chore: sync main into staging (agentic per-doc cap + doc-agent) - #250
Open
EricNGOntos wants to merge 11 commits into
Open
chore: sync main into staging (agentic per-doc cap + doc-agent)#250EricNGOntos wants to merge 11 commits into
EricNGOntos wants to merge 11 commits into
Conversation
#236) When last_context (the preceding markdown text) is very long, the generated image filename exceeds the OS 255-byte limit and os.rename fails with OSError ENAMETOOLONG. Truncate to 60 chars after sanitization.
* fix: share one 80-char cap for image and table asset filenames Unify the post-#236 image context truncate with table header naming so cosmetic asset stems use a single MAX_ASSET_FILE_NAME_CHARS constant. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: handle None from path_handle before truncating image titles Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>
Dashboard still sends result_mode in job creation requests but the API removed it. Add to _PUBLIC_COMPATIBILITY_EXTRA_FIELDS so it's silently ignored instead of rejecting the whole request with 400.
- Added DOC_PROFILE_FILENAME to persist anatomy map artifacts for better debugging. - Updated hierarchy_locator to retain original TOC headings while normalizing titles. - Introduced TOC_VLM_MAX_TOKENS for consistent token limits in VLM calls. - Refactored rendering logic in extract_toc_with_boundaries to handle multiple pages. - Improved evidence extraction from confirmation items in VLM processing. - Adjusted zip package writer to conditionally include TOC hierarchies based on parse track.
- Removed the obsolete 'verdict_now' action, consolidating decision-making under 'tool_call'. - Updated prompts and instructions to clarify the executor's role in handling actions and verdicts. - Enhanced the handling of legacy actions to ensure compatibility with the new decision structure. - Refactored the logic in the executor to enforce 'tool_call' as the only valid action, improving clarity and maintainability. - Adjusted the planner's behavior to treat 'verdict_now' as a non-finish signal, delegating success/abort handling to the executor.
refactor: document-agent profile protocol and TOC boundary tools
Replace chunk-weighted per-doc min shares with a flat per-doc cap, and grow planning/context plus wallet totals after document selection so spendable budget tracks the selected set. Co-authored-by: Cursor <cursoragent@cursor.com>
refactor: scale agentic budget by flat per-doc caps
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| ) | ||
| from app.services.document_agent.planner.planner import _parse_profile_and_decision | ||
| from app.services.document_agent.registry import REGISTRY | ||
| from app.services.document_agent import tools as _registered_tools # noqa: F401 |
Classic path/content channels loaded the full scoped corpus into Python before BM25. Prefetch via simple FTS (server-side OR tsquery), apply section exclusions before the candidate LIMIT, and fall back to a full scan when FTS matches nothing so recall does not regress. Combines the approaches from #244 and #251; closes #195. Co-authored-by: Ray Tien <ray.tien0907@gmail.com> Co-authored-by: nuemaan <anonnumaan@gmail.com> Co-authored-by: Cursor <cursoragent@cursor.com>
* refactor: update retrieval architecture and agentic mode handling - Reorganized the retrieval flowchart to enhance clarity and structure. - Introduced new retrieval modes: classic top-K and map-nav, with clear descriptions for each. - Updated the `use_agentic` parameter to default to map-nav, simplifying user experience. - Removed legacy agentic components and related tests to streamline the codebase. - Adjusted documentation to reflect changes in retrieval modes and internal structures. * perf: bound classic BM25 candidates with Postgres FTS Classic path/content channels loaded the full scoped corpus into Python before BM25. Prefetch via simple FTS (server-side OR tsquery), apply section exclusions before the candidate LIMIT, and fall back to a full scan when FTS matches nothing so recall does not regress. Combines the approaches from #244 and #251; closes #195. Co-authored-by: Ray Tien <ray.tien0907@gmail.com> Co-authored-by: nuemaan <anonnumaan@gmail.com> Co-authored-by: Cursor <cursoragent@cursor.com> * fix: green CI for mapnav PR (lint, pyright, demo classic path) Exclude vendored nav/ from pyright, tighten mapnav plan typing, and force demo contract retrieval onto classic so CI does not hit a live LLM. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Ray Tien <ray.tien0907@gmail.com> Co-authored-by: nuemaan <anonnumaan@gmail.com> Co-authored-by: Cursor <cursoragent@cursor.com>
|
|
||
| # Back-compat aliases for tests / callers. | ||
| _evidence_owner_section_id = evidence_owner_section_id | ||
| _unit_score_for_evidence_chunk = unit_score_for_evidence_chunk |
|
|
||
|
|
||
| # Back-compat name used by older tests; prefer _mark_collected_branch. | ||
| _update_collect_coverage = _mark_collected_branch |
| result = json.loads(text) | ||
| if isinstance(result, list): | ||
| return [str(item) for item in result if str(item) in valid_ids] | ||
| except (ValueError, json.JSONDecodeError): |
| result = json.loads(fence_match.group(1).strip()) | ||
| if isinstance(result, list): | ||
| return [str(item) for item in result if str(item) in valid_ids] | ||
| except (ValueError, json.JSONDecodeError): |
| result = json.loads(bracket_match.group()) | ||
| if isinstance(result, list): | ||
| return [str(item) for item in result if str(item) in valid_ids] | ||
| except (ValueError, json.JSONDecodeError): |
|
|
||
| def roots(self, doc_id: str) -> Sequence[str]: | ||
| """Top-level section ids for a document (or corpus root).""" | ||
| ... |
|
|
||
| def children(self, section_id: str) -> Sequence[str]: | ||
| """Direct child section ids, in document order.""" | ||
| ... |
|
|
||
| def node_meta(self, section_id: str) -> NodeMeta: | ||
| """Title/summary/chunk-count/has_children for one node.""" | ||
| ... |
|
|
||
| def relations(self, section_id: str) -> Tuple[Set[str], Set[str]]: | ||
| """(ancestor_ids, descendant_ids); section_id itself excluded from both.""" | ||
| ... |
|
|
||
| def content(self, section_id: str) -> str: | ||
| """Full text for this node's subtree, as one evidence unit.""" | ||
| ... |
…c leftovers (#254) Fall back to provider structure summaries when the section store is absent, make map_mode config-authoritative, and remove unused llm_adapter/old mocks. Co-authored-by: Cursor <cursoragent@cursor.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
mainintostagingsoapi-staging(used by notebook.staging) picks up recent retrieval/parser work.per_doc_capagentic budget and PR refactor: document-agent profile protocol and TOC boundary tools #246 document-agent/TOC updates, plus related filename/result_modefixes already onmain.Why
Staging Notebook (
https://notebook.staging.knowhereto.ai/) talks tohttps://api-staging.knowhereto.ai, which currently still runs03374ffe(2026-08-03) and does not include #248/#246.Test plan
GET https://api-staging.knowhereto.ai/v1/versionshows a commit containing refactor: scale agentic budget by flat per-doc caps #248 (66fe1b0for descendant)Made with Cursor