qianfan-deepresearch

Version 1.1.4 of deepresearch-conversation — major update and rebranding. - Renamed skill to "qianfan-deepresearch" and updated the description for greater clarity and coverage. - Streamlined the workflow: switched to a single-step, fully automated bash script execution that outputs report download links in Markdown and HTML. - Introduced deep research versions: lite (default), standard, pro; includes explicit mapping rules triggered by specific user keywords. - Set strict guidelines for query generation, with clear rules for use, required clarifications, and which user inputs map to which research depth. - Standardized user-facing output with a fixed template; all responses now strictly follow the mandated format, forbidding extra commentary or formatting. - Deprecated manual SSE/HTTP workflow in favor of a robust wrapper script; users/agents must now always call scripts/deepresearch.py with proper long timeouts and parse only its stdout JSON. - Enhanced resource section and practical examples to illustrate real-world usage and correct input/output patterns.

DeepResearch skill 1.1.3 — major overhaul and simplification. - Replaced and simplified the SKILL.md to focus on core DeepResearch API use cases, agent parameters, and step-by-step workflows. - Added `scripts/deepresearch.py` for end-to-end skill execution using standard library and requests. - Added detailed API and workflow references in `references/api.md` and `references/workflow.md`. - Removed legacy entry points (`scripts/deepresearch_conversation.py`, `_meta.json`). - Dependencies expanded to include `requests` library.

- No changes detected in this version. - Functionality and documentation remain consistent with previous release.

- No file changes detected in this release. - Version number incremented to 1.1.1; functionality remains unchanged.

- Added comprehensive documentation detailing multi-round deep research conversation workflow and API usage. - Introduced two workflow paths: topic discussion with and without file attachments. - Described all available APIs, required parameters, supported file formats, and streaming interaction rules. - Clarified response handling with conversation IDs, outline confirmation, and iterative query cycles. - Outlined shell command examples for each API endpoint.

**Summary: Improved skill documentation, added usability notes, and clarified API workflow.** - SKILL.md rewritten for clarity and concise step-by-step workflows, with separate paths for discussions with or without file upload. - All API endpoint descriptions and example shell commands standardized and formatted for easier copy/paste. - File parameter constraints and supported formats made clearer in documentation. - Instructions for multi-round conversations clarified, including use of `conversation_id`, `interrupt_id`, and `structured_outline`. - Documentation now explains that the API key is loaded automatically from configuration—no manual setup required.

deepresearch-conversation 1.0.4 - Updated requirements to specify "python3" instead of "python" for compatibility. - Minor metadata improvements in SKILL.md to clarify environment setup.

- Added the X-Appbuilder-From: openclaw header to all API curl examples in SKILL.md for better integration tracking. - Updated the documented curl commands across ConversationCreate, FileUpload, FileParseSumbit, and FileParseQuery APIs to include the new header. - No changes in functionality or core logic; documentation updates only.

- Updated required environment variable from apiKey to BAIDU_API_KEY for consistency. - Adjusted all documentation and example commands to reference BAIDU_API_KEY. - No functional changes to API or workflow; documentation and configuration improvements only.

- Updated required environment variable from BAIDU_API_KEY to apiKey for better consistency. - Adjusted API documentation, replacing all BAIDU_API_KEY references with apiKey in endpoint examples. - Added _meta.json file. - Minor clarifications and cleanups throughout SKILL.md for better usability.

Initial release of deepresearch-conversation. - Introduces multi-round streaming conversation with Baidu "Deep Research" agents for in-depth, iterative discussions. - Supports file upload, parsing, and integration into research dialogue. - Provides a detailed workflow for starting and continuing conversations, including error and session handling. - Lists APIs for creating conversations, uploading and parsing files, querying parsing status, and conducting deep research interactions. - Requires BAIDU_API_KEY and appropriate environment setup.