daily_stock_analysis
daily_stock_analysis combines watchlist market data, news, model analysis and report delivery. It is relevant to users who are willing to configure providers and retain an analysis history. Our review fixes one source commit and checks selected engineering paths using synthetic inputs. It does not evaluate real securities or investment performance. We used Python 3.12.13, temporary SQLite files and the project’s default configuration object, bypassing environment bootstrap. The full application, live providers, model calls and notification channels were outside this local test.
Twelve checks covered daily-row updates, database rebinding, moving averages and report parsing. Three input records spanning two dates created two rows, with the last duplicate winning. Rewriting an existing date returned zero additions while updating its value. A new database URL produced an isolated binding, the old reference remained readable, and an invalid candidate did not break the healthy binding. Reversing an eighty-row synthetic series still produced the correct latest value and independently checked averages. A ten-row input reported insufficient analysis data.
Report scores outside zero to one hundred were rejected, but an empty object parsed with missing fields and extra fields were preserved. This permissive schema is an entry point, not evidence verification or the complete publication gate. Teams adopting the system should reconcile dates, source provenance and adjustment conventions before evaluating a model narrative. Self-hosting options do not remove model, data or compute requirements. Choose a small, inspectable data trial if organizing reports is the objective; predictive accuracy, returns and full deployment reliability require separate evaluation.
Read the full review, verification scope and sources →Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-11-03
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 4
- Latest release
- v3.33.0 (2026-10-15)
- Open issues
- 41
- Recent issues with at least one comment
- 12/12
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #1903 feat: 增强 DecisionSignal 后验复盘并反馈到 Agent 记忆9 comments · 2026-07-03
- #1743 roadmap: Codex / Claude Code / OpenCode / Hermes 本地生成与 Agent Backend9 comments · 2026-06-21
- #1595 perf: 提高 LLM 分析输入的 prompt cache 利用率9 comments · 2026-06-04
- #1733 长期开发规划:AI 投研系统、AlphaSift 深度融合、本地 Agent 能力复用与跨资产分析6 comments · 2026-06-20
- #2411 feat(llm): 官方账号授权与模型接入(先调研与规划,待审查)4 comments · 2026-10-14
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Who it fits
- You can reconcile source dates and values before reviewing generated reports.
- You want a small, inspectable self-hosted data-workflow trial.
- You require demonstrated investment performance.
- You expect schema parsing to prove report completeness and evidence quality.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!