chore(dataset-updater): migrate to GPT-5.x models - #222
Merged
Conversation
Migrate all 7 DatasetUpdater task configs + default model from gpt-4.1/gpt-4.1-mini to GPT-5.x family, tiered by task nature: - Translation empty-only (FR→EN, FR→RU, FR→PT): gpt-5.4-mini (eco tier) - Taxonomy/description refinement (Virtues, desc_fr, example_fr): gpt-5.4 (quality tier) - Multi-lang cleanup review: gpt-5.4 (quality tier for nuanced comparisons) - Default fallback (DatasetUpdaterConfig.Model): gpt-5.4-mini Fallback to gpt-4.1 series documented inline for each entry for quick rollback if a GPT-5.x model is unavailable. Unblocks downstream work on: - #211 (PT Rules retranslation) - #218 (Virtues i18n population) - #219 (Scenarii EN/RU/PT completion) All task entries remain Enabled=false except the Cleanup entry (Enabled=true, but DatasetUpdater mode itself is off by default in AssetConverterConfig.Mode). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
4 tasks
This was referenced Apr 24, 2026
jsboige
added a commit
that referenced
this pull request
Apr 24, 2026
Adds 3 DatasetUpdaterConfig entries (Enabled=false) for translating the 76 untranslated scenarios per target language (EN/RU/PT) via OpenAI GPT-5.4-mini, plus 6 Scenarii-specific prompt files (User + Assistant x 3 languages). Audit (167 total FR-complete scenarios): - EN: 85 scenarios missing ≥1 field (category, subcategory, title, smoothTalker, drawer, context, issue, suggestion_en) - RU: 76 scenarios missing _ru fields - PT: 76 scenarios missing _pt fields Config pattern mirrors #231 (Virtues): SequentialChunks, ChunkSize=8, SelectEmptyTargets=true, MaxGroupItemNb=12, UseFunctionCalling=true. Each config uses a dedicated prompt pair tailored to scenario context: - Scenarii-specific field mapping (catégorie→category, baratineur→smoothTalker, piocheur→drawer, enjeu→issue, suggestion→suggestion_en — only one with suffix) - Narrative-tone instructions (rhythm, humor, brevity) - pt-PT (not pt-BR); Russian contemporary register (not archaic) - Category/subcategory consistency across scenarios - Measured adaptation of French cultural references Prerequisites satisfied: SDK migration #183 (PR #210) + GPT-5.x models (PR #222). Scenario.cs entity already had complete i18n scaffolding (EN without _en suffix is historical design; RU/PT use suffix). Build: 0 errors, 17 warnings (pre-existing). Tests: 88 pass, 1 skip (Freeplane GUI), 0 fail. Closes #219 (pending successful end-to-end run with OpenAI key). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Collaborator
|
Post-hoc review — PR #222 Verdict: ✅ LGTM Clean model migration across 7 DatasetUpdater task configs. The tiered approach is well-reasoned:
Observations:
No schema changes, no data changes. Safe migration. |
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
gpt-4.1/gpt-4.1-mini→ GPT-5.x familygpt-5.4-mini, taxonomy/description refinement + multi-lang cleanup usesgpt-5.4gpt-4.1series for quick rollbackContext
po-2023 updated
OpenAI-Key.txt(hors-repo) with a new project key that grants access to GPT-5.x models (gpt-5,gpt-5.1,gpt-5.2,gpt-5.3,gpt-5.4,gpt-5.4-pro,gpt-5.4-mini,gpt-5.4-nano,o3,o3-pro,o4-mini). This PR unblocks downstream translation work that was waiting on SOTA models.Tier mapping
gpt-5.4-minigpt-5.4desc_frsimplificationgpt-5.4example_frcreative generationgpt-5.4gpt-5.4DatasetUpdaterConfig.Model)gpt-5.4-miniSafety
DatasetUpdateris not in defaultAssetConverterConfig.Mode— opt-in onlyEnabled=falseexcept the Cleanup entry (pre-existing state, untouched)Model =lineUnblocks
Test plan
gpt-5.4-miniunavailable (rate-limit/access), revert togpt-4.1-miniper inline commentsRelated: #183, #205, #210 (SDK upgrade), #211, #218, #219
🤖 Generated with Claude Code