✨ Feat: support user to configurate model concurrency limit and timeout seconds#2943
Open
xuyaqist wants to merge 42 commits into
Open
✨ Feat: support user to configurate model concurrency limit and timeout seconds#2943xuyaqist wants to merge 42 commits into
xuyaqist wants to merge 42 commits into
Conversation
xuyaqist
changed the title
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds per-model request timeout and concurrency limit configuration across the frontend, backend persistence, and SDK model wrappers, and uses the configured concurrency limit to throttle concurrent LLM calls during system-prompt generation.
Changes:
- Add
timeout_seconds/concurrency_limitfields to model config types, API payloads, and DB schema. - Expose timeout/concurrency controls in model add/edit dialogs and propagate them through
modelService. - Apply timeout during connectivity checks and throttle concurrent prompt-generation threads based on the model’s concurrency limit.
Reviewed changes
Copilot reviewed 22 out of 22 changed files in this pull request and generated 16 comments.
Show a summary per file
| File | Description |
|---|---|
| sdk/nexent/core/models/openai_llm.py | Adds timeout + concurrency parameters to OpenAIModel and uses them in connectivity checks. |
| sdk/nexent/core/agents/nexent_agent.py | Passes timeout into OpenAIModel when instantiating agent models. |
| sdk/nexent/core/agents/agent_model.py | Extends ModelConfig schema with timeout and concurrency fields. |
| frontend/types/modelConfig.ts | Adds timeoutSeconds / concurrencyLimit to the frontend model option type. |
| frontend/services/modelService.ts | Maps timeout/concurrency fields between API snake_case and UI camelCase for create/update flows. |
| frontend/public/locales/zh/common.json | Adds i18n strings for timeout and concurrency fields (ZH). |
| frontend/public/locales/en/common.json | Adds i18n strings for timeout and concurrency fields (EN). |
| frontend/app/[locale]/models/components/model/ModelEditDialog.tsx | Adds timeout/concurrency inputs and extends provider config dialog to edit them. |
| frontend/app/[locale]/models/components/model/ModelDeleteDialog.tsx | Uses the shared provider config dialog for per-model settings and batch settings. |
| frontend/app/[locale]/models/components/model/ModelAddDialog.tsx | Adds timeout/concurrency inputs and per-model settings via shared dialog. |
| docker/sql/v2.1.1_0507_add_concurrency_and_timeout_to_model_record_t.sql | Adds DB columns for timeout_seconds and concurrency_limit. |
| backend/utils/llm_utils.py | Passes timeout from model config into OpenAIModel for system prompt calls. |
| backend/services/prompt_service.py | Fetches concurrency_limit and uses a semaphore to throttle concurrent LLM calls during prompt generation. |
| backend/services/model_provider_service.py | Defaults timeout for LLM provider models and merges existing attributes (incl. timeout/concurrency). |
| backend/services/model_management_service.py | Adds update-by-id-or-name logic for batch updates and adjusts ssl_verify auto-setting. |
| backend/services/model_health_service.py | Passes timeout into connectivity checks and adds an ssl_verify fallback behavior. |
| backend/services/file_management_service.py | Passes timeout into OpenAILongContextModel construction. |
| backend/services/conversation_management_service.py | Passes timeout into OpenAIModel for title generation. |
| backend/database/model_management_db.py | Adds update_model_record_by_model_name helper for batch updates. |
| backend/database/db_models.py | Adds ORM columns for timeout_seconds and concurrency_limit. |
| backend/consts/model.py | Extends request schemas with timeout/concurrency for create/update/manage flows. |
| backend/agents/create_agent_info.py | Propagates timeout into agent ModelConfig generation. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+304
to
+307
| if model_id_or_name and model_id_or_name.isdigit(): | ||
| # Use model_id (primary key) for update | ||
| logging.info(f"[DEBUG] Updating model by id: model_id={model_id_or_name}, tenant_id={tenant_id}, update_data={update_data}") | ||
| update_model_record(int(model_id_or_name), update_data, user_id, tenant_id) |
xuyaqist
changed the title
xuyaqist
force-pushed
the
xyq/feat_add_model_timeout
branch
2 times, most recently
from
0a433db to
0eb02b0
Compare
…ack fallback casuing dimension=0
This reverts commit d1cffeb.
xuyaqist
force-pushed
the
xyq/feat_add_model_timeout
branch
from
5e70bf9 to
c33b368
Compare
…rating agent info
This reverts commit 9b59e72.
# Conflicts: # backend/utils/llm_utils.py # frontend/app/[locale]/agents/components/agentInfo/AgentGenerateDetail.tsx # frontend/types/agentConfig.ts # test/backend/services/test_prompt_service.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
（1）批量编辑
3. 当用户配置了并发限制之后，在生成智能体的时候，会根据并发限制分批次地去调用模型生成智能体信息