diff --git a/CHANGELOG.md b/CHANGELOG.md index f76e1fbb4..fa0f32f16 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -21,6 +21,7 @@ Docs: https://docs.openclaw.ai - Cron/Gateway: keep `cron.list` and `cron.status` responsive during startup catch-up by avoiding a long-held cron lock while missed jobs execute. (#23106) Thanks @jayleekr. - Gateway/Config reload: compare array-valued config paths structurally during diffing so unchanged `memory.qmd.paths` and `memory.qmd.scope.rules` no longer trigger false restart-required reloads. (#23185) Thanks @rex05ai. - TUI/Input: enable multiline-paste burst coalescing on macOS Terminal.app and iTerm so pasted blocks no longer submit line-by-line as separate messages. (#18809) Thanks @fwends. +- Agents/Fallbacks: treat JSON payloads with `type: "api_error"` + `"Internal server error"` as transient failover errors so Anthropic 500-style failures trigger model fallback. (#23193) Thanks @jarvis-lane. - Gateway/Pairing: treat operator.admin pairing tokens as satisfying operator.write requests so legacy devices stop looping through scope-upgrade prompts introduced in 2026.2.19. (#23125, #23006) Thanks @vignesh07. - Memory/QMD: add optional `memory.qmd.mcporter` search routing so QMD `query/search/vsearch` can run through mcporter keep-alive flows (including multi-collection paths) to reduce cold starts, while keeping searches on agent-scoped QMD state for consistent recall. (#19617) Thanks @nicole-luxe and @vignesh07. - Chat/UI: strip inline reply/audio directive tags (`[[reply_to_current]]`, `[[reply_to:]]`, `[[audio_as_voice]]`) from displayed chat history, live chat event output, and session preview snippets so control tags no longer leak into user-visible surfaces. diff --git a/src/agents/pi-embedded-helpers.isbillingerrormessage.e2e.test.ts b/src/agents/pi-embedded-helpers.isbillingerrormessage.e2e.test.ts index 62dd44531..3eb78cf95 100644 --- a/src/agents/pi-embedded-helpers.isbillingerrormessage.e2e.test.ts +++ b/src/agents/pi-embedded-helpers.isbillingerrormessage.e2e.test.ts @@ -377,4 +377,11 @@ describe("classifyFailoverReason", () => { ), ).toBe("rate_limit"); }); + it("classifies JSON api_error internal server failures as timeout", () => { + expect( + classifyFailoverReason( + '{"type":"error","error":{"type":"api_error","message":"Internal server error"}}', + ), + ).toBe("timeout"); + }); }); diff --git a/src/agents/pi-embedded-helpers/errors.ts b/src/agents/pi-embedded-helpers/errors.ts index 9717dd6dc..9e0ceb050 100644 --- a/src/agents/pi-embedded-helpers/errors.ts +++ b/src/agents/pi-embedded-helpers/errors.ts @@ -686,6 +686,16 @@ export function isOverloadedErrorMessage(raw: string): boolean { return matchesErrorPatterns(raw, ERROR_PATTERNS.overloaded); } +function isJsonApiInternalServerError(raw: string): boolean { + if (!raw) { + return false; + } + const value = raw.toLowerCase(); + // Anthropic often wraps transient 500s in JSON payloads like: + // {"type":"error","error":{"type":"api_error","message":"Internal server error"}} + return value.includes('"type":"api_error"') && value.includes("internal server error"); +} + export function parseImageDimensionError(raw: string): { maxDimensionPx?: number; messageIndex?: number; @@ -794,6 +804,9 @@ export function classifyFailoverReason(raw: string): FailoverReason | null { // Treat transient 5xx provider failures as retryable transport issues. return "timeout"; } + if (isJsonApiInternalServerError(raw)) { + return "timeout"; + } if (isRateLimitErrorMessage(raw)) { return "rate_limit"; }