover test asserts the backup continued the turn after
the primary committed a tool result. A new test exhausts a two-route
chain and checks that one agent.failover and one
agent.route.failover.stopped are stored on the work stage, the stop
after the error it reports, with the exhausted reason and the failing
route. The events catalog documents both.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Pebble's RouteFailover event now describes the route that failed and how
the new route carried the prompt on. Record the continuation on fabro's
agent.failover event as an optional string (replay_prompt or
continue_turn); events written before it existed, and one-shot prompt
stages that walk the plan themselves, read as absent. The failed route's
usage, cost, and timing are not mirrored: the stage's totals already
include them through the prompt report, and no fabro run event carries
per-route usage yet.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Pebble reports an MCP server whose connection closed mid-session once,
as McpServerDisconnected, and carries startup_ms on McpServerReady and
McpServerFailed. The workflow event sink mirrors the disconnect onto a
new agent.mcp.disconnected run event shaped like agent.mcp.failed, and
passes startup_ms through on agent.mcp.ready and agent.mcp.failed. The
raw pebble event is not stored for these, so the timing would otherwise
be dropped at the boundary.
The stage projection's McpServerStatus gains a `disconnected` kind next
to `ready` and `failed`. The fold keeps the server's tool count and
sticky invoked flag and only moves the status. The OpenAPI
McpServerStatus oneOf gains McpServerStatusDisconnected, and the
fabro-api round-trip test covers its JSON shape. A new
session_projection_parity test folds the same MCP events through
pebble's SessionProjection and fabro's stage projection and compares
them, including pebble's `disconnected`.
ToolErrorKind::Timeout needs no fabro change: the kind is stored as
pebble serializes it and never matched.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Pebble's McpServerReady and McpServerFailed events now carry startup_ms.
The workflow event sink destructured both variants by name, so it stops
listing every field. The pin is temporary: it moves to pebble main once
lithoscomputer/pebble merges the branch.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A run now resolves a single author and committer identity once, after its
GitHub credentials are selected and before anything can commit, and uses it
for every commit it creates. Resolution order: a complete explicit
`run.git.author`; the run's GitHub App bot account
(`<slug>[bot] <id+slug[bot]@users.noreply.github.com>`); the authenticated
user of the run's PAT; the generic `Fabro <noreply@fabro.sh>`. A partial
explicit author overlays the fields it supplies. Only the selected
credential is consulted; a failed lookup is a setup error. A standalone
installation token falls back to the generic identity with a warning.
The resolved identity is carried on `RunOptions` and `EngineServices`,
recorded as a `git.identity.resolved` event and `RunProjection.git_identity`
so resume reuses it, and exposed through the run state API. Engine
checkpoints and metadata commits read it through `RunOptions::git_author`.
Every workflow execution path receives it as `GIT_AUTHOR_NAME`,
`GIT_AUTHOR_EMAIL`, `GIT_COMMITTER_NAME`, and `GIT_COMMITTER_EMAIL`, applied
last so it wins over inherited host variables and `[run.environment]`
entries: prepare steps, command stages, native agent shell tools, and ACP
launches. The identity is injected even without a Git origin, and the old
local `git config user.*` write is removed.
fabro-github gains `GET /user` and `/users/{slug}[bot]` lookups with mocked
tests for success, unauthorized, malformed, and transient cases. Real-Git
integration tests commit in the primary checkout, a clone, and a fresh
repository under conflicting local config, `[run.environment]`, and host
variables, and prove concurrent runs do not leak identities. CLI workflow
tests cover host script stages and ACP launch env through `fabro run`.
Docs and generated option metadata now describe the credential-derived
defaults instead of the stale `fabro`/`fabro@local` values.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
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>
Pebble's `SteeringBus` now owns the map of live sessions, the buffer for
steers that arrive between sessions, fan-out of steers and interrupts, the
close-the-door detach, and the hold that keeps a paired session open. The
hub keeps what only fabro knows: pair records, principals, stage ids, and
the run events that put bus activity on the run's stream in the order its
consumers expect. `PebbleControlHandle` is gone, since the coding agent's
control handle is a bus session natively; the ACP session joins the bus
through a small adapter and carries pebble's steering message end to end,
so a human steer keeps its author on the ACP `agent.steering.injected`
event. A pair message that evicted an older steer is now accepted and the
eviction recorded, where before it was queued and reported as refused.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Steps 4, 6, and 7 of .ai/plans/pebble-absorbs-embedder-concerns.md,
pinning pebble fc907a1 with its `search-providers` feature.
The sandbox's `Environment` adapter uses pebble's `environment::support`
for the glob grammar check, the tree-order sort of a listing, and the
capture accounting, in place of its own copies; the adapter itself stays.
The stage reads the compactions a prompt performed from the report, as a
breakdown of the usage it already billed. `web_search.rs` keeps the
vault-backed credentials and the Brave-over-Venice preference, and hands
pebble's `Brave` or `Venice` provider a fabro HTTP client; the providers
and their tests are pebble's now.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Steps 5 and 8 of .ai/plans/pebble-absorbs-embedder-concerns.md, pinning
pebble 49da137.
Agent stages and `fabro exec` ask pebble for the profile's instruction
files from the repository root down to the working directory
(`MemoryDiscovery::from_git_root`), which fabro lacked: it read the
working directory alone. Skill directories are pebble's to resolve too:
the user's skills directory, then `.fabro/skills` and `skills` under the
repository root. Prompt stages keep reading the working directory alone,
through the same discovery and loader, so `agent_memory.rs` keeps only
that call; the filename table is pebble's now.
A retained thread's export comes from `export_for_reuse`, which closes
the session and hands back an export whose cursor is already past the
close, in place of export, shutdown, and a cursor advance by hand. Ask
Fabro resumes a stored record with `resume_after`, the rule it applied
under the older name.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Step 3 of .ai/plans/pebble-absorbs-embedder-concerns.md, pinning pebble
6cdb30a with its `mcp` feature.
Pebble starts the stage's MCP servers while the agent is built, registers
their tools under `mcp__{server}__{tool}` with `ToolSource::Mcp`, and
closes them with the agent, for all three placements: a child of the run
worker over stdio, a server over HTTP (streamable or SSE), and a server
launched in the run sandbox and reached through the sandbox's preview
URL. `fabro_mcp::pebble::pebble_server` maps `McpServerSettings` onto
pebble's `McpServer`, keeping fabro's `/sse` path for sandbox-hosted SSE
servers; `RunSandbox::port_routes` hands pebble the driver's `PreviewUrls`
facet as the route to a sandbox port. The stage's event sink mirrors
`McpServerReady` and `McpServerFailed` onto the run's `agent.mcp.ready`
and `agent.mcp.failed` events, as it mirrors `RouteFailover` onto
`agent.failover`, and stores no second copy of a mirrored fact.
Deleted: `sandbox_mcp.rs`, the MCP branches of `pebble.rs` and `fabro
exec`, and fabro-mcp's client, connection manager, HTTP helpers, and SSE
transport, whose tests moved to pebble. fabro-mcp keeps the settings
re-export, the mapping, and a stdio client behind `test-support` for the
tests of fabro's own MCP server. `fabro exec` reports each server's
outcome from the agent's snapshot. The Daytona Playwright live test now
drives the sandbox-hosted server through an agent.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Steps 1 and 2 of .ai/plans/pebble-absorbs-embedder-concerns.md, pinning
pebble 1a5abe4.
Files touched come from `PromptReport`: pebble computes them from every
successful write, edit, and patch across the prompt, subagents included,
so the event-fed `FileTracking` and the tracking half of
`WorkflowEventSink` go. The stage unions the reports of its prompts.
Route failover is pebble's. The stage resolves its plan from the catalog
as before and hands pebble the remaining routes through
`fallback_routes`, each with its controls and the stage's output limit.
Pebble keeps the conversation, moves it to the next route, requeues
pending steering, and continues the prompt; the stage's plan follows the
route the report says the prompt ended on, re-activates the session
there, and mirrors pebble's `RouteFailover` as the run's `agent.failover`
event with the same payload as before. `prompt_with_failover`,
`resume_agent_on_route`, and the route bookkeeping in `LiveAgent` go.
One-shot prompt stages still walk the plan themselves.
`agent.route.failover` and `agent.tool.rounds.exhausted` join the derived
event names; both variants were falling back to `agent.event`.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Step 0 of .ai/plans/pebble-absorbs-embedder-concerns.md. Pebble's
fabro-exec-sink-max-turns branch is merged into its main (pebble 4db661c,
on the embedder-concerns branch until it lands), so fabro and petri pin
one line. Both prompt budgets survive the merge because they count
different things.
- Agent hooks use `with_max_tool_rounds`, which is what the
`max_tool_rounds` setting names and what petri does: `max_tool_rounds`
model turns may run, and the hook proceeds on a turn that still asks for
tools, so pebble gets `max_tool_rounds - 1` rounds and `ToolRoundsExhausted`
fails open. Zero rounds proceeds without an agent, as the old loop did.
Agent stages set no turn budget; the stage timeout and stall watchdog
bound them.
- Prompt stages load project memory through pebble's `ProjectMemory`, the
loader agent stages already run over `with_memory_files`, instead of a
hand-rolled copy of its budget, deduplication, and truncation.
- `fabro_sandbox::SecretRedactor` puts fabro's secret scanner on pebble's
text seams (process output tails, failed tool messages) for agent
stages, Ask Fabro, hook evaluators, and `fabro exec`. The final redaction
pass over every stored `RunEvent` stays; this does not replace it.
- Agent stages state their compaction policy explicitly: the 80 percent
threshold and six preserved turns fabro's own agent loop applied.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Each behaviour the pebble backend owes a run now has one test that drives
it through the workflow engine against a scripted OpenAI-compatible model:
- an agent stage under every harness profile (openai, anthropic, claude-5,
gemini, kimi) writing a file with that profile's own tool spelling, with
the event sequence, files touched, response, usage, and cost checked; the
codex vocabulary applies a patch through the OpenAI twin's custom tool
call, which `TwinToolCall::custom` now scripts
- steering delivered mid-stage, an interrupt with a steer, run cancellation,
and the executor-enforced stage timeout
- a question answered through the interviewer, a subagent whose events carry
its parent's session id, and an MCP tool served by a stdio server
- failover to a second provider after a tool ran, continuing the recorded
conversation without running the tool again
- a failing event sink ending the stage with the sink's error
- Ask Fabro resuming a stored record across turns, with the cursor moved
past the run's event log when the record's own cursor fell behind
- Docker and Daytona smokes running an agent stage through the provider
sandboxes
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
SandboxSpec had a Local variant beside the provider spec, and a local
sandbox was created by hand over a bare Host provider: no workspace, no
provider connection, its own reconnect, and its own push rule for the
designated directory. The local kind is now one more SandboxSpec:
SandboxSpec::local names the directory on a HostDirectory spec with a
skip clone, and provider_sandbox builds it like a plugin kind, creating
the directory when missing since the Host provider requires it to exist.
Every RunSandbox carries a workspace; a handle wrapped as is gets the
workspace of its own working directory.
The push rule is one rule for every checkout: a checkout fabro cloned
pushes with the credentials it was cloned with, and any other checkout
pushes when it has an origin, with whatever credentials it carries. A
local run therefore pushes the same way before and after a resume;
before, a reconnected local sandbox carried an attached workspace that
never pushed while a fresh one did.
Reconnect uses the recorded id for every kind. The recompute of a local
id from its directory, kept for records written before directories had
ids, is gone, and test fixtures that wrote made-up local ids derive them
through test_support::local_sandbox_id instead. A local run's record now
carries its workspace layout like every provider-chosen directory, and
the sandbox.initializing event precedes the driver's create events for
local as for every other kind.
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>
format_lines_numbered renders a file the way the agent's Read tool shows
it: every line prefixed with its number, from an offset for a limit. That
is the agent's presentation, not a sandbox concern, and it only lived in
fabro-sandbox so RunSandbox::read_file(path, offset, limit) could call
it. The function now lives in fabro-agent next to the Read tool, with its
tests, and the Read, ReadManyFiles, and Kimi ReadFile tools number the
text they get from read_file_text themselves. RunSandbox::read_file goes
away; the sandbox returns bytes or text and nothing else.
fabro-sandbox also re-exported shell_quote through a one-line wrapper so
callers could reach it from the sandbox crate or from fabro-agent. The
audited implementation is fabro_util:🐚:shell_quote; the six
importers now use it directly and the wrapper and both re-exports are
gone.
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>
The attach snapshots now carry the driver's create events, whose event
source and operation ids are minted per process and whose durations run
to the nanosecond, and the local sandbox's id is derived from a temporary
directory; the shared snapshot filters cover all three. A local sandbox's
ready event no longer names that id: the record already holds the
directory, and the id is nothing a person reads.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
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>
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>
Fabro carried its own retry loop, its own reading of what a git failure
class means for the credentials in hand, and a credential context derived
from the token snapshot. The driver now owns the loop and the decision:
a rejected credential retries only while its mint time is within the
replication horizon, a remote that could not be reached retries on its
own, a static credential fails fast, and an operation whose outcome is
unknown is never replayed. Fabro keeps its budgets as retry policies
(clone, repository probe, checkpoint push, publish push), hands the mint
time along with the token, and records the driver's attempt history as
the push attempts the events carry. Host-side git (the repository probe
and the metadata push classification) goes through the same decision
from its rendered message.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
A local sandbox was rebuilt by creating a fresh Host sandbox over the
recorded working directory, so reconnect, sandbox details, the console
URL, the recorded id, and the terminal each carried a local branch. The
Host provider now derives a designated directory's id from its path and
attaches to it from any provider instance, so reconnect goes through the
one attach path: the record carries that id, a record written before
directories had ids recomputes it from the directory, and describe works
for local like every other kind. The local provider skips the ownership
scope because a designated directory carries no labels and nothing else
shares the host's directories with fabro.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Add pebble-agent and pebble-coding-agent as git dependencies pinned to
the pebble branch that carries the live exec output sink and max_turns,
and align the shared crate versions with lithos-llm's lockfile.
RunSandbox implements pebble_coding_agent::environment::Environment
directly: rename_file over the driver's rename with a pre-created
destination parent, grep rendered as path:line:text, pebble's glob
grammar enforced before the driver sees a pattern, directory listings in
tree order, and exec over the streaming path with the output sink mapped
onto the driver's OutputSink. Pebble's EnvironmentContract runs against
the Host provider in the unit tests and against Docker in the live suite.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
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>
MockSandbox forwarded a dozen read-backs to the driver's scripted doubles
one line each: the commands run, the term stops, the stdin fed, the files
written and deleted, the lifecycle counts, whether a walk ran. Tests now
ask the double through MockSandbox::driver. The accessors that convert a
recorded spec into the shape a test asserts on stay: the last command, the
timeouts in milliseconds, the caller's environment without the exec
policy's BASH_ENV blank, and written files as text.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
DaytonaCredentials mirrored DaytonaConfig field for field and was copied
into one at connect time. It is now a newtype over the SDK configuration
with the API key always present and a Debug that never prints it; the
driver's Daytona provider connects with the configuration as it is.
Callers build it from an API key, a settings lookup, and the optional
control-plane URL, organization, and HTTP client.
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>
Fabro kept its own ExecResult, streaming request and result, output
capture stats, stdio process types, and an Error::Exec variant, each a
field-for-field copy of a sandbox-driver type with a translation layer
between them. Every command a tool, a stage, or a hook ran crossed that
layer twice.
The driver's types are now the ones fabro uses. SandboxExec applies
fabro's policy to an ExecSpec (stop grace, the run's working directory,
the explicit-env filter, the Bash helper's BASH_ENV blank winning over a
caller value) and returns the driver's ExecResult and
ExecStreamingResult as they are. Callers that stream build an ExecSpec
and ExecControls; the buffered exec_command keeps its signature.
ExecResultExt adds fabro's reading of a result: the event-facing
duration, the exit code only when the command exited on its own, the
redacted output tail, and the ExecFailure a non-zero exit becomes. The
three-way termination collapse the run events use lives in one function,
command_termination, called where events are built.
Error::Exec and the git-shaped stderr hint table are gone; a failed
command is the driver's ExecFailure, whose Display carries the label and
the classified metadata and never the raw output. OutputCaptureStats
moves to fabro-agent, whose tool output accounting it belongs to, and
converts from the driver's CaptureStats at the exec boundary. The stdio
process the ACP transport drives is the driver's own, so the cancel-token
bridge and StderrCollector go too.
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>
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>
The reasoning-effort substitution rule now lives on lithos's
ModelCapabilities, so the workflow fallback planner calls it directly
and fabro-types drops its controls module. ReasoningEffort is re-exported
from lithos alongside the other request types.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
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>
fabro-llm's catalog module held some 250 lines of listing and picking
helpers over lithos data: enabled and listed providers, model lookup by
id, alias, or wire id, matches ranked as the resolver ranks, default and
probe models, the small utility model across ready providers, the nearest
model on another provider, and cost by handle. lithos-llm now answers all
of those on `Catalog` and `CatalogProvider` through `Offering`, so the
helpers and the `ModelEntry` wrapper go.
What stays in Fabro's catalog module is its own: building the catalog from
the operator overlay, and reading the agent harness and
`reasoning_by_default` from the shared `metadata.agent` namespace. The
passthrough selection policy in `selection.rs` keeps its rules and calls
lithos for the lookups.
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-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>
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>
lithos-llm now exposes `ReasoningEffort::ALL`, `Speed::ALL`, `as_str`,
`Display`, and `FromStr` on its request-control enums. Fabro's
`controls` module kept parallel name tables and parsers for them; only
the nearest-supported-effort rule is Fabro's own, so that is what stays.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
