[maiphucgiang]

Summary

• Add the five live cloud growth tasks for Valorant, Bowangwang, Douyinyin, Maidehao and Shangjia promotion to Web accept/claim handling and the existing opt-in execution dispatch.
• Reuse the summon, real-chat and usage-report chain with verified task-specific expert IDs and metadata. Same-name market entries cannot replace an ID, market failures retain the verified fallback, and the lighthouse task keeps its LOCAL event shape.
• Update English/Chinese automation docs and offline regression coverage. Validation did not execute or claim real account tasks.

Tests

• uv run python -B -m pytest -q tests/ — 2373 passed, 2 skipped, 5328 subtests passed.

Summary by Sourcery

Enable the five named cloud growth tasks to run through the existing opt-in expert automation flow with verified identities and compatible event reporting.

New Features:

• Add Web growth-task accept/claim and opt-in execution support for five named cloud experts: Valorant, Bowangwang, Douyinyin, Maidehao, and Shangjia promotion.

Bug Fixes:

• Ensure named expert tasks retain their verified expert identities when market data is unavailable or contains same-name alternatives.

Enhancements:

• Share the named-expert summon and real-conversation reporting flow while preserving the lighthouse task’s existing LOCAL event format.

Documentation:

• Document task-specific expert automation in the English and Chinese growth-center automation guides.

Tests:

• Add regression coverage for verified expert IDs, metadata, fallback behavior, and lighthouse event compatibility.

[sourcery-ai]

Sorry @maiphucgiang, you've used your own review budget of 250,000 diff characters for the last 7 days.

You can request another review in 3 hours and 51 minutes by commenting @sourcery-ai review. Upgrade to get a review now.

[sourcery-ai]

Reviewer's Guide

The PR completes Web accept/claim and opt-in execution support for five named cloud growth tasks by centralizing expert summon and real-chat reporting around verified task-specific metadata, while retaining lighthouse compatibility and adding bilingual documentation and regression coverage.

Sequence diagram for named expert growth task execution

sequenceDiagram
    participant Sweep as GrowthSweep
    participant Dispatch as GrowthDispatch
    participant Chain as _run_named_expert
    participant Market as ExpertMarket
    participant Chat as RealChat
    participant Report as GrowthReport

    Sweep->>Dispatch: growth_auto task
    Dispatch->>Chain: run_workbuddy_valorant / run_expert_bowangwang / run_expert_douyinyin / run_expert_maidehao / run_expert_shangjia_xuanchuan
    Chain->>Market: market_expert_list
    alt verified expert ID found
        Market-->>Chain: task-specific expert metadata
    else market failure or no matching ID
        Chain-->>Chain: retain verified fallback metadata
    end
    Chain->>Report: expert_summon_sequence
    Chain->>Chat: _real_chat
    Chat-->>Chain: conversation_id, request_id
    Chain->>Report: chat_sequence
    Chain->>Report: expert_actual_use

Loading

File-Level Changes

Change	Details	Files
Adds five named expert growth tasks to the shared real-conversation execution path while preserving the lighthouse task’s legacy LOCAL reporting behavior.	Defines verified expert IDs and reporting metadata for Valorant, Bowangwang, Douyinyin, Maidehao, and Shangjia promotion tasks. Introduces a reusable named-expert runner with market lookup, exact-ID matching, verified fallback behavior, summon/chat/usage reporting, and task-specific event mode. Registers each task in the execution dispatch and categorizes it as a chat task for opt-in automation. Keeps the lighthouse expert on LOCAL mode and its existing response semantics.	app/growth_chains.py app/growth_tasks.py
Documents named expert task automation and its opt-in real-conversation behavior in both supported languages.	Explains that named expert tasks use verified task-specific IDs. Clarifies that the tasks reuse the existing opt-in real-conversation chain.	docs/advanced.md docs/advanced.zh-CN.md
Adds offline regression coverage for ID integrity, metadata propagation, dispatch classification, fallback behavior, and lighthouse compatibility.	Verifies same-name market entries cannot override configured expert IDs. Checks summon and actual-use events carry the expected expert metadata and craft mode. Confirms lighthouse reporting retains LOCAL mode, empty type, and zero cost.	tests/test_growth_chains.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.