Skip to content

Commit cd1cae5

Browse files
fuller-stack-devvincentkocclawsweeper[bot]Takhoffman
authored
fix(auto-reply): preserve sessions after compaction failures (#70479)
Summary: - The PR removes the auto-reply compaction-failure session reset hook, adds preserved-session recovery guidance for overflow/compaction failure paths, and updates focused tests, docs, and the changelog. - Reproducibility: yes. at source level with high confidence. Current main routes both embedded overflow paylo ... resetSessionAfterCompactionFailure, and the PR body includes before/after terminal proof of those branches. Automerge notes: - PR branch already contained follow-up commit before automerge: fix(auto-reply): drop dead compaction reset hook - PR branch already contained follow-up commit before automerge: fix(auto-reply): preserve sessions after compaction failures Validation: - ClawSweeper review passed for head 193d3c0. - Required merge gates passed before the squash merge. Prepared head SHA: 193d3c0 Review: #70479 (comment) Co-authored-by: FullerStackDev <263060202+fuller-stack-dev@users.noreply.github.com> Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
1 parent 93c613c commit cd1cae5

5 files changed

Lines changed: 147 additions & 91 deletions

File tree

‎CHANGELOG.md‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4929,7 +4929,8 @@ Docs: https://docs.openclaw.ai
49294929
- Providers/SDK retry: cap long `Retry-After` sleeps in Stainless-based Anthropic/OpenAI model SDKs so 60s+ retry windows surface immediately for OpenClaw failover instead of blocking the run. (#68474) Thanks @jetd1.
49304930
- Agents/TTS: preserve spoken text in TTS tool results while defusing reply directives in transcript content, so future turns remember voice replies without treating spoken `MEDIA:` or voice tags as delivery metadata. (#68869) Thanks @zqchris.
49314931
- Providers/OpenAI: harden Voice Call realtime transcription against OpenAI Realtime session-update drift, forward language and prompt hints, and add live coverage for realtime STT.
4932-
- Agents/Pi embedded runs: suppress the "⚠️ Agent couldn't generate a response" warning when the assistant already delivered user-visible content through a messaging tool and the turn ended cleanly (`stopReason=stop`). Real failure modes (tool errors, provider `stopReason=error`, interrupted tool use) still surface the existing "verify before retrying" warning. Fixes #70396. (#70425) Thanks @neeravmakwana.
4932+
- Agents/Pi embedded runs: suppress the "⚠️ Agent couldn't generate a response" warning when the assistant already delivered user-visible content through a messaging tool and the turn ended cleanly (`stopReason=stop`). Real failure modes (tool errors, provider `stopReason=error`, interrupted tool use) still surface the existing "verify before retrying" warning. Fixes #70396. (#70425) Thanks @neeravmakwana.
4933+
- Auto-reply/WebChat: preserve the active session mapping when context-overflow recovery or auto-compaction fails, and return retry, `/compact`, and `/new` guidance instead of silently rotating to a fresh session. Fixes #70472. (#70479) Thanks @fuller-stack-dev.
49334934
- Gateway/Linux: wrap gateway-managed supervisor, PTY, MCP stdio, and browser child processes in a tiny `/bin/sh` shim that raises the child's own `oom_score_adj` on Linux, so under cgroup memory pressure the kernel prefers transient workers over the long-lived gateway. Opt out with `OPENCLAW_CHILD_OOM_SCORE_ADJ=0`. Fixes #70404. (#70419) Thanks @neeravmakwana.
49344935
- Providers/Moonshot: stop strict-sanitizing Kimi's native tool_call IDs (shaped like `functions.<name>:<index>`) on the OpenAI-compatible transport, so multi-turn agentic flows through Kimi K2.6 no longer break after 2-3 tool-calling rounds when the serving layer fails to match mangled IDs against the original tool definitions. Adds a `sanitizeToolCallIds` opt-out to the shared `openai-compatible` replay family helper and wires Moonshot to it. Fixes #62319. (#70030) Thanks @LeoDu0314.
49354936
- Dependencies/security: override transitive `uuid` to `14.0.0`, clearing the runtime advisory across dependencies.

‎docs/reference/session-management-compaction.md‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -274,6 +274,11 @@ In the embedded Pi agent, auto-compaction triggers in two cases:
274274
number of tokens`, `input token count exceeds the maximum number of input
275275
tokens`, `input is too long for the model`, `ollama error: context length
276276
exceeded`, and similar provider-shaped variants) → compact → retry.
277+
If overflow recovery still fails, OpenClaw surfaces explicit guidance to the
278+
user and preserves the current session mapping instead of silently rotating
279+
the session key to a fresh session id. The next step is operator-controlled:
280+
retry the message, run `/compact`, or run `/new` when a fresh session is
281+
preferred.
277282
2. **Threshold maintenance**: after a successful turn, when:
278283

279284
`contextTokens > contextWindow - reserveTokens`

0 commit comments

Comments
 (0)