Resolve Issue #60 - #61
Merged
Merged
Conversation
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| 0, | ||
| min(100, round(remaining_int * 100 / capacity_int)), | ||
| ) | ||
| except (TypeError, ValueError): |
| from shared.core.database import get_db_context | ||
| from shared.services.retrieval.agentic.budget import BudgetLedger | ||
| from shared.services.retrieval.agentic.orchestrator import RetrievalAgent | ||
| from shared.services.retrieval.agentic.orchestrator import RetrievalAgent, _load_budget_inventory |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #60
This PR addresses the issue of agentic retrieval failing abruptly on complex queries due to token exhaustion. We've implemented the following features:
attempt_answerbefore finalizing the context payload. It now projects the required context tokens accurately, ensuring the prompt will fit within limits without silently failing.collect_all_paths) to correctly exclude paths during discovery, preventing duplicate rendering of L3 structural nodes.NOT_FOUND, making it easier for users to diagnose query mismatch.These changes significantly improve the reliability of the system under heavy token loads.