xsl/meida_backend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
59 Commits 1 Branch 0 Tags
a1d0171fc5fb43e9077b0c0e582795172db925d7
Commit Graph
5 Commits
Author SHA1 Message Date
xsl 7bcbb8d40b feat(agent,report): 会话持久化与画像注入、报告反馈与预约留资——PM/开发双Agent迭代1-3
CI / lint / typecheck / import-linter / tests / secrets (push) Canceled after 0s
Details 
- agent: ag_conversation/ag_message 表(迁移0007),上下文组装注入最近报告画像摘要
  (report.profile.latest_profile_summary 经 apps 层闭包注入,同层不互调),历史带最近
  AGENT_HISTORY_TURNS=10 轮;POST/GET /agent/conversations 与消息历史接口
- agent 修复:ChatRequest.conversation_id 改 str(雪花ID超2^53,JS Number丢精度);
  _build_context 挪进 reserve commit 后同一 try,异常走 refund 兜底
- report: rp_feedback(维度反馈 upsert,认同率/修正率 SQL 可算,T-P3-21 最小版——
  L1 记忆未建,不回写结论)+ rp_reservation(预约留资幂等,T-P3-22,预约率口径
  行数/full_report.card_view 去重曝光,门槛≥8%),迁移0008
- 测试:全量 606 passed;ruff/mypy/lint-imports 全绿;E2E 真实 deepseek-v4-flash 验证
  画像注入与历史携带
 2026-09-11 21:50:58 +08:00
xsl cd0ddb131b feat(report): 报告 PDF 导出管线（Phase A，WeasyPrint 服务端渲染） 
- POST /reports/{id}/export：request_key 幂等 + hd_export 日配额三段式（reserve/commit/refund）+ tier2 熔断场景闸（BudgetGuardDep），仅 succeeded 报告可导
- GET /reports/{id}/export/download：归属校验 + 路径收敛（rendered_asset_key 必须落在 report_export_dir 内），FileResponse 携带 UTF-8 文件名
- celery 任务 meida.report.export（cpu 队列）：渲染→落盘 var/exports→回写 rendered_asset_key；业务性拒绝（报告状态变化）结案退款不重试，基础设施异常重试一次后兜底结案退款
- packages/report/pdf：Jinja2 模板 + WeasyPrint 渲染器（url_fetcher 全拒外部资源防 SSRF；维度中文名按 DIMENSION_BY_KEY 回填；色板维度渲染色卡）
- 单测 10 例（资格/幂等/并发同键/下载校验/渲染）；scripts/seed_pdf_e2e.sql 供本地 E2E 造数
 2026-08-30 13:17:23 +08:00
xsl 9e7a886863 chore(prep): shared groundwork for the parallel task batch 
多 agent 并行批次的协调提交（消除全部共享文件冲突面）：
- 迁移 0004：id_session + ob_event 两表（T3/T4 用，任务不再写迁移）
- ORM：UserSession / ObEvent；错误码：九个新码（40xxx/60006，含 meta）
- 配置：四档 tiers / refresh TTL / 任务奖励注册表 / 埋点上限 / COS 直传全套
- 骨架：packages/analytics + packages/storage + events/uploads 空路由（已注册）
- deps：AnalyticsServiceDep / StorageServiceDep；DailyBudgetGuard 接收 tiers
- uv add cos-python-sdk-v5；import-linter/CI/Makefile 纳入两个新包
 2026-08-14 16:02:54 +08:00
xsl f46ecc5eb0 fix(llm): price by call time and stop paying for thinking tokens 
Two defects that only surface against the real DeepSeek API, both of which
break the cost model rather than the code:

deepseek-v4-flash enables thinking mode by default. The same single-turn
question took 13.5s with it on and 1.8s with it off, and the thinking tokens
are billed at the output rate. That misses NFR-PERF-02b (15s per turn) and
inflates every conversational call. SceneConfig now carries an explicit
`thinking` flag, all four V1 scenes set it to false, and the provider always
sends the parameter rather than relying on the upstream default. Reasoning
tokens are recorded separately in Usage.tokens_reasoning so the cost of ever
turning it back on is visible.

DeepSeek moves to peak/off-peak pricing on 2026-08-17, with peak (Beijing
09:00-12:00 and 14:00-18:00) at twice the off-peak rate. Reports are generated
mostly during peak hours, so a single blended rate would leave ob_ai_call --
the only input to V2 pricing -- off by nearly a factor of two.
PeakAwareRateTable resolves the rate at call time; cost is computed and stored
then, never recomputed later at whatever the current rate happens to be.

Also here:
- Replace the live API key in the redaction test with a synthetic one. The
  test that proves we redact secrets was itself a secret leak waiting for its
  first commit.
- Correct LLM_COST_RATES_JSON, which held placeholder rates.
- Make ids.SnowflakeGenerator take an injectable clock so rollover and
  clock-rollback are testable without patching a slots class.
- Rename exceptions to the -Error suffix (N818) and clear the remaining ruff,
  mypy and import-linter findings, including two dead lines: a duplicate
  pytestmark assignment and a no-op assert on a None return.

Gates: ruff, mypy (96 files incl. tests), 4/4 import contracts,
detect-secrets, 166 unit + 3 integration tests, migration up/down round-trip.
 2026-08-14 00:54:40 +08:00
xsl 746b66da01 feat(api): vertical slice POST /v1/agent/chat and the Celery ping path 
One request exercises every layer: JWT auth, quota reservation, a versioned
prompt through the LLM gateway, a cost row, quota commit or refund, and the
unified envelope. The trivial ping task proves the queue routing and the
tk_task transitions before any real long-running task is written.

Routes are mounted at the /api/v1 base path of 架构文档 §9.1; /v1/* is
rewritten to it at the ASGI layer so both spellings work from one route table.
 2026-08-14 00:26:39 +08:00