inference-bot
8ddd023786
gateway: stop forwarding provider response headers to callers
...
LiteLLM copies every upstream response header onto its own response prefixed
'llm_provider-'. For our providers that hands callers operational detail about the
co-op's own account — verified live: llm_provider-x-credits-remaining carried the
remaining provider balance in every member's response.
Build-time patch makes _get_llm_provider_headers() return {}. The four OpenAI-style
x-ratelimit-* headers a provider may send are still forwarded: those describe the
caller's own request, not the co-op's account.
2026-10-27 04:00:57 +00:00
Inferencebot
f75851d6cf
start.sh: kill stale tinfoil-proxy before bind + fail hard if the proxy never comes up
...
The 3301 'address already in use' on process-level restarts left an unmanaged
old proxy serving (pre-update code/flags) while the new one died. Also: if the
proxy never binds, exit 1 instead of exec-ing LiteLLM against a dead 3301 —
that masqueraded as a provider outage. Cache continuity: with
TINFOIL_USER_CACHE_SECRET now pinned (env, 2026-10-22), restarts keep Tinfoil's
prompt-cache warm either way.
2026-10-22 08:25:11 -06:00
Inferencebot
79f0447089
gateway: build-time patch keeping image-gen pricing on the shared cost-map key (upstream #10023/#12471) so image spend is tracked
2026-10-19 09:26:45 -06:00
Inferencebot
9d95527e93
Remove PublicAI provider (billing never operational; Regolo replaces it for Apertus)
2026-10-16 10:46:04 -06:00
Inferencebot
ad34da72a4
Add Regolo provider: apertus-70b, qwen3.5-122b (thinking off), qwen-image + Apertus fallback chain
2026-10-16 10:10:45 -06:00
Inferencebot
d082957167
README: document the audio keep-alive scheduled task
2026-10-12 19:33:18 -06:00
Inferencebot
0d73c80562
keepalive: read master key from /app/data/.master_key (scheduler runs outside litellm's env)
2026-10-12 19:20:24 -06:00
Inferencebot
acceb43995
Move audio keep-alive into the gateway container (Cloudron scheduler addon, every 10m)
2026-10-12 19:18:46 -06:00
Inferencebot
3397d07ec1
Replace tinfoil/glm-5-3-flash (deprecated 2026-10-09) with tinfoil/glm-5.3 flagship
2026-10-07 22:07:40 -06:00
Inferencebot
cc8f7d237a
Add tinfoil/nomic-embed-text embedding model (admin-team scoped, for co-op docs RAG)
2026-10-07 09:44:12 -06:00
Inferencebot
5389d9acfc
credit-pack hint: patch budget-exceeded message at BUILD time (runtime rootfs is read-only; boot-time patch crashed startup)
2026-10-06 14:24:55 -06:00
Inferencebot
91aa0e0b1d
start.sh: append credit-pack hint to LiteLLM's hardcoded budget-exceeded messages (team + key)
2026-10-06 14:04:22 -06:00
Inferencebot
1f2c330762
greenpt/glm-5.3: add cache-read price (0.275/1M per GreenPT pricing API) — member PR follow-up
2026-10-05 08:40:13 -06:00
Inferencebot
a0ae99329f
Add greenpt/deepseek-v4.1-flash as default (renewable, not Experimental); fallback → tinfoil deepseek
2026-10-02 22:15:44 -06:00
Inferencebot
516167aaf9
Remove green-l/green-r models (GreenPT marks them not recommended)
2026-10-02 22:04:47 -06:00
Inferencebot
b6e8542146
config: remove duplicate broken audio-model entries (audio_transcription//audio_speech/ prefixes); keep the correct openai/ routing
2026-10-02 15:39:07 -06:00
Inferencebot
b9af62a614
README: current base image v1.103.2
2026-10-02 15:32:49 -06:00
Inferencebot
a2864ce34a
Upgrade to LiteLLM v1.103.2 (schema pre-migrated live; CVE fix line + streaming-usage bugfix window)
2026-10-02 15:25:27 -06:00
Inferencebot
23f73cf6ae
README: current architecture (3 providers, portal key injection, hardening), remove MVP model list (point to co-op/docs as source of truth), all provider env vars, member-key verification kept
2026-10-02 01:08:34 -06:00
inference-bot