mirror of
https://github.com/openclaw/openclaw.git
synced 2026-08-07 16:05:52 +00:00
b39e1cf66f
Code mode previously suspended to the model with a waiting result for every
awaited tools.search/describe/call, forcing one wait tool turn per await
(turns = tool calls + 1). Bridge calls now resolve inline within the exec
deadline and resume the QuickJS snapshot host-side, matching the namespace
auto-drain path. Restart-safe runs keep their existing no-drain semantics.
Live proof across OpenAI/Anthropic/Google: ~45% fewer turns and ~45% fewer
input tokens at equal success rate.
Also landed with the same contract:
- one shared wall-clock deadline per exec/wait call (initial worker, inline
drain rounds, and resumed guest interrupt budget all share it)
- park the snapshot instead of resuming when the remaining budget could not
survive VM restore, so near-deadline settles stay recoverable
- abort now terminates the guest worker, skips resume, and drops suspended
runs instead of pinning process-global slots until TTL, reported with the
existing aborted failure code
- exec description omits API.list/MCP/namespace guidance when the run catalog
has no MCP tools or namespaces, so models stop probing an empty surface
- API.list tolerates a trailing-slash prefix like API.list("mcp/")
|
||
|---|---|---|
| .. | ||
| templates | ||
| AGENTS.default.md | ||
| api-usage-costs.md | ||
| code-mode.md | ||
| credits.md | ||
| device-models.md | ||
| full-release-validation.md | ||
| memory-config.md | ||
| openclaw-ai.md | ||
| path3-live-sqlite-e2e-harness.md | ||
| prompt-caching.md | ||
| release-performance-sweep.md | ||
| RELEASING.md | ||
| rich-output-protocol.md | ||
| rpc.md | ||
| secret-placeholder-conventions.md | ||
| secretref-credential-surface.md | ||
| secretref-user-supplied-credentials-matrix.json | ||
| session-management-compaction.md | ||
| test.md | ||
| token-use.md | ||
| transcript-hygiene.md | ||
| wizard.md | ||