feat: fallback chain configuration with per-agent overrides and gateway providers (t132.4) #781
Conversation
…ateway providers (t132.4) Configurable multi-provider fallback chains that activate on API errors, timeouts, and rate limits. Supports per-agent YAML frontmatter overrides, global JSON config defaults, and gateway providers (OpenRouter, Cloudflare AI Gateway) for provider-level fallback routing. New files: - fallback-chain-helper.sh: Chain resolution, trigger detection, cooldown mgmt - fallback-chain-config.json.txt: Global config template with per-tier chains - fallback-chains.md: Documentation with architecture and integration guide Integration: - supervisor resolve_model() now tries fallback chain first (chose chain-first over availability-first -- matches existing patterns where chain provides richer resolution including gateway providers) - model-availability-helper.sh resolve_tier() falls through to chain when primary/fallback both fail; new resolve-chain command for direct chain access - Model tier files (opus.md, sonnet.md) gain fallback-chain: frontmatter
|
Warning Gemini encountered an error creating the summary. You can try again by commenting |
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
2 similar comments
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
All 8 subtasks of t132 (Cross-Provider Model Routing) are now complete: - t132.1: Model-specific subagents (PR #758) - t132.2: Provider/model registry (PR #761) - t132.3: Model availability checker (PR #770) - t132.4: Fallback chain config (PR #781) - t132.5: Supervisor model resolution (PR #787) - t132.6: Quality gate with escalation (PR #788) - t132.7: Multi-provider runner/cron support (PR #789) - t132.8: Cross-model review workflow (PR #791) Also fixed stale git conflict markers in TODO.md.
1 participant
Summary
New Files
Modified Files
Quality
Closes t132.4