v0.9.9

zeroclaw-labs/zeroclawv0.9.9Sep 10, 2026by tashfeenahmed

Upgrading?

AI Summary

This release adds support for Router9 and Septor Labs, optimizes routing by skipping platforms without keys, enables response caching for streaming requests, and adds execution IDs for better observability.

Key Highlights

  • New first-class adapters for Router9 and Septor Labs with key import aliases.
  • Streaming requests can now be cached and replayed as SSE.
  • Execution ID added to every chat body for request tracking.
  • Sign-in gate accessibility improvements with labels and ARIA roles.

New Features

  • First-class adapters for Router9 and Septor Labs with platform colors and quota observations.
  • Keyless platforms are dropped before the routing walk to save the attempt budget.
  • Response cache support for streaming requests (off by default, up to 2 MB).
  • New 'caller' column in the requests table for OpenAI and other paths.
  • Dashboard sign-in gate accessibility improvements (labels, ARIA roles, mobile centering).
  • Documentation updates describing streaming replay and observability details.

Full Release Notes

## Providers
- **Router9 and Septor Labs** join the router with first-class adapters: key import aliases, key-picker entries, platform colours and account-wide quota observations. Router9 keys are validated with a no-inference probe; Septor responses that come back under a different model identity are rejected as retryable before any substituted content is streamed. (#1194)

## Routing
- **Keyless platforms no longer eat the attempt budget.** Models whose platform has no enabled, healthy key are dropped before the routing walk, so the "all attempts failed" summary and the retry budget only count candidates that could actually run. Pinned models are still tried and still report against their own label. (#1105, thanks @chongjiazhen)

## Cache
- **Streaming requests can hit the response cache.** `stream: true` completions are stored frame by frame in their own store and replayed as byte-identical SSE on a hit, with `X-FreeLLM-Cache: HIT`. Streams are only buffered when a cache key exists, buffering stops at 2 MB, truncated or broken streams are never stored, stream lookups feed the hit-rate counters, and both stores share the one `RESPONSE_CACHE_MAX_ENTRIES` cap. Off by default, as before. (#1099, #1197, thanks @suantea)

## Observability
- **`execution_id` in every chat body.** Both completion routes now return the request's execution id on success, cache hits, idempotency replays and every error body, so a client can quote it against the request log. The `requests` table gains a `caller` column, written by the OpenAI, Responses, Messages, Ollama/Gemini and fusion paths. (#1103, #1196, thanks @suantea)

## Dashboard
- **Sign-in gate accessibility.** Fields are labelled, validation errors are tied to their inputs with `aria-describedby` and announced with `role="alert"`, the desktop session-repair error is announced the same way, and the gate uses `min-h-dvh` so it centres correctly on mobile viewports. Covered by tests. (#1078, #1195, thanks @Kaban15)

## Docs
- Streaming-pipeline, REST API, environment and idempotency pages in `docs/en` and `docs/zh-cn` now describe streaming replay; the observability page documents `execution_id` and `caller`. README credits @Kaban15.

Full changelog: https://github.com/tashfeenahmed/freellmapi/compare/v0.9.8...v0.9.9

---
⭐ Like the free router? [Go Premium](https://freellmapi.co/?utm_source=github&utm_medium=release&utm_campaign=premium&utm_content=v0.9.9#pricing) — the live signed catalog, $19/yr, cancel anytime.

Related Repositories