GenarrativeAI/Genarrative
11
0
Fork 0
Code Issues 14 Pull Requests 3 Actions Packages Projects 3 Releases Wiki Activity

修复AGC大上下文请求体限制 #295

Merged
kdletters merged 2 commits from fix/llm-body-limit into master 2026-09-07 17:05:43 +08:00
Conversation 1 Commits 2 Files Changed 6
+166 -12
suzmii commented 2026-09-07 11:14:47 +08:00
Member
Copy Link
Copy Source

背景与问题

AGC（AI 游戏创作智能体 App）Direct Codex 模式在携带图片工具结果等大上下文调用 LLM 时，/api/llm/responses 与 /api/llm/chat/completions 会命中 Axum 默认 2 MiB 请求体上限，直接被 413 拒绝，大上下文任务无法执行；同时 Codex app-server 的 failed turn 未把上游 413 映射为稳定错误分类，前端只能显示笼统的“其他错误”，无法引导用户处理。

改动内容

1. api-server（server-rs）

  • 新增常量 LLM_REQUEST_MAX_BODY_BYTES = 32 MiB，作为两个 LLM 代理路由的正式请求体上限；
  • 两个路由显式配置 DefaultBodyLimit::max(32 MiB)，避免 Axum 默认 2 MiB 提前拒绝；handler 内保留超限检查，超过 32 MiB 仍返回 413 PAYLOAD_TOO_LARGE；
  • 补充回归测试：>2 MiB 大上下文请求不再命中默认限制；超过 32 MiB 仍返回 413。

2. AGC 壳（apps/ai-game-creator-shell）

  • codex_app_server 错误映射：上游/连接层 HTTP 413、PAYLOAD_TOO_LARGE、provider request too large 等统一映射为稳定分类 codex-app-server-error:request-too-large，不再落入 other 或误判为权限/安全策略错误；
  • 前端新增用户可见文案“模型请求体过大，请减少参考图或上下文后重试”，并补充单测断言。

3. 文档

  • 【技术方案】AI游戏创作智能体App实施计划-2026-06-24.md 补充“2026-09-06 AGC LLM 代理请求体合同”：明确 32 MiB 上限、必须显式配置 DefaultBodyLimit、413 映射规则与用户文案。

验证

  • cargo test -p api-server llm_routes_accept_large_context_bodies_beyond_axum_default 通过
  • cargo test -p api-server llm_responses_rejects_bodies_above_explicit_limit 通过
  • cargo test ... ai-game-creator-shell ... codex_app_server_failed_turn_maps_request_too_large_details 通过
  • npm run test -- apps/ai-game-creator-shell/tests/agentRuntimeModel.test.ts（27 通过）

全量 workspace 测试与 CI 门禁待推送后由 CI 覆盖。

## 背景与问题 AGC（AI 游戏创作智能体 App）Direct Codex 模式在携带图片工具结果等大上下文调用 LLM 时，`/api/llm/responses` 与 `/api/llm/chat/completions` 会命中 Axum 默认 **2 MiB** 请求体上限，直接被 413 拒绝，大上下文任务无法执行；同时 Codex app-server 的 failed turn 未把上游 413 映射为稳定错误分类，前端只能显示笼统的“其他错误”，无法引导用户处理。 ## 改动内容 **1. api-server（server-rs）** - 新增常量 `LLM_REQUEST_MAX_BODY_BYTES = 32 MiB`，作为两个 LLM 代理路由的正式请求体上限； - 两个路由显式配置 `DefaultBodyLimit::max(32 MiB)`，避免 Axum 默认 2 MiB 提前拒绝；handler 内保留超限检查，超过 32 MiB 仍返回 `413 PAYLOAD_TOO_LARGE`； - 补充回归测试：>2 MiB 大上下文请求不再命中默认限制；超过 32 MiB 仍返回 413。 **2. AGC 壳（apps/ai-game-creator-shell）** - `codex_app_server` 错误映射：上游/连接层 HTTP 413、`PAYLOAD_TOO_LARGE`、`provider request too large` 等统一映射为稳定分类 `codex-app-server-error:request-too-large`，不再落入 `other` 或误判为权限/安全策略错误； - 前端新增用户可见文案“模型请求体过大，请减少参考图或上下文后重试”，并补充单测断言。 **3. 文档** - 【技术方案】AI游戏创作智能体App实施计划-2026-06-24.md 补充“2026-09-06 AGC LLM 代理请求体合同”：明确 32 MiB 上限、必须显式配置 `DefaultBodyLimit`、413 映射规则与用户文案。 ## 验证 - `cargo test -p api-server llm_routes_accept_large_context_bodies_beyond_axum_default` 通过 - `cargo test -p api-server llm_responses_rejects_bodies_above_explicit_limit` 通过 - `cargo test ... ai-game-creator-shell ... codex_app_server_failed_turn_maps_request_too_large_details` 通过 - `npm run test -- apps/ai-game-creator-shell/tests/agentRuntimeModel.test.ts`（27 通过） 全量 workspace 测试与 CI 门禁待推送后由 CI 覆盖。
suzmii added 1 commit 2026-09-07 11:14:47 +08:00
修复AGC大上下文请求体限制
Project CI / Frontend tests (pull_request) Successful in 3m55s
Details
Project CI / Repository checks (pull_request) Successful in 4m2s
Details
Project CI / Backend tests (pull_request) Successful in 14m59s
Details
Project CI / Native shell tests (pull_request) Successful in 18m52s
Details
1aac66d159 
为LLM Responses与Chat路由显式启用32MiB请求体限制

将Codex上游413映射为request-too-large稳定分类

补充大请求体与错误文案回归测试和架构文档
suzmii self-assigned this 2026-09-07 15:13:02 +08:00
suzmii requested review from kdletters 2026-09-07 15:47:41 +08:00
suzmii added 1 commit 2026-09-07 15:47:50 +08:00
Merge branch 'master' into fix/llm-body-limit
Project CI / Frontend tests (pull_request) Successful in 2m47s
Details
Project CI / Repository checks (pull_request) Successful in 2m15s
Details
Project CI / Backend tests (pull_request) Successful in 6m16s
Details
Project CI / Native shell tests (pull_request) Successful in 20m43s
Details
7929e4d881
kdletters approved these changes 2026-09-07 17:00:40 +08:00
kdletters left a comment
Member
Copy Link
Copy Source

当前提交代码审查通过，未发现需要修改的问题。

已在该提交完成以下定向验证：

  • api-server：两个 LLM 路由接受超过 Axum 默认 2 MiB 的请求体，通过。
  • api-server：Responses 请求体超过显式 32 MiB 上限返回 413，通过。
  • 原生壳：codex_app_server_failed_turn 错误映射 5 项测试通过，覆盖 HTTP 413 与文本详情分类。
  • 前端：agentRuntimeModel 27 项测试通过。

远端 4 项 CI 仍为 Waiting to run，合并前请等待门禁通过。

当前提交代码审查通过，未发现需要修改的问题。 已在该提交完成以下定向验证： - api-server：两个 LLM 路由接受超过 Axum 默认 2 MiB 的请求体，通过。 - api-server：Responses 请求体超过显式 32 MiB 上限返回 413，通过。 - 原生壳：codex_app_server_failed_turn 错误映射 5 项测试通过，覆盖 HTTP 413 与文本详情分类。 - 前端：agentRuntimeModel 27 项测试通过。 远端 4 项 CI 仍为 Waiting to run，合并前请等待门禁通过。
kdletters merged commit e15e3b455f into master 2026-09-07 17:05:43 +08:00
kdletters deleted branch fix/llm-body-limit 2026-09-07 17:05:43 +08:00
Sign in to join this conversation.
Reviewers
No Reviewers
kdletters
Labels
Clear labels
Compat/Breaking
Breaking change that won't be backward compatible
 Kind/Bug
Something is not working
 Kind/Documentation
Documentation changes
 Kind/Enhancement
Improve existing functionality
 Kind/Feature
New functionality
 Kind/Security
This is security issue
 Kind/Testing
Issue or pull request related to testing
Priority
Critical
1
The priority is critical
Priority
High
2
The priority is high
Priority
Low
4
The priority is low
Priority
Medium
3
The priority is medium
Reviewed
Confirmed
1
Issue has been confirmed
Reviewed
Duplicate
2
This issue or pull request already exists
Reviewed
Invalid
3
Invalid issue
Reviewed
Won't Fix
3
This issue won't be fixed
Status
Abandoned
3
Somebody has started to work on this but abandoned work
Status
Blocked
1
Something is blocking this issue or pull request
Status
Need More Info
2
Feedback is required to reproduce issue or to continue work
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
HuangJiaJia JenkenB k88936 (王德宇) kdletters (段舒康) laura2008 (王乐) lhk229 (孔令弘) Loer (农洛儿) loong suzmii (董羽秦) taobaisu (叶东旭) wuxiangwanzi (王子民) YixuanLiu ziyu
No Assignees suzmii
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: GenarrativeAI/Genarrative#295
Delete Branch "fix/llm-body-limit"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?