feat: message_history storage in redis

[YEEthanCC]

Summary by CodeRabbit

• Refactor
  • Query endpoint updated to use session-based history management instead of inline history passing
  • API response payload no longer includes conversation history

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

Caution

Review failed

The pull request is closed.

Walkthrough

The pull request migrates history management from client-side to server-side. The API endpoint now accepts a session_id instead of passing history with each request. Session history is stored and retrieved from Redis via new utility functions in the service and persistence layers.

Changes

Cohort / File(s)	Summary
Session Management Layer db/session.py	New module with Redis-backed session store. Adds get_session() and set_session() functions for storing and retrieving pickled session history keyed by session_id. Initializes module-level Redis client connected to localhost:6379.
Service Layer services/repo_service.py	Updated query() function signature to accept session_id: str instead of history: list[Any]. Function now retrieves history via get_session(), passes it to rag_agent.run(), and persists updates via set_session(). Returns only response output.
Controller Layer controllers/repo_controller.py	Updated GET /repo/query endpoint to accept session_id parameter instead of history. Changed internal service call and response payload to exclude history; now returns only {"response": response}.
Application Setup main.py	Removed Redis client import and initialization lines. Session management is now delegated to db/session.py.

Sequence Diagram

sequenceDiagram
    participant Client
    participant Controller as API Controller
    participant Service as Repo Service
    participant Redis as Redis Session Store

    Note over Client,Redis: New Session-Based Flow
    Client->>Controller: GET /repo/query<br/>(question, repo_path, session_id)
    Controller->>Service: query(question, repo_path, session_id)
    Service->>Redis: get_session(session_id)
    Redis-->>Service: history (or [])
    Service->>Service: rag_agent.run(question,<br/>message_history=history)
    Service->>Redis: set_session(session_id, history)
    Redis-->>Service: ack
    Service-->>Controller: response
    Controller-->>Client: {"response": response}

Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

• Signature changes across layers: Verify that session_id parameter is correctly threaded through controller → service → session store.
• Session serialization: Confirm pickle serialization/deserialization is appropriate and handles edge cases (empty sessions, corrupt data).
• Redis connectivity: Ensure hardcoded localhost:6379 connection is intentional or should be configurable; verify Redis availability assumptions.
• History retrieval and persistence: Validate that get_session() returning empty list [] for missing keys doesn't cause unexpected behavior in rag_agent.run().

Poem

🐰 A rabbit hops through sessions now,

No history clutters each request's bow.

Redis stores our tales with care,

Server-side magic floats in the air! 🔴✨

---

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Free

📥 Commits

Reviewing files that changed from the base of the PR and between 539566d and 7f7ceef.

📒 Files selected for processing (4)

• controllers/repo_controller.py (1 hunks)
• db/session.py (1 hunks)
• main.py (0 hunks)
• services/repo_service.py (1 hunks)

Tip

📝 Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.

• Provide your own instructions using the high_level_summary_instructions setting.
• Format the summary however you like (bullet lists, tables, multi-section layouts, contributor stats, etc.).
• Use high_level_summary_in_walkthrough to move the summary from the description to the walkthrough section.

Example instruction:

"Divide the high-level summary into five sections:

1. 📝 Description — Summarize the main change in 50–60 words, explaining what was done.
2. 📓 References — List relevant issues, discussions, documentation, or related PRs.
3. 📦 Dependencies & Requirements — Mention any new/updated dependencies, environment variable changes, or configuration updates.
4. 📊 Contributor Summary — Include a Markdown table showing contributions:
   | Contributor | Lines Added | Lines Removed | Files Changed |
5. ✔️ Additional Notes — Add any extra reviewer context.
   Keep each section concise (under 200 words) and use bullet or numbered lists for clarity."

Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later.

---

Note

🎁 Summarized by CodeRabbit Free

Your organization is on the Free plan. CodeRabbit will generate a high-level summary and a walkthrough for each pull request. For a comprehensive line-by-line review, please upgrade your subscription to CodeRabbit Pro by visiting https://app.coderabbit.ai/login.

_{Comment @coderabbitai help to get the list of available commands and usage tips.}