Commit Graph

6 Commits

Author SHA1 Message Date
Émile Ré
9156d6a16a Add wsl linter and fix
Signed-off-by: Émile Ré <emile@probo.com>
2026-05-20 09:27:28 +04:00
Aurélien Sibiril
1b62d39a2e Update agent tests for the ctx-cancel suspend contract
Rewrite the WithStopSignal-driven test in restore_test.go to use a
cancellable ctx. Update agent_test.go's "context cancellation"
case from asserting "cannot complete" failure to asserting a
SuspendedError. Add cancel_test.go covering both pre-first-turn
cancel (no LLM call, empty checkpoint persisted) and mid-run
cancel from inside a tool (just-completed turn preserved in the
checkpoint, second LLM call suppressed).

Signed-off-by: Aurélien Sibiril <81782+aureliensibiril@users.noreply.github.com>
2026-05-08 12:49:03 +02:00
Aurélien Sibiril
e5b354c3b4 Collapse RunWithOpts duplicates into variadic options
Run, RunStreamed, and Resume each shipped both a no-options form and a
mirror *WithOpts form taking variadic RunOption. Variadic parameters
are backward-compatible additions, so the wrappers were dead surface.

Make Run, RunStreamed, and Resume directly variadic and update the two
internal callers.

Signed-off-by: Aurélien Sibiril <81782+aureliensibiril@users.noreply.github.com>
2026-04-26 22:58:22 +02:00
Aurélien Sibiril
d13c83c19f Snapshot MaxTurns in checkpoint and apply it on restore
MaxTurns is the only agent bound compared against a counter that is
serialised in the checkpoint (Turns). When config drifts between save
and restore -- typically because a deploy changed WithMaxTurns or a
different build of the agent is registered by name -- cp.Turns can
exceed agent.maxTurns on the resumed run, which previously surfaced
as a warning log and then a MaxTurnsExceededError on the first
iteration of the resumed coreLoop.

Capture MaxTurns in the new AgentConfig on every save, and on
restore clone the registry-resolved agent with WithMaxTurns applied
from the snapshot. The override flows through the outer Restore path
and through both inner-agent resolution sites in
restoreNestedSuspended and restoreAwaitingApproval, so nested
runs get the same treatment. Other loop bounds
(maxEmptyOutputRetries, maxToolDepth) reset per turn / per tool
depth and stay intentionally live so deploys can tune them without
invalidating in-flight checkpoints. Live references (tools, hooks,
LLM client, approval callbacks, guardrails) are not snapshotted for
the same reason.

With the snapshot in place, the "restored agent run has already
reached max turns" warning at the top of continueFromMessages is
structurally unreachable -- the live agent's bound is now the same
value cp.Turns was bounded by at save time -- and is removed.

Signed-off-by: Aurélien Sibiril <81782+aureliensibiril@users.noreply.github.com>
2026-04-26 22:58:21 +02:00
Aurélien Sibiril
71e2d00b3a Rename CheckpointStatus to AgentStatus
The status values describe the agent state, not the
checkpoint data state.

Signed-off-by: Aurélien Sibiril <81782+aureliensibiril@users.noreply.github.com>
2026-04-26 22:58:21 +02:00
Aurélien Sibiril
363d696906 Add Restore function for agent checkpoint recovery
Restore loads a checkpoint from the store, resolves the agent from
a registry, and re-enters coreLoop. Handles suspended, nested
suspended (concurrent inner restore), and awaiting-approval states.
Partial progress is saved when some inner agents complete while
others remain suspended.

Signed-off-by: Aurélien Sibiril <81782+aureliensibiril@users.noreply.github.com>
2026-04-26 22:58:21 +02:00