Add Railway deployment support with Gemini API configuration#724
Closed
seesawrubs wants to merge 1 commit into
Closed
Add Railway deployment support with Gemini API configuration#724seesawrubs wants to merge 1 commit into
seesawrubs wants to merge 1 commit into
Conversation
heatherstew44-maker
pushed a commit
to heatherstew44-maker/openclaw
that referenced
this pull request
Mar 8, 2026
This was referenced Apr 11, 2026
dzianisv
pushed a commit
to dzianisv/openclaw
that referenced
this pull request
Apr 11, 2026
…thinking-only retry, startup replay Bug 1 (openclaw#724): Timeout compaction gate now uses preflight estimated prompt tokens when LLM reports no usage, and treats idle-timeout as full context pressure to trigger compaction instead of silently stalling. Bug 2 (openclaw#724): Preemptive compaction upgrades truncation-only to compact_then_truncate when session exceeds 200 messages, preventing structural overhead from overwhelming the model. Bug 3 (openclaw#64570): Thinking-only LLM responses (stopReason=stop with no visible text and no tool calls) are now detected as incomplete turns and retried with a user-visible warning, instead of being silently dropped. Bug 4 (openclaw#64571): Added startup stuck-session replay — on gateway restart, scans transcripts for sessions with unanswered user turns or empty assistant tails, re-verifies the transcript tail before sending (race guard), and replays up to 10 newest candidates via sessions.send with a 30s per-send timeout to prevent startup hang. 45 tests passing (11 incomplete-turn, 18 timeout-compaction, 9 preemptive-compaction, 7 startup-replay). Co-authored-by: Copilot <[email protected]>
dzianisv
pushed a commit
to dzianisv/openclaw
that referenced
this pull request
Apr 18, 2026
…thinking-only retry, startup replay Bug 1 (openclaw#724): Timeout compaction gate now uses preflight estimated prompt tokens when LLM reports no usage, and treats idle-timeout as full context pressure to trigger compaction instead of silently stalling. Bug 2 (openclaw#724): Preemptive compaction upgrades truncation-only to compact_then_truncate when session exceeds 200 messages, preventing structural overhead from overwhelming the model. Bug 3 (openclaw#64570): Thinking-only LLM responses (stopReason=stop with no visible text and no tool calls) are now detected as incomplete turns and retried with a user-visible warning, instead of being silently dropped. Bug 4 (openclaw#64571): Added startup stuck-session replay — on gateway restart, scans transcripts for sessions with unanswered user turns or empty assistant tails, re-verifies the transcript tail before sending (race guard), and replays up to 10 newest candidates via sessions.send with a 30s per-send timeout to prevent startup hang. 45 tests passing (11 incomplete-turn, 18 timeout-compaction, 9 preemptive-compaction, 7 startup-replay). Co-authored-by: Copilot <[email protected]>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.