docs: task complexity scoring + model routing proposal (post-mortem + rubric)#102
Merged
neoneye merged 2 commits intoPlanExeOrg:mainfrom Feb 27, 2026
Merged
Conversation
added 2 commits
February 26, 2026 23:21
- Post-mortem of Simon's 26 Feb 2026 refactor with realistic cost estimates (~$18) - Three independent complexity assessments (Sonnet/Haiku/Minimax perspectives) - Proposal 73: task complexity scoring + model routing for PlanExe - For Simon's calibration review
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Post-mortem of Simon's 26 Feb 2026 refactor + a proposal for adding task complexity scoring and model routing to PlanExe.
What's in this PR (docs-only, no code changes)
71-model-routing-postmortem-simon-26feb2026.mdAnalysis of Simon's day (64 commits, 108 files, ~15K lines). Corrected cost estimate: ~$18 total at Opus. Identifies where Haiku/Minimax could have handled execution after an Opus planning pass.
72-complexity-assessment-*.md(3 files)Three independent complexity assessments of the same 8 task clusters — one from each model perspective (Sonnet 4.6, Haiku 4.5, Minimax M2.5). Written independently, designed to show how different model tiers assess the same work.
73-task-complexity-routing.mdThe core proposal: PlanExe should score each task it generates on a 4-dimension Likert rubric (file size, semantic complexity, ambiguity, context dependency) and route tasks to the appropriate model tier for execution.
For Simon's Review
The three complexity assessments need your calibration. Questions embedded in each doc:
This is the first real calibration dataset for the routing rubric. Your feedback drives the next iteration.
Authors
Larry (Sonnet 4.6) — primary author
Egon (Minimax M2.5) — Minimax perspective
Bubba (Haiku 4.5) — Haiku perspective
Authorized by: Mark Barney