* fix(gateway): stop terminal PTYs on session archive
Bind agent terminals to the durable session incarnation, drain exact ownership during archive, and terminate every job-control process group in the PTY session.\n\nCloses #125769
* test(gateway): cover terminal cleanup on archive
* test(gateway): align terminal outcome assertions
* test(gateway): preserve session exports in invoke test
* fix(gateway): await terminal exit before archive
* test(codex): consolidate supervised instruction coverage
Move the duplicated two-attempt regression into the canonical thread lifecycle test so the exact two-worker extension shard stays bounded on low-core CI.\n\nRelated: #125783
* fix(agents): report interrupted tool outcomes honestly
Prevent restart recovery from claiming that an interrupted tool call completed when no successful matching result was recorded.
* fix(agents): keep ambiguous recovery restart-safe
Classify failed replay-unsafe tool results at the shared restart-recovery owner so interrupted side effects remain unavailable until their external state is verified.
* fix(agents): distinguish missing tool outcomes
Carry the existing missing_tool_result fact into projected Codex transcripts so restart recovery restricts only genuinely unknown outcomes, while confirmed failures remain retryable.
formatFileOperations in agent-core joined every accumulated read/
modified path unbounded — and the lists ratchet: each compaction merges
the prior summary's file operations into the next accumulation, so a
long default-mode session (or branch summarization, which runs in every
mode) re-emitted an ever-growing path dump into each model-visible
summary with no cap, violating the context-budget invariant.
The safeguard extension already solved this with a bounded formatter
(900 chars/list, 2000 chars/section, '...and N more' overflow). Move
that implementation into the agent-core owner so compact(),
generateBranchSummary, and the safeguard all share one bounded
formatter, and delete the safeguard-local duplicate plus its constant
copies.
* refactor: consolidate coercion ownership
Centralize four canonical coercion helpers, migrate exact core and plugin duplicates through narrow Plugin SDK facades, and enforce declaration and plugin-normalization ownership boundaries.
The sweep adds eight focused SDK exports while deleting more production and tooling code than it adds. User-visible behavior is unchanged except for safer equivalent object and UI parsing at existing boundaries.
* fix: guard integer option ownership
Register resolveIntegerOption with the canonical function owner and extend the declaration-guard fixture so future local duplicates fail validation.
* fix: keep integer helpers on numeric facade
Remove the unshipped duplicate string-coerce exports and route every affected plugin consumer through the existing number-runtime contract.
* fix: point numeric coercion to number runtime
Make boundary and declaration diagnostics recommend the canonical numeric facade, with failing-before coverage for both guidance paths.
* fix(agents): exclude private shell output from context compaction
## What Problem This Solves
Shell executions explicitly excluded from model context could still contribute their private output to session replay, token estimates, compaction boundaries, or branch summaries.
## Why This Change Was Made
The session projection owner now omits context-excluded shell messages, while compaction assigns those messages zero tokens and prevents private persisted entries from becoming retained-history cut boundaries.
## User Impact
Private shell output remains durably recorded for its intended owner without leaking into model-visible conversation context or wasting compaction budget; legitimate retained context remains intact.
## Context
Actual production code executed in an isolated VM reduced more than 20,000 characters of private output to zero model-visible characters while preserving eligible context. New owner and sibling regressions cover replay, compaction, branch summaries, and token accounting. Existing oxfmt formatting and scoped whitespace checks passed.
* test(agents): cover private Codex history projection
* fix(agents): pair reset tool results within retained session history
## What Problem This Solves
Session resets selected tool-call pairs from history preceding the retained-session boundary, allowing an excluded call to incorrectly claim a retained tool result and leaving replayed conversation history inconsistent.
## Why This Change Was Made
The session-context owner now identifies the retained range before pairing reset tool calls and results. Both reset and compaction flows reuse the same canonical bounded history slice, removing duplicate scan and membership logic.
## User Impact
Reset agent sessions retain only legitimate in-window tool exchanges, repeated resets remain consistent, and cloud-worker replay receives coherent session context without resurrecting discarded calls.
## Context
Actual production-source execution reproduced the previous failure and passed after the fix across valid in-window pairs, repeated resets, and cloud-worker boundaries. Focused session-context and worker-launcher regressions cover the owner and downstream consumer. Existing oxfmt formatting and scoped whitespace checks passed; production code decreases by five lines.
* test(gateway): cover reused reset tool call ids
* fix(llm-core): settle result() when a stream ends without a terminal event
EventStream.end() with no argument and no prior terminal event left the final
result promise pending forever; any consumer awaiting result() dead-ended
silently for the whole run budget (the agent loop's fall-through in
streamAssistantResponse awaits exactly that promise). All in-repo pumps push
terminals or pass end(result), so this only fires on producer contract
violations — which previously hung and now reject loudly with a named error.
A pre-attached catch keeps iterate-only consumers free of unhandled
rejections. Also dedupe the agent loop's two identical final-message blocks
into one finalizeAssistantMessage helper (net-negative production delta).
Follow-up from #120426's turn-liveness investigation.
* fix(llm-core): void the intentional rejection pre-catch
ClawSweeper P1: the pre-attached no-op catch returns a Promise that would
float under typescript/no-floating-promises.
* fix(agent): apply steering before unstarted tools
Restore steering checkpoints before sequential tool launches and before parallel batch launch. Preserve paired synthetic tool results, async callback compatibility, and Code Mode outcome handling.
* fix(agent): delay tool loop admission commits
Commit loop-detection history only for calls crossing the final launch checkpoint. Release steering-skipped markers, add repeated-steer coverage, and align remaining steering contract text.
* fix(agent): keep tool admission lifecycle internal
Attach delayed admission callbacks through the private internal-hooks seam so steering history remains correct without widening the public Agent Core or Plugin SDK contract.
* fix(agent): preserve steering API contracts
Keep public steering callbacks Promise-based and protocol error kinds unchanged. Use private synchronous draining and structured skip details to retain launch-boundary behavior without API or generated protocol drift.
* test(gateway): use canonical steering fixture config
Use keyed agent entries in the real gateway steering harness so current main does not migrate the fixture during startup.
* fix(agent): remove unused lifecycle re-export
* fix(agent): gate tool launch after wrapper preflight
Split OpenClaw tool execution into private prepare and launch phases so steering is checked after policy, approval, validation, and reconciliation but before the original side effect. Preserve final arguments, voice grants, loop admission, context wrappers, and direct tool execution.
* fix(agent): preserve steering callback receiver
Invoke public steering callbacks with their AgentLoopConfig receiver and cover method-style implementations that read config-owned queue state.
* [AI] fix(agents): emit aborted tool results for skipped tool calls on mid-turn abort
When an abort fires mid-batch in executeToolCalls (after the assistant
message with tool_use is committed but before all tool_results are
written), the sequential and parallel dispatch loops break out and skip
the remaining tool calls. The committed assistant turn retains N tool_use
blocks but only M < N tool_results land in context.messages, leaving
orphaned tool_use that corrupts retries/continuation and triggers provider
400 errors on providers that do not synthesize missing results
(allowSyntheticToolResults=false, e.g. openai-completions/DeepSeek).
Emit aborted tool results (createErrorToolResult("Operation aborted")) for
the skipped tail in both executeToolCallsSequential and
executeToolCallsParallel so every tool_use keeps a paired tool_result.
This complements the existing write-side guard (which only covers
synthetic-enabled providers) and the persisted replay repair.
The aborted tail outcomes are routed through finalizeToolCallOutcome (via
a shared finalizeAbortedToolCall helper) so config.afterToolOutcome hooks
(audit, redaction, metadata, error-normalization) observe these skipped
calls just like every immediate or executed outcome, instead of bypassing
the outcome contract. Regression tests assert afterToolOutcome fires for
every skipped call in both dispatch modes.
Fixes#116379
Co-Authored-By: Maas <noreply@anthropic.com>
* [AI] fix(agents): emit tool_execution_start before aborted end for skipped calls
The abort-tail backfill added in #116379 emits tool_execution_end (and a
paired tool_result) for tool calls the dispatch loop never reached, but it
skipped the matching tool_execution_start. Channel/client subscribers that
pair start→end events received an end for an unknown tool-call id during
abort recovery.
Emit tool_execution_start for each skipped call before its aborted end/result,
mirroring the start event every dispatched (including immediate non-executed)
call already emits. Covers both sequential and parallel dispatch, with
regression assertions that every skipped call has a start before its end and
that start/end counts stay paired.
Co-Authored-By: Maas <noreply@anthropic.com>
* fix(agents): complete aborted tool tails safely
Fixes#116379
---------
Co-authored-by: Maas <noreply@anthropic.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* test(process): reproduce Windows taskkill process-tree leak
* fix(process): stop leaked Windows child process trees
Escalate only when Windows taskkill reports that graceful process-tree termination failed. Preserve awaited taskkill completion, grace-period fallback, one-shot signaling, and PID-reuse protection.
Closes#110789
Supersedes #112202
Co-authored-by: Mohammed Alkindi <alkndymhmd692@gmail.com>
---------
Co-authored-by: Mohammed Alkindi <alkndymhmd692@gmail.com>
* feat(anthropic): add Claude Opus 5 model support
Wire claude-opus-5 through the Claude 5 contract seams: adaptive-by-default
thinking with the full low..max effort range, default-sampling and prefill
stripping, streaming refusal contract, model-bound thinking replay, and 1M/128k
catalog metadata across anthropic, claude-cli, Vertex, Bedrock, and Mantle.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(anthropic-vertex): normalize explicit Vertex Opus 5 model rows
Extend normalizeAnthropicVertexResolvedModel so user-configured Vertex Opus 5
rows regain reasoning, image input, 1M/128k limits, and the native thinking
map; update the live-model priority expectation and regenerate docs_map.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Peter Steinberger