Eric Wang
24e2cfbe10
- Validate stage prefixes before forwarding model tokens. Invalid prefixes may use the existing repair budget; once output starts, validation failure aborts the turn without appending a regenerated reply. Bound the token queue and close inner streams when consumption stops. - Replace delete-time lock eviction with reference-counted session locks covering holders and waiters. Serialize set/get with chat/stream/delete and release cancelled waiters without replacing a live lock. - Store person synonyms under workflow-native driver keys and expose consistent alias views to single/group reads and graph prompt injection. - Separate committed field patches from public formUpdate visibility. Commit callbacks keep repository fields synchronized even when updates are hidden or the consumer closes after graph completion. - Disable OpenAI SDK automatic retries. Own bounded retry attempts in the application, use 1/2/4 second backoff, retry streams only before text is emitted, enforce attempt timeouts, and close upstream/client resources. - Translate FastGPT SDK max_retries (total attempts) from the configured extra-retry count, and verify the real SDK loop uses four attempts. - Document the per-LLM budget and streaming failure semantics without claiming the whole multi-call HTTP turn has the same timeout. Validation: 267 offline tests passed, including actual SDK requests through MockTransport, stream repair/abort, timeout/close, lock races, aliases and formUpdate visibility; existing four dependency deprecation warnings.
42 lines
1.9 KiB
Bash
42 lines
1.9 KiB
Bash
DATABASE_URL=sqlite:///./test.db
|
||
SECRET_KEY=your_secret_key
|
||
DEBUG=True
|
||
|
||
ANALYSIS_SERVICE_URL=http://127.0.0.1:3030
|
||
ANALYSIS_AUTH_TOKEN=replace-with-fastgpt-api-key
|
||
APP_ID=replace-with-fastgpt-app-id
|
||
|
||
# Voice demo (Pipecat /ws-product). Relative to project root, or an absolute path.
|
||
VOICE_CONFIG=config/voice.json
|
||
|
||
# LangGraph chat backend（作业 2）
|
||
# AGENT_BACKEND=langgraph
|
||
#
|
||
# 命名 LLM 提供商组（均为 OpenAI 兼容接口）：LLM_PROVIDERS 声明名单，
|
||
# LLM_PROVIDER 选择当前生效组；缺省或 fake = 离线脚本模型。
|
||
# 每组 LLM_<名>_BASE_URL / _API_KEY / _MODEL 必填；
|
||
# 可选 _TIMEOUT_SECONDS / _MAX_RETRIES / _TEMPERATURE / _EXTRA_BODY（JSON 字符串，
|
||
# 如思考开关 KIMI 网关为 {"reasoning_effort":"none"}）。
|
||
# 超时/重试缺省：每次尝试 60 秒，最多额外重试 3 次，退避 1、2、4 秒。
|
||
# SDK 自动重试关闭；流式发出首个文本 token 后不重试。
|
||
# 单次 LLM 调用预算最多 247 秒（另加响应关闭清理）；不是整轮聊天总超时。
|
||
# AGENT_HISTORY_MESSAGES=50：注入模型的对话历史上限（最近 N 条，
|
||
# 双向计数）；调大支持长对话；0 = 不截断（对齐 FastGPT 全量历史）。
|
||
# AGENT_HISTORY_MESSAGES=0
|
||
# LLM_PROVIDERS=deepseek,kimi,gpt6luna
|
||
# LLM_PROVIDER=deepseek
|
||
# LLM_DEEPSEEK_BASE_URL=https://api.openai.com/v1
|
||
# LLM_DEEPSEEK_API_KEY=replace-with-llm-api-key
|
||
# LLM_DEEPSEEK_MODEL=gpt-4o-mini
|
||
# LLM_DEEPSEEK_EXTRA_BODY={"reasoning_effort":"none"}
|
||
# LLM_KIMI_BASE_URL=http://127.0.0.1:3425/v1
|
||
# LLM_KIMI_API_KEY=magpie
|
||
# LLM_KIMI_MODEL=kimi-code-cn/kimi-for-coding
|
||
# LLM_KIMI_EXTRA_BODY={"reasoning_effort":"none"}
|
||
# LLM_GPT6LUNA_BASE_URL=http://127.0.0.1:3425/v1
|
||
# LLM_GPT6LUNA_API_KEY=magpie
|
||
# LLM_GPT6LUNA_MODEL=codex/gpt-6-luna
|
||
# LLM_GPT6LUNA_EXTRA_BODY={"reasoning_effort":"none"}
|
||
# 本地网关需直连（系统代理会导致 5xx）；外部网关如需代理：
|
||
# LLM_HTTP_TRUST_ENV=true
|