Files
PaperClipAI/packages/paperclip-runner/src/contracts/native-session-backend.ts
T
Nicky LeachandClaude Fable 5.2 ddfbbfff20 fix(runner): recover provider-started turns after a controller restart (#21612)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Core runs Claude Code through Paperclip Runner. Claude can start a
shell command in the background and end its turn. When the command
finishes, Claude Code starts a cycle of its own to continue.
> - The Runner can keep Claude while a background shell is running and
give the cycle of Claude to the controller as a turn that the provider
started. Core can wait for that turn. #21607 lets a caller ask the
transport for it.
> - A controller can restart at any time, for example at a deploy. A
wait can last 10 minutes and a provider-started turn can last longer, so
a restart during one of them is a normal event.
> - Tests with the real `paperclip-runnerd` showed that such a restart
failed the session. The checkpoint that Core had was the checkpoint of
the turn before, and the recovery of the driver refused or mislabelled
the turns that it did not know.
> - This pull request makes that restart safe. It changes no production
run, because no caller asks for provider-started turns before part 3.
> - The benefit is that part 3 can turn the behavior on without a failed
run at each deploy.

## Linked Issues or Issue Description

No public issue exists. The issue is described here.

#21456 turned the behavior on and had grown too large to review. It is
now three stacked pull requests:

1. #21607 (merged): the transport can ask the Runner for
provider-started turns. No caller asks.
2. **This pull request:** the recovery after a controller restart during
a wait or during a provider-started turn.
3. #21456: Core sets the option for native ACPX Claude runs. Only that
part changes what a production run does.

This is part 2. Its base branch is `master`. Refs #19912 (design),
#21456.

**What existing behavior does this improve?**

None in production. It makes a controller restart safe for a run that
asked for provider-started turns.

**Subsystem affected**

Paperclip Runner package: the consumer
(`src/native-session-runtime.ts`), the session backend
(`src/backends/harness-driver-backend.ts`), the driver
(`src/drivers/codex/`) and the transport (`src/live/`). Only for a run
that asked for provider-started turns.

**Current behavior**

- The consumer saves no checkpoint when a wait starts or when a
provider-started turn starts. During a wait and during a
provider-started turn, the checkpoint that Core has is the checkpoint
from the start of the turn before. It names that turn as active.
- A restart from that checkpoint fails: the driver has the old turn as
active, gets the events of a provider-started turn, and stops the
session with `turn_binding_mismatch`.
- The recovery of the driver adopts one turn that it does not know as a
disposition recovery turn, and refuses two or more. With two or more, it
closes the transport, and that stops the Runner and Claude.
- The Runner does not send again an event that the controller
acknowledged. If the start of a provider-started turn was acknowledged
before the restart, the new driver gets the other events of that turn
with no start.
- A turn that ends waiting for a provider-started turn sets the terminal
of the session, as a turn that ends the run does. After a restart, if
the provider-started turn already has its result when recovery
completes, the consumer finds a result and a terminal, settles the run,
and does not read the events of that turn. The start, the items, the
usage event and the terminal of that turn do not reach Core.
- The recovered driver reads notifications from its construction, and
`reconcile()` maps the terminal of the saved turn only after its reads.
If the saved checkpoint is still the checkpoint of the controller turn
and the start of the provider-started turn is already queued, the driver
judges that start too early and stops the session with
`turn_binding_mismatch`.
- A checkpoint that waits can also have a consumed disposition marker (a
recovery turn after an earlier restart ended waiting). The driver
restores that session as closed and reads no notifications, and the
consumer settles the run on the earlier terminal with no result.

**Proposed behavior**

- **Checkpoints.** The consumer saves a checkpoint when a wait starts
and when a provider-started turn starts, with the function that it
already uses for a governed wait. A checkpoint that fails stops the
turn, as for a governed wait.
- **A checkpoint as of the event that Core stored.** The driver gives
each event its sequence when it reads it from the provider, before the
consumer stores it. A snapshot that is taken later can be ahead of Core.
For these two checkpoints, the driver captures its snapshot when it has
handled the notification that made the event (the `turn.completed` that
waits, or the `turn.started` of the provider), with the sequence of that
event. The consumer asks for the snapshot as of the event that it has
just appended. The saved state and cursor are then those of an event
that Core has.
- **Session terminal.** A turn that ends waiting for a provider-started
turn does not set the terminal of the session (`HarnessNativeSession`).
The terminal of the session is the end of the run, and that turn does
not end the run. A checkpoint that is saved during a wait or during a
provider-started turn has no terminal, so a recovered session settles
only from the events that it reads, in order, to the terminal of the
turn that has the result.
- **Driver, a checkpoint that waits.** Recovery keeps the wait. It does
not adopt and does not refuse the turns after the last terminal that it
knows. The Runner sends again, in order, each event that was not
acknowledged, and the driver admits each provider-started turn from that
stream, as it does with no restart.
- **Driver, a checkpoint with an active turn.** `reconcile()` accepts
one turn in progress that comes after the saved active turn, when the
saved turn ended with the wait marker. It refuses each other unexpected
active turn as before, and it refuses this one too when the reconciled
turn settled a result.
- **Driver, a start that is queued before recovery reconciled the saved
turn.** A `turn/started` of the provider that arrives while the session
does not wait for one first waits until `reconcile()` has settled, and
is then judged as before. `reconcile()` judges the live state after its
reads; if the stream already settled the saved turn into a wait, it
accepts exactly one turn in progress after the last terminal turn and
does not adopt it. The driver admits that turn at its start.
- **A wait with a consumed disposition marker.** The driver keeps
reading notifications for a restored session that waits, as it does for
a wait with no restart. It still refuses a second controller-started
turn. The consumer does not take the consumed-marker shortcut for a
recovered snapshot that waits, so the wait is resumed.
- **Transport, the start comes first.** For each driver, the transport
gives the `turn/started` of a provider-started turn before each other
notification and before a tool call of that turn. If it did not give
that start to this driver, it builds it from the `turn.started` event in
its stored events. It does not do this for the turn that the recovered
driver already has as active (`resumeActiveTurnId`). It binds the events
and the tool call of a provider-started turn to that turn, not to the
turn that the Runner reports as active at the time of the recovery read.
- **Transport, which start owns an event.** The stored events can have
gaps: the window removes old events but keeps the latest of each anchor
type, and the controller checkpoint drops streamed deltas. The owner of
an event is the last stored `turn.started` before it, if it is a
provider start, and if the first turn terminal that is stored after that
start is not before the event and is the terminal of the same provider
turn (`providerTurnId`). If the first stored terminal after the start is
the terminal of a different turn, the end of the provider turn is not
known, and the transport builds no start.

**Reason and benefit**

- The checkpoint is the cause. With a true checkpoint, the two states of
a restart are states that recovery can handle: a wait, or an active
turn.
- The Runner already sends again each event that was not acknowledged.
Recovery uses that stream and does not build the turns again from a
read.
- The window removes a terminal only while a later terminal of the same
type is stored. Thus the first stored terminal after a start shows if a
terminal of that turn was removed. A rule that only ignores the gaps is
not safe: the Runner can make a `turn.failed` for a turn that did not
emit its start (`provider_turn_lost_on_restore`).

## What Changed

Production code: 113 lines added, 19 removed.

- `src/native-session-runtime.ts` (15 added, 4 removed): the two
checkpoints in `consumeTurn`, with the sequence of the appended event,
and the resumed wait with a consumed disposition marker.
- `src/drivers/codex/codex-session-state.ts` (24 added, 1 removed),
`codex-session-terminal.ts` (2 added), `codex-session-notifications.ts`
(2 added), `codex-harness-session.ts` (24 added, 7 removed),
`codex-app-server-driver-impl.ts` (4 added, 1 removed): the snapshot at
the event, and the recovery of the driver.
- `src/contracts/harness-driver.ts` and
`src/contracts/native-session-backend.ts` (1 added each): an optional
`boundarySnapshot` on a driver session, and an optional sequence in the
snapshot options. Other drivers do not implement it and are not changed.
- `src/backends/harness-driver-backend.ts` (7 added, 5 removed): the
session terminal, and the snapshot as of a sequence.
- `src/live/runnerd-codex-transport.ts` (15 added, 1 removed) and
`src/live/provider-turn-tool-order.ts` (18 added): the start-first rule
and the owner of an event.
- Tests: `src/live/runnerd-acpx-provider-turn.test.ts` (572 added, 5
removed),
`src/drivers/codex/codex-app-server-driver.provider-turn.test.ts` (348
added), `src/live/runnerd-codex-transport.test.ts` (137 added),
`src/control-plane/durable-prp-control-plane.test.ts` (84 added),
`src/live/provider-turn-tool-order.test.ts` (new, 61),
`src/native-session-runtime.provider-turn.test.ts` (92 added, 6
removed), `src/backends/harness-driver-backend.test.ts` (56 added).
- `runner/crates/runner-core/src/bin/fake-acpx-sidecar.rs` (test binary
only, 123 added, 14 removed): a delay before a provider-started turn, a
goal state at its terminal, a list of provider-started turns for one
session, a gap between them, a turn that stays open until the new
controller reads the snapshot, and a turn that starts after that read.
The modes that existed are not changed, and the fake reads its input on
one thread as before.

## State saved by the previous release

- No new persisted field. The driver session already has
`awaitingProviderTurn` (#21453).
- **More checkpoints:** one when a wait starts and one when a
provider-started turn starts. An ordinary turn saves the same number of
checkpoints as before (4 in the unit test, measured before and after).
- **No terminal in a checkpoint of a wait.** A checkpoint that is saved
during a wait or during a provider-started turn has `terminal: null`.
When a wait ends with no provider-started turn (the limit, a comment of
a person, or the Runner ends the run), the last checkpoint of the run
also has `terminal: null`; before, it had the terminal of the turn that
waited. One reader uses that field with no result: the text of a cleanup
failure (`nativeCheckpointRecordsCompletedTurn`), which then does not
say that the turn completed. In the tests with the real daemon (the
limit, the provider process lost, the sidecar exits), the run still ends
on the path of today (`native_finalization_missing`).
- **A checkpoint of the previous release** has no waiting state.
Recovery takes the path of today.
- **Rollback of the Runner package during a wait:** the previous code
reads the checkpoint, ignores `awaitingProviderTurn`, and takes its
recovery path of today.

## Verification

With nothing from part 3. The Rust checks and the build checks in the
first item were run before the last seven commits; these commits change
no Rust. The other items were run at the head of this branch
(`36d5e5e587`), or at an earlier commit of this branch for a suite whose
files the later commits do not change.

- Before the last seven commits: `pnpm run typecheck:typescript`, `pnpm
run build:typescript` and `node --test
test/acpx-sidecar-contract.test.mjs` (18 passed) in
`packages/paperclip-runner`; `node
scripts/verify-runner-vendor-dependencies.mjs` in `server`; `node --test
scripts/__tests__/runner-release-crate-cache.test.mjs`; `cargo fmt
--check`, `cargo build`, the 17 `acpx_*` suites (241 passed) and the
`acpx` unit tests (102 passed): all passed.
- `npx tsc --noEmit -p tsconfig.json` and `npx tsc --noEmit -p
tsconfig.test.json` in `packages/paperclip-runner`; `pnpm typecheck` in
`server`: all passed.
- `src/live/runnerd-acpx-provider-turn.test.ts`, 4 runs with the
production code of this head, 26 of 26 passed in each. The Core of these
tests follows the production append (`appendNativeSourceEvent`): it
stores an event that is out of order, keeps its contiguous cursor below
a gap, and reports a duplicate or a conflict for an event that it has.
It does not reject a gap in the sequence; production does not. The
restart cases, all with the real `paperclip-runnerd`:
- **From the checkpoint that the real consumer saved.** The first
`executeNativeSession` is fenced and detached as the server does for a
restart, and a second one recovers from the last checkpoint that the
first one saved. (a) Restart during the wait; the provider-started turn
starts after the new controller is attached. (b) Restart while a
provider-started turn is in progress. In each: the test asserts the
shape of that checkpoint, the run settles with the result of the
provider-started turn, each event is appended one time and in order, the
turn has one `turn.started` with `origin: "provider"`, and the session
closes with no error.
- **Without the two checkpoints, each of these cases fails:** the saved
checkpoint is the checkpoint of the turn before, and the second
controller fails with `turn_binding_mismatch` or with a replay conflict.
- **A slow `appendEvent`, with events that arrive behind the stored
event** (3 cases, each run 3 times with the fix and 3 times without it,
with the same result in each run). R7: the append of the
`turn.completed` that waits is slow, and the provider-started turn
starts behind it. With the snapshot at the event, the checkpoint is the
waiting state at the sequence that Core has, and Core gets the
`turn.started` of the turn one time. Without it, the checkpoint names
the provider-started turn as active, the transport builds no start, and
Core never gets that `turn.started`. R8: the first controller answers
the `paperclip_finish` call while the append of the provider
`turn.started` is slow. With the snapshot at the event, the checkpoint
has no result and the run ends with `native_finalization_missing` (see
Risks). Without it, the checkpoint has a result that Core does not have,
and recovery stops with "session cannot start another turn". R6: the
append of the provider `turn.started` is slow and a delta is queued
behind it. With the snapshot at the event, the new controller continues
the sequence that Core has. Without it, the only difference is one
sequence number that Core never gets.
- **The start was acknowledged before the restart** (3 cases: one turn
open across the restart; two turns; a turn that waits for the answer to
its `paperclip_finish` call). The new driver gets the start of each turn
one time before its other events, the finish call is answered exactly
one time, and the session closes with no error.
- **The turn ran with no controller attached** (2 cases, with and with
no result) and **two turns in one outage** (2 cases): the turns arrive
in order after the recovery.
- **A provider-started turn that is active in the checkpoint** gets no
second start, and the next provider-started turn arrives after it.
- **The turn already has its result when recovery completes** (3 cases:
the turn made its `paperclip_finish` call with no controller attached;
the turn waited for the answer to that call at the restart; two turns
across the restart). The test asserts the exact list of events that Core
gets: each provider-started turn has one start, its usage item, its
message item and its terminal, and then `run.result.accepted` and
`run.terminal`. `completeRun` is called one time with the turn that has
the result. Before the change to the session terminal, the second
controller appended only `run.result.accepted` and `run.terminal` in
each of these cases.
- **The wait checkpoint is not saved, then a restart** (R10). The last
checkpoint is the checkpoint of the controller turn, Core has the
terminal of that turn, and the start of the provider-started turn is
queued. The run settles with the result of the provider-started turn,
Core has one `turn.started` for it, and the finish call is answered one
time. Without the wait in the driver, recovery stops with
`turn_binding_mismatch`.
- **An ordinary turn**, with no option. One that waits for the answer to
its finish call at a restart: Core gets its result, its terminal and the
run terminal one time. One whose checkpoint after `startTurn` is ahead
of Core at a restart (R9): the run settles, and Core does not have only
the one event that the first controller did not store. These cases pass
with and without this pull request.
- **No checkpoint with a terminal and no result** is saved by the two
controllers in the cases above.
- `src/live/provider-turn-tool-order.test.ts` and
`src/live/runnerd-codex-transport.test.ts`: 345 passed. The helper tests
cover a stored start with removed events after it, a dropped delta, the
terminal of the turn before and after the event, a terminal of a
different turn after a removed terminal, and a controller start. With no
option, with a different agent or provider, and for a turn that the
controller started, the notifications of the transport are the same as
before this pull request.
- `src/control-plane/durable-prp-control-plane.test.ts`: 230 passed.
Three new tests use the real commit path: a full window of 4,096 events
removes the events after a provider start and the start is found; the
window removes the `turn.failed` of a provider turn after a later
`turn.failed` with no start, and no start is found; a restored
checkpoint that dropped the deltas of the turn, and the start is found.
- `src/drivers/codex` and `src/backends/harness-driver-backend.test.ts`:
491 passed. The driver tests cover a provider start that is queued
before `recoverSession()` is called, the wait state with one turn in
progress at `reconcile()` (and the two cases that it must still refuse),
a restored wait with a consumed disposition marker (the provider turn is
admitted and `startTurn` is refused), the snapshot at the two events
(also after the driver moved on, and for a restart continuation that
ends waiting), one later turn in progress, one completed and a second in
progress, two completed with a result, and the cases that `reconcile()`
must still refuse. The backend tests cover the session terminal and the
snapshot as of a sequence.
- `src/native-session-runtime.provider-turn.test.ts` and
`src/native-session-runtime.test.ts`: 333 passed. Two new cases resume a
restored wait with a consumed disposition marker: the provider-started
turn arrives and settles the run, or the wait ends at its limit and the
run takes the path of today with no new turn.
- `server`: `native-session-executor.test.ts`,
`native-provider-turn-wait.test.ts` and
`native-runner-restart-recovery.integration.test.ts`: 1,743 passed, 21
skipped.
- Mutation checks, each made named tests fail: no checkpoint at the
start of a wait; no checkpoint at the start of a provider-started turn;
the consumer does not pass the sequence (R6, R7 and R8 fail: a hole in
the sequence, no `turn.started` in Core, a different failure); the
backend ignores the sequence; the driver has no snapshot at the event;
no start-first rule; no exclusion of the active turn of the recovered
driver; the turn binding only at the first delivery; the contiguous
sequence required again; no check of the first terminal after the start;
the adoption of later turns put back; no exception in `reconcile()`; no
check after the settlement in `reconcile()`; the terminal of the session
set again by a turn that ends waiting; no wait of the provider start for
`reconcile()`; no exception in `reconcile()` for a session that waits;
the pump deferred for a restored wait; the consumed-marker shortcut
taken for a snapshot that waits.

Not run: the full suite. CI supplies that coverage.

## Risks

- **No production effect.** Each change is behind the waiting state, a
provider `turn.started`, or the option of the transport. No caller sets
the option before part 3.
- **An event that the first controller received but Core did not store
is not sent again after a restart.** This is the same on `master` and is
not changed here. Only the terminal of a turn is built again. If the
lost event is the result of a provider-started turn (the first
controller answered the `paperclip_finish` call and stopped before Core
stored the proposal), the run ends on the path of today for a turn with
no result. R8 shows this. R9 shows the same loss for one event of an
ordinary turn.
- **A second `turn.started` for one provider-started turn can reach
Core.** This occurs if the restart comes after Core stored the start and
before the checkpoint of that start is saved (the time of one checkpoint
write). The last checkpoint then waits, and the transport builds the
start again for the new driver. Seen with the real daemon when the
checkpoint write is held; not in a committed test. The usage accounting
of the server uses the turn id as its key, so there is no second count,
but the second start resets the "restored" mark of that turn. The
transcript does not read `turn.started`.
- **The older checkpoints can also save a cursor that is ahead of Core**
(measured for the checkpoint after `startTurn` of an ordinary turn).
Production accepts the gap in the sequence that follows, so this is not
a failure there. It is on `master` and is not changed here.
- **When the terminal of a provider-started turn was removed from the
stored events,** the transport builds no start for an event of that
turn, and the session stops on that event, as before. This needs a later
terminal of the same type with no start of its own (a turn that was lost
while it started) and a full window.
- **The last checkpoint of a wait that ends with no provider-started
turn has no terminal,** as the section above says. The change is only in
a run that waits, and no run waits before part 3.
- **A wait with a consumed disposition marker has no test with the real
daemon.** The state needs two restarts in one run, and the test helper
does one. Unit tests of the driver and of the consumer cover it.
- **A provider start that waits for `reconcile()`** waits as long as the
reads of `reconcile()` take. Each read ends at the command deadline of
the Runner (30 seconds by default) or when the transport closes.
- **`item.delta` events across a restart are not asserted.** A streamed
delta that the first controller received is not sent again. The
completed items are asserted.
- **The driver keeps a maximum of 8 snapshots at events** and drops each
one when the consumer asks for it or for a later one. If the consumer is
more than 8 such events behind, the checkpoint uses the current
snapshot, as before this change.
- **A second provider-started turn that also ends during the same
outage** is not tested with the real daemon: the fake gives each
terminal the same goal revision, and the Runner then holds the second
terminal until a controller is attached. The end of the reconnect time
of the Runner is not tested here.

## Model Used

- Claude Fable 5.2 (`claude-fable-5-2`) in Claude Code planned the
change and the split, decided the designs, reviewed the diffs, and ran a
part of the verification again.
- Claude Opus 5.5 (`claude-opus-5-5`), as Claude Code subagents with
tool use (shell, file edits, local test runs), wrote the change and the
tests, reproduced the review findings with the real daemon, and verified
this slice alone.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-14 12:51:52 -08:00

389 lines
17 KiB
TypeScript

import type { ProviderFailure } from "./provider-failure.generated.js";
import type { DurableRecoveryIdentity } from "./durable-recovery.js";
import type { NativeRunRuntimeGrant } from "./runtime-context.js";
import type {
NativeRunIdentity,
NativeSessionCapabilities,
NativeUserMessage,
} from "./types.js";
import type {
PrpEvent,
PrpStructuredRunResult,
PrpTerminalState,
} from "../protocol/replay-contract.js";
import type {
DownloadRunnerAttachment,
HarnessRuntimeRequest,
HarnessRuntimeRequestHandoff,
HarnessRuntimeRequestResolution,
HarnessGoalOperation,
HarnessSessionRecoveryResult,
HarnessThreadGoal,
HarnessThreadLineageEntry,
NativeRuntimeContextCapabilities,
PersistedHarnessProviderIdentity,
PersistedHarnessSession,
PersistedHarnessTurnTerminal,
CancelledTurnSettlement,
} from "./harness-driver.js";
export interface NativeSessionBackendDescriptor {
kind: "runner" | "remote" | "mock";
name: string;
version: string;
capabilities: NativeSessionCapabilities;
runtimeContextCapabilities?: NativeRuntimeContextCapabilities;
}
export interface OpenNativeSessionInput {
identity: NativeRunIdentity;
workingDirectory?: string;
/**
* When present, aborts provider bootstrap if the caller's recovery deadline
* expires. Backends own cleanup for work that has not returned a session yet.
*/
signal?: AbortSignal;
}
export interface NativeSessionRecoveryOptions {
normalizeReplayPayload?(payload: PrpEvent["payload"]): PrpEvent["payload"];
/** Abort provider recovery and release any not-yet-returned provider state. */
signal: AbortSignal;
}
export interface PersistedNativeSession {
backendKind: NativeSessionBackendDescriptor["kind"];
driverKind?: string | null;
sessionId: string;
identity: NativeRunIdentity;
providerSessionId?: string | null;
/** Tagged provider-owned identity required for safe driver recovery. */
providerIdentity?: PersistedHarnessProviderIdentity;
workingDirectory?: string;
codexUsageBaseline?: PersistedHarnessSession["codexUsageBaseline"];
providerRecoveryPolicy?:
| "same_session_only"
| "allow_replacement_after_governed_wait"
| "allow_replacement_after_resume_failure";
cursor?: string | null;
semanticResult?: PrpStructuredRunResult | null;
terminal?: PrpTerminalState | null;
activeTurnId?: string | null;
terminalTurns?: PersistedHarnessTurnTerminal[];
/** Control-plane disposition bound to the exact committed tool event. It is
* independent of the interaction's later answer and proves no provider terminal. */
governedWait?: { sourceEvent: PrpEvent; result: PrpStructuredRunResult; settlement?: CancelledTurnSettlement };
/** At-most-once marker for resultless disposition repair or restart continuation. */
dispositionOnlyRecoveryConsumed?: boolean;
dispositionOnlyRecoveryTurnId?: string | null;
pendingRuntimeRequests?: HarnessRuntimeRequest[];
goal?: HarnessThreadGoal | null;
lineage?: HarnessThreadLineageEntry[];
awaitingProviderTurn?: boolean;
}
export interface NativeSessionRecoveryResult {
recovered: boolean;
session?: NativeSession;
reason?: string;
failureClass?: HarnessSessionRecoveryResult["failureClass"];
resumeStateUnavailable?: HarnessSessionRecoveryResult["resumeStateUnavailable"];
runnerExitConfirmed?: HarnessSessionRecoveryResult["runnerExitConfirmed"];
}
/** Runner-owned cause: the process was restored, but its active turn was lost. */
export const NATIVE_RESTART_INTERRUPTION_CODE = "provider_turn_lost_on_restore";
export function isNativeRestartInterruption(error: unknown): boolean {
if (!error || typeof error !== "object" || Array.isArray(error)) return false;
const failure = error as Record<string, unknown>;
return failure.code === NATIVE_RESTART_INTERRUPTION_CODE && failure.recoverable === true;
}
const RESTART_CONTINUATION_DRIVER_KINDS: ReadonlySet<string> = new Set(["codex_app_server", "acpx_runtime", "opencode_server"]);
/** The terminal fingerprint survives a crash between interruption and continuation. */
export function nativeRestartInterruptedTurnId(snapshot: Pick<PersistedNativeSession,
"driverKind" | "activeTurnId" | "semanticResult" | "terminalTurns" | "dispositionOnlyRecoveryConsumed" | "pendingRuntimeRequests" | "goal"
>): string | null {
// Runnerd records this cause for Codex app-server and ACPX sessions after
// proving the old provider lifetime ended and restoring the conversation.
// A lost continuation re-arms the driver's marker before it is checkpointed,
// so a consumed marker here still means the allowance is used.
if (!RESTART_CONTINUATION_DRIVER_KINDS.has(snapshot.driverKind ?? "") || snapshot.activeTurnId != null ||
snapshot.semanticResult != null || snapshot.dispositionOnlyRecoveryConsumed ||
snapshot.goal != null || snapshot.pendingRuntimeRequests?.length) return null;
const terminal = Array.isArray(snapshot.terminalTurns) ? snapshot.terminalTurns.at(-1) : null;
if (!terminal || typeof terminal.fingerprint !== "string" || !terminal.turnId) return null;
try {
const fingerprint = JSON.parse(terminal.fingerprint);
return fingerprint?.terminalState === "failed" && fingerprint.result === null &&
isNativeRestartInterruption(fingerprint.error) ? terminal.turnId : null;
} catch { return null; }
}
export function nativeRestartContinuationInFlight(snapshot: Pick<PersistedNativeSession,
"activeTurnId" | "terminalTurns"
>): boolean {
const activeTurnId = snapshot.activeTurnId;
if (typeof activeTurnId !== "string" || !activeTurnId) return false;
const last = Array.isArray(snapshot.terminalTurns) ? snapshot.terminalTurns.at(-1) : null;
if (!last || typeof last.fingerprint !== "string" || !last.turnId || last.turnId === activeTurnId) return false;
try {
const fingerprint = JSON.parse(last.fingerprint);
return fingerprint?.terminalState === "failed" && fingerprint.result === null &&
isNativeRestartInterruption(fingerprint.error);
} catch { return false; }
}
/**
* Cancellation is a synchronous authority transition followed by passive
* provider cleanup. Once `cancel` returns, the provider session must no longer
* be able to publish accepted output or acquire new mutation authority for the
* cancelled turn. Cleanup may stop processes or transports, but it must not
* perform durable control-plane mutations.
*/
export interface NativeSessionCancellation {
cleanup: Promise<void>;
terminalDrainTimeoutMs?: number;
}
export interface NativeSessionSnapshotOptions {
/** Stop provider snapshot work that outlives the execution deadline. */
signal: AbortSignal;
sourceSeq?: number;
}
/** A dispatched operation may have taken effect, but has no proven result. */
export class SemanticToolOutcomeUnknownError extends Error {
readonly code = "semantic_tool_outcome_unknown";
constructor(message: string, options?: ErrorOptions) {
super(message, options);
this.name = "SemanticToolOutcomeUnknownError";
}
}
export function isSemanticToolOutcomeUnknownError(error: unknown): error is SemanticToolOutcomeUnknownError {
// Match across the server's vendored and source-mode runtime boundaries.
return error instanceof Error && "code" in error && error.code === "semantic_tool_outcome_unknown";
}
/** The exact close owner has torn down its controller without proving suspension. */
export class NativeSessionCloseUnrecoverableError extends Error {
readonly code = "native_session_close_unrecoverable";
constructor(
readonly settlement?: Record<string, unknown>,
/** Exact durable results exist for every admitted Core tool callback. */
readonly semanticToolsSettled = false,
) {
super(
"provider_transport_failed: runner did not durably suspend before checkpoint",
);
this.name = "NativeSessionCloseUnrecoverableError";
}
}
/** The provider recovery deadline ended a recovery that was still waiting on its Runner. */
export class NativeProviderRecoveryDeadlineError extends Error {
readonly code = "native_provider_recovery_deadline";
constructor(readonly timeoutMs: number) {
super(`native session provider recovery timed out after ${timeoutMs}ms`);
this.name = "NativeProviderRecoveryDeadlineError";
}
}
export function isNativeProviderRecoveryDeadlineError(error: unknown): error is NativeProviderRecoveryDeadlineError {
return error instanceof Error && "code" in error && error.code === "native_provider_recovery_deadline";
}
/** An authenticated, exactly bound runner event failed permanent integrity checks. */
export class NativeSessionProtocolIntegrityError extends Error {
readonly code = "native_event_replay_conflict";
readonly recovery = "operator_required";
constructor(
readonly reason:
| "semantic_input_digest_mismatch"
| "source_event_replay_conflict"
| "runner_event_commit_stalled",
readonly detail?: string,
) {
super(
reason === "semantic_input_digest_mismatch"
? "native_event_replay_conflict: authenticated runner semantic input failed integrity validation; automatic recovery is stopped."
: reason === "runner_event_commit_stalled"
? `native_event_replay_conflict: runner_event_commit_stalled: runner events kept failing to commit without progress (last cause: ${detail ?? "unknown"}); automatic recovery is stopped.`
: "native_event_replay_conflict: authenticated runner event conflicts with committed history; automatic recovery is stopped.",
);
this.name = "NativeSessionProtocolIntegrityError";
}
}
/** Admission is blocked by a retained owner that has no safe automatic close retry. */
export class NativeSessionCleanupQuarantinedError extends Error {
readonly code = "native_session_cleanup_quarantined";
readonly recovery = "operator_required";
constructor() {
super(
"native_session_cleanup_quarantined: the previous session is still shutting down; Paperclip finishes the cleanup automatically and the saved work is kept.",
);
this.name = "NativeSessionCleanupQuarantinedError";
}
}
export interface NativeSession {
identity(): NativeRunIdentity;
capabilities(): Promise<NativeSessionCapabilities>;
downloadAttachment?: DownloadRunnerAttachment;
/** completionContract is the attaching run's own contract; a retained session must not keep the prior run's. */
attachRun?(input: { identity: NativeRunIdentity; currentRunGrant?: NativeRunRuntimeGrant; completionContract?: { revision: string; criterionIds: readonly string[] } }): Promise<void>;
beginRunAttachment?(input: { identity: NativeRunIdentity }): boolean;
/** Return the confirmed released source, or false when active use was not released. */
release?(): Promise<DurableRecoveryIdentity | false>;
/** Relinquish controller authority without suspending provider execution. */
detachControllerForRestart?(): Promise<void>;
events(input?: { afterCursor?: string | null }): AsyncIterable<PrpEvent>;
startTurn(input: {
message: NativeUserMessage;
/** Set by orchestration only after successful provider-session recovery. */
continuation?: true;
requestedCollaborationMode?: "default" | "plan";
/** OpenCode/OpenRouter only. Applies to this turn, never subsequent turns. */
reasoningMode?: "default" | "disabled";
/**
* Run the provider's own context compaction as this turn instead of
* submitting `message`. Only for a resumed session with prior context.
*/
compact?: true;
/** Last context occupancy Paperclip recorded before a compaction turn. */
contextTokensBefore?: number;
}): Promise<{
turnId: string;
effectiveCollaborationMode?: "default" | "plan";
/**
* This restart continuation borrowed the driver's one-shot disposition
* marker. If it completes without a result the driver returns the marker,
* and orchestration may send one disposition request in the same attempt.
*/
borrowedDispositionMarker?: true;
}>;
steer?(input: {
mode?: "steer" | "follow_up";
turnId: string;
message: NativeUserMessage;
correlationId?: string;
}): Promise<void>;
interrupt?(input: { turnId?: string; reason?: string }): Promise<void>;
/** Revoke publication synchronously while the control plane journals a wait.
* Does not interrupt the provider; cancel owns the subsequent passive cleanup. */
revokeTurnPublication?(): void;
/** Commit cancellation synchronously; the returned promise owns cleanup only. */
cancel?(input: {
reason: string;
signal: AbortSignal;
failureCleanup?: boolean;
}): NativeSessionCancellation;
settleCancelledTurn?(input: { turnId: string; reason: string }): Promise<CancelledTurnSettlement | null>;
resolveRuntimeRequest?(input: {
commandId?: string;
requestId: string;
turnId: string;
resolution: HarnessRuntimeRequestResolution;
}): Promise<void>;
handoffRuntimeRequest?(input: {
requestId: string;
turnId: string;
reason: "durable_handoff";
/**
* Revokes durable mutation authority when event consumption fails. The
* method must commit synchronously before returning; its returned promise
* owns provider cleanup only and must not mutate durable request state.
*/
signal: AbortSignal;
}): HarnessRuntimeRequestHandoff;
goal?(input: HarnessGoalOperation): Promise<HarnessThreadGoal | null>;
result(): Promise<{
result: PrpStructuredRunResult;
terminal: PrpTerminalState;
turnId: string | null;
} | null>;
usage?(): Promise<Record<string, unknown> | null>;
snapshot(
options?: NativeSessionSnapshotOptions,
): Promise<PersistedNativeSession>;
/**
* Idempotently stop provider work and release every pending `events().next()`
* before this promise resolves. Implementations must settle every promise
* previously returned by the session (including interrupt, cancel, handoff,
* and iterator teardown). The runtime bounds its wait for a broken provider,
* revokes that session's mutation authority, removes it from reuse, and keeps
* observing late cleanup so a contract violation cannot defeat a run timeout
* or become an unhandled rejection.
*/
close(input: { reason: string }): Promise<void>;
}
/** Normalized control-plane boundary shared by runner and hosted backends. */
export interface NativeSessionBackend {
/** Existing task rules at user-message priority, for prepared native envelopes. */
readonly preparedTaskConstraints?: readonly string[];
descriptor(): Promise<NativeSessionBackendDescriptor>;
openSession(input: OpenNativeSessionInput): Promise<NativeSession>;
/** Open a fresh provider session after an explicitly governed continuity break. */
openReplacementSession?(
input: OpenNativeSessionInput,
previous: PersistedNativeSession,
): Promise<NativeSession>;
recoverSession?(
snapshot: PersistedNativeSession,
options: NativeSessionRecoveryOptions,
): Promise<NativeSessionRecoveryResult>;
}
/** Same-session recovery is forbidden here, and the runner proved that the
* saved provider session cannot be restored by its build. Retrying the same
* run cannot succeed. */
export class NativeProviderStateIncompatibleError extends Error {
readonly code = "native_provider_state_incompatible";
constructor(reason: string) {
super(`native_session_recovery_failed: ${reason}`);
this.name = "NativeProviderStateIncompatibleError";
}
}
/** The saved provider session still owns a side-effecting call without a
* recorded result. A replacement session could repeat or lose that action, so
* the run stops for an operator and the saved state stays intact. */
export class NativeProviderSideEffectPendingError extends Error {
readonly code = "native_provider_side_effect_pending";
constructor(reason: string) {
super(`native_session_recovery_failed: ${reason}`);
this.name = "NativeProviderSideEffectPendingError";
}
}
export class NativeGovernedWaitSettlementPendingError extends Error {
readonly code = "native_governed_wait_settlement_pending";
constructor(options?: ErrorOptions) {
super("The waiting state is saved; confirming shutdown of the previous execution is still pending.", options);
this.name = "NativeGovernedWaitSettlementPendingError";
}
}
/** A provider failed terminal is not a missing completion proposal. */
export class NativeProviderTerminalFailure extends Error {
readonly code = "native_provider_terminal_failed";
declare readonly providerFailure?: ProviderFailure;
constructor(readonly providerCode: string, readonly recoverable: boolean, message = "Provider session ended with a failed terminal",
providerFailure?: ProviderFailure | null) {
super(message);
this.name = "NativeProviderTerminalFailure";
if (providerFailure) Object.defineProperty(this, "providerFailure", { value: providerFailure, enumerable: false });
}
}