Uh oh!
There was an error while loading. Please reload this page.
fix: compress lever payload and batch FocusOnVitalFewLeversTask - #134
Closed
82deutschmark wants to merge 2 commits into
Closed
fix: compress lever payload and batch FocusOnVitalFewLeversTask#13482deutschmark wants to merge 2 commits into
82deutschmark wants to merge 2 commits into
Conversation
82deutschmark
commented
Mar 6, 2026
CollaboratorAuthor
Closing per Simon's feedback. The compress_lever() approach strips review/consequences fields, losing context the LLM needs for quality assessment. Replacement PR incoming: try full levers first, only fall back to batched+compressed on failure. |
82deutschmark added a commit
to VoynichLabs/PlanExe2026
that referenced
this pull request
Mar 6, 2026
FocusOnVitalFewLeversTask now attempts a single LLM call with all enriched lever fields (review, consequences, options, etc.) first. Only if that fails (context overflow, HTTP 400, parse error) does it fall back to batched processing with compressed levers. This preserves full context for cloud models and large-context local models while maintaining compatibility with smaller context windows. Replaces the always-compress approach from PR PlanExeOrg#134 (closed).
82deutschmark added a commit
to VoynichLabs/PlanExe2026
that referenced
this pull request
Mar 6, 2026
FocusOnVitalFewLeversTask now attempts a single LLM call with all enriched lever fields (review, consequences, options, etc.) first. Only if that fails (context overflow, HTTP 400, parse error) does it fall back to batched processing with compressed levers. This preserves full context for cloud models and large-context local models while maintaining compatibility with smaller context windows. Replaces the always-compress approach from PR PlanExeOrg#134 (closed).
82deutschmark added a commit
to VoynichLabs/PlanExe2026
that referenced
this pull request
Mar 6, 2026
FocusOnVitalFewLeversTask now attempts a single LLM call with all enriched lever fields (review, consequences, options, etc.) first. Only if that fails (context overflow, HTTP 400, parse error) does it fall back to batched processing with compressed levers. This preserves full context for cloud models and large-context local models while maintaining compatibility with smaller context windows. Replaces the always-compress approach from PR PlanExeOrg#134 (closed).
82deutschmark added a commit
to VoynichLabs/PlanExe2026
that referenced
this pull request
Mar 6, 2026
FocusOnVitalFewLeversTask now attempts a single LLM call with all enriched lever fields (review, consequences, options, etc.) first. Only if that fails (context overflow, HTTP 400, parse error) does it fall back to batched processing with compressed levers. This preserves full context for cloud models and large-context local models while maintaining compatibility with smaller context windows. Replaces the always-compress approach from PR PlanExeOrg#134 (closed).
82deutschmark added a commit
to VoynichLabs/PlanExe2026
that referenced
this pull request
Mar 6, 2026
FocusOnVitalFewLeversTask now attempts a single LLM call with all enriched lever fields (review, consequences, options, etc.) first. Only if that fails (context overflow, HTTP 400, parse error) does it fall back to batched processing with compressed levers. This preserves full context for cloud models and large-context local models while maintaining compatibility with smaller context windows. Replaces the always-compress approach from PR PlanExeOrg#134 (closed).
82deutschmark added a commit
to VoynichLabs/PlanExe2026
that referenced
this pull request
Mar 6, 2026
FocusOnVitalFewLeversTask now attempts a single LLM call with all enriched lever fields (review, consequences, options, etc.) first. Only if that fails (context overflow, HTTP 400, parse error) does it fall back to batched processing with compressed levers. This preserves full context for cloud models and large-context local models while maintaining compatibility with smaller context windows. Replaces the always-compress approach from PR PlanExeOrg#134 (closed).
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 freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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.
Compresses enriched-lever JSON to only the 5 fields consumed by the task (lever_id, name, description, synergy_text, conflict_text), makes optional fields Optional, and processes levers in batches of 4 with graceful retries to avoid context limit errors.