Requesty (added in #474) is an OpenAI-compatible gateway whose capabilities
were a copy of OpenRouter's: same provider/model naming, same
extra_body.reasoning opt-in, no adapter code of its own. Built-in slots are
kept for providers with their own behaviour; a gateway that speaks an
existing wire format is configured through that provider, and #1532 (API
Route) is being closed on the same grounds.
Migration, identical request shape: LANGCHAIN_PROVIDER=openrouter,
OPENROUTER_BASE_URL=https://router.requesty.ai/v1, OPENROUTER_API_KEY=<the
Requesty key>. Past news and contributor credits in the READMEs are left
as history; the supported-provider lists drop it.
The models listed for Novita were older ids that no longer reflect what
the platform leads with. Point the recommendations at the three current
flagships instead, each verified against api.novita.ai:
moonshotai/kimi-k3 1M context, native vision
zai-org/glm-5.2 1M context, long-horizon agentic work
deepseek/deepseek-v4-flash-0731 1M context, cheapest of the three
Context windows, output limits, input modalities and pricing were taken
from the live /openai/v1/models response rather than carried over.
Signed-off-by: jax-novita <jax-novita@users.noreply.github.com>
Wire Novita AI's OpenAI-compatible endpoint
(https://api.novita.ai/openai, Bearer API key) through the provider
registry, capabilities, legacy CLI onboarding, .env.example, and the
README provider list. Novita rides the generic OpenAI-compatible path
with no special capability flags; the default model is
deepseek/deepseek-v3.2, which supports function calling.
Model IDs use ``vendor/model`` naming and were verified against the live
public catalog at https://api.novita.ai/openai/v1/models.
Signed-off-by: jax-novita <jax@novita.ai>
Wire iFlytek Spark's OpenAI-compatible HTTP endpoint
(https://spark-api-open.xf-yun.com/v1, Bearer APIPassword) through the
provider registry, capabilities, legacy CLI onboarding, .env.example, and
the README provider list, with "iflytek" accepted as an alias. Spark rides
the generic OpenAI-compatible path with no special capability flags; the
default model is 4.0Ultra, which supports function calling.
Signed-off-by: FenjuFu <92919259+FenjuFu@users.noreply.github.com>
- Replace assistant-role handoff messages with user-role in agent loop
to avoid "assistant message prefill" rejection on Anthropic Claude Opus 4.8+
- Allow MOONSHOT_USER_AGENT env var to override Kimi/Moonshot User-Agent header
for compatibility with Kimi Coding API endpoint
Closes#246, Closes#204
Signed-off-by: wesley <wesley87@wesley87deMacBook-Pro.local>
Co-authored-by: wesley <wesley87@wesley87deMacBook-Pro.local>
A cluster of provider reports traced to one root: every OpenAI-compatible
provider shared a single shim that applied DeepSeek/Kimi/Gemini quirks
globally and silently swallowed stream failures.
- Provider capability layer (capabilities.py): reasoning capture/replay,
Gemini thought signatures, Kimi User-Agent (version from package
metadata), OpenRouter reasoning body — gated per provider, no
cross-contamination
- Optional native DeepSeek adapter via VIBE_TRADING_DEEPSEEK_ADAPTER
(auto/native/openai-compatible) + 'deepseek' extra (langchain-deepseek)
- ChatLLM.stream_chat: silent fallback to chat() removed; failures raise
ProviderStreamError with redacted provider/model context; one retry for
transient errors in AgentLoop + swarm worker (deterministic 4xx fail fast)
- Empty model response diagnosed as empty_model_response instead of
'reached max iterations'
- reasoning_delta SSE event (throttled to 1/s, first chunk immediate) +
frontend 'Reasoning…' indicator; reasoningActive reset on safety timeout
- SSE heartbeats carry no replay id; replay falls back to full buffer on
unknown last-event-id; read-only tools get a hard timeout
(VIBE_TRADING_TOOL_TIMEOUT_SECONDS) instead of hiding behind heartbeats
- 'vibe-trading provider doctor' prints redacted provider/model/package/
proxy diagnostics; preflight includes the same hint
- kimi-k2.x temperature=1 requirement auto-applied; Kimi path verified
end-to-end against the live API (kimi-k2.6 tool calls + strict
multi-turn reasoning replay)
Refs #208#203#195#204
Haozhe Wu