docs(readme): the diary sections become key points - #27
Merged
Conversation
'What we measured' (86 lines), 'Hybrid Loading' (44), and 'Session Resilience' (79) had grown into developer diaries — correction sagas, version-by-version narratives, instrument-bug war stories. Users need the key points; the full story already lives in docs/eval-baseline.md and is linked. Rewritten to ~70 lines total (README 1053 -> 914) keeping every honest number and claim: test-first 3/3 vs 0/3 because it's a hook; prose ties bare at ~1.6x; multi-session ties at a few times the cost (resume ~4x published, being cut); the three loading layers + the 177-line budget; resume via the generated brief + authority order, determinism not correctness as the edge. Nothing measured was dropped — only the journey to it.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The three sections the README grew during the measurement program — What we measured (86 lines), Hybrid Loading (44), Session Resilience (79) — read as developer diaries: correction sagas, version-by-version narratives, instrument-bug war stories. Users need the key points; the full story lives in
docs/eval-baseline.mdand stays linked.209 lines → ~70 (README 1053 → 914), keeping every honest number and claim:
Nothing measured was dropped — only the journey to it. Docs-only; truth-table + context-budget validators green; the
#what-we-measuredanchor still resolves.