Skip to content

Staging - #396

Merged
suguanYang merged 18 commits into
stagingfrom
main
Sep 8, 2026
Merged

Staging#396
suguanYang merged 18 commits into
stagingfrom
main

Conversation

@suguanYang

Copy link
Copy Markdown
Contributor

No description provided.

suguanYang and others added 13 commits September 8, 2026 16:21
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Added constants for body chunk types that can own Root-parked assets in the serving manifest and navigation modules. Updated relevant logic to utilize these constants for improved clarity and maintainability. Enhanced documentation in the CORPUS_SCHEMA to reflect the ownership rules of body chunks.
Updated the README to reflect the new Knowhere 2.0 branding. Enhanced the retrieval server by integrating corpus tools for improved functionality and backward compatibility. Introduced a character budget for evidence text across various tools, ensuring consistent output limits. Refactored agent tools to utilize shared snippet building logic, improving code maintainability and reducing duplication. Added support for a new agentic routing mechanism to facilitate exploration through the agent_explore path.
Enhanced the agent exploration logic by implementing a two-phase fix for stale tool-message collapsing, ensuring efficient message management across turns. Introduced a fallback mechanism for trajectory references, allowing the system to utilize previously read content when no current references are available. Updated documentation to clarify the requirements for `refs` when calling `{FINISH_TOOL_NAME}` and refined the handling of tool messages to prevent unnecessary resends, optimizing performance and clarity in the exploration process.
Added support for the Cursor SDK as an alternative harness for agent exploration. Introduced a new optional dependency, `cursor-sdk`, and updated the agent exploration logic to allow switching between OpenAI-compatible and Cursor SDK providers. Enhanced the `debug_agent_explore_episode` script to accept a `--harness` argument for selecting the desired harness. Updated relevant documentation and configuration to reflect these changes, ensuring clarity on the new harness integration.
…ath resolution

Updated the agent exploration logic to include a budget status line in tool observations, allowing the model to self-regulate based on remaining budget. Improved section path resolution by integrating a new method for handling ambiguous paths and ensuring accurate references during retrieval. Enhanced documentation to clarify the behavior of the `read` tool regarding section paths and added notes for better guidance on recall tool usage.
Archive map-nav out of the live path, keep shared scoring for classic
BM25 and corpus.recall, drop the FTS fallback and unused chunk
tsvector columns, and use cursor_sdk unless use_agentic is false.

Co-authored-by: Cursor <cursoragent@cursor.com>
feat(retrieval): default to agent explore and retire map-nav
Comment thread apps/worker/scripts/run_agentic_router_eval.py Fixed
Comment thread apps/worker/scripts/run_agentic_router_eval.py Fixed
Comment thread apps/api/app/mcp/dynamic_tools.py Fixed
suguanYang and others added 3 commits September 8, 2026 21:30
…atenation in a list'

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
…tiple times'

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Addresses the remaining code-scanning comments from the main->staging PR
#396 (alerts 417-419 were already fixed on main by b6a95a8/7a0a51b8):

- harness/base.py: replace the ineffectual "..." ellipsis placeholder in
  the Harness Protocol with "raise NotImplementedError", matching the
  convention used by other Protocols in this repo (CodeQL: statement has
  no effect).
- agent_tools/__init__.py: perform the tools side-effect import (which
  registers every corpus.* tool via @register_tool) here, so any consumer
  importing a name from this package is guaranteed a fully populated
  REGISTRY; list "_tools" in __all__ as a deliberate re-export.
- drop the now-redundant per-consumer side-effect imports of
  "agent_tools.tools" in dynamic_tools.py, cursor_harness.py, and
  openai_harness.py (CodeQL: unused import). Removing them outright would
  have broken tool registration - REGISTRY.all() would be empty.
@suguanYang
suguanYang merged commit 5b2afc2 into staging Sep 8, 2026
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants