findCutPoint defaulted cutIndex to the earliest valid cut (cutPoints[0],
keep everything) and only moved it forward to a cut point at or after the
backward token cursor. When the final entry is a toolResult whose estimate
alone meets keepRecentTokens, the cursor stops at that trailing toolResult
index, no valid cut point sits at or after it (toolResult entries are not
valid cut points), and the default stuck at keep-everything. Compaction then
summarized zero messages, so preflight and overflow compaction silently
no-op and the session loops on a context it cannot shrink.
Default cutIndex to the most recent valid cut before the forward search.
When a cut point exists at or after the cursor the search still finds it and
behavior is unchanged; only the trailing-tool-result case now keeps the
recent tail and summarizes the prefix.
Persistent ACP threads died on the second turn for Kiro: when the backend
can no longer resume a stale session, acpx raises a SessionResumeRequiredError
whose reason text varies by backend ("Resource not found" for Claude,
"Internal error" / RequestError -32603 for Kiro). The recovery gate matched
the human reason text and required "resource not found", so Kiro's "Internal
error" never triggered the fresh-session retry and the thread produced no
reply (ACP_TURN_FAILED).
Recover by acpx's structured detail code instead of the reason text: acpx
tags every such failure with detailCode "SESSION_RESUME_REQUIRED"
(retryable), independent of wording. The two AcpRuntimeError construction
seams were discarding detailCode, so preserve it on AcpRuntimeError and match
it across the error and its cause chain. This fixes every backend's
resume-required failure and is more precise than the reason regex — a generic
"Internal error" without the code is still surfaced rather than silently
retried.
Fixes#87830. Reported by @chouzz.
normalizeAgentEventType checked the `phase:"end" || status==="completed"`
branch before the `failed/blocked` branch, but terminal tool/item events are
emitted with phase:"end" AND the real status, so failed and blocked tools were
normalized to tool.call.completed and the tool.call.failed branch was dead for
the item stream. SDK consumers filtering on tool.call.failed never saw tool
failures (they looked like successes). Reorder so failed/blocked is classified
before end/completed.
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
estimateTokens charged 4800 chars per image in the toolResult branch but
counted only text in the user branch, so image blocks in recent user turns
scored zero. findCutPoint never reached keepRecentTokens and left the cut at
the earliest point, so image-heavy sessions compacted to a no-op and looped on
context overflow. Fold the per-image accounting into one shared helper used by
both branches.
SDK list helpers now send an empty params object when filters are omitted while preserving explicit invalid params for Gateway validation.\n\nVerification:\n- git diff --check origin/main...HEAD\n- node --check packages/sdk/src/client.ts\n- codex review --base origin/main\n- GitHub Actions CI release gate 27855603923 succeeded on 353f13c0d1
Distinguish validated gateway reachability from pre-open and TLS-validation failures, and sanitize close diagnostics before terminal output.
Fixes#79099.
Co-authored-by: xialonglee <li.xialong@xydigit.com>
Summary:
- The PR widens the virtual Clack output columns for wrapped terminal notes and adds a rendered-output regression test for copy-sensitive session-lock paths.
- PR surface: Source +8, Tests +28. Total +36 across 2 files.
- Reproducibility: yes. Current source routes session lock paths through `note()`, and the pinned Clack note renderer hard-wraps final content from `getColumns(output) - 6` after OpenClaw's first wrapping pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test(note): add rendered-output regression test for copy-sensitive to…
Validation:
- ClawSweeper review passed for head b17a4ff571.
- Required merge gates passed before the squash merge.
Prepared head SHA: b17a4ff571
Review: https://github.com/openclaw/openclaw/pull/94746#issuecomment-4747714518
Co-authored-by: Dirk <0668000837@xydigit.com>
Yuval Dinodia