Repository navigation
Save verified native quality defaults and acceptance practice - #35
Merged
Merged
Conversation
9 of 22 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Native Linux Codex had no saved reasoning-effort override while Desktop already used
ultra. This handbook now records the verified nativegpt-6-astra/ultradefault and Claude's supported persistentxhighdefault, with portable instructions for applying them on another PC.The shared quality rule ties completion to the requested outcome, upstream or project checks, source inspection and independent review for substantive changes. Existing accounts, models, permissions, hooks and scoped integrations are preserved. New sessions inherit saved settings; existing sessions may retain their current selection.
Evidence includes the installed native model catalog, Claude's exact persisted-settings schema, native doctor output, and safe official SDK
config/readoutput for both Codex homes. The new instruction paragraph costs 60 additional tokens per frozen instruction artifact; this is not a savings or quality benchmark. No model turns were run for this configuration wave.Validation: 50 focused catalog/lifecycle tests passed, repository integrity validation passed (68 components, 105 receipts), deterministic HTML rebuild passed, and whitespace checks passed. Independent review verified settings preservation, output hashes, schema evidence and instruction token recounts with no remaining findings. Claude doctor retains the documented intentional embedding-prefix whitespace warning. Desktop's pre-existing setting was read back; no before-copy was retained for an independent byte comparison.