feat(dataset-updater): migrate to official OpenAI .NET SDK (#183) - #210
Merged
Conversation
… .NET SDK v2.10.0 (#183) Replace Betalgo.OpenAI v8.1.0 + Betalgo.OpenAI.Utilities with the official OpenAI .NET SDK (v2.10.0). Rewrite Prompt.cs to use OpenAIClient/ChatClient, replace FunctionCallingHelper with manual FunctionToolDef, and update all model references from deprecated constants to current model strings. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Contributor
Author
Review — PR #210 SDK Migration (#183)Verdict structurel : LGTM ✅ (runtime validation à confirmer par test manuel DatasetUpdater) Ce qui fonctionne bien
Points d'attention (non-bloquants)
Runtime check manquantLe test plan mentionne correctement : "Manual test: run DatasetUpdater with Enabled = true". Tant que ce test n'est pas passé (nécessite
Impact avalCette PR débloque :
Prêt à merger après validation manuelle round-trip. 👍 |
This was referenced Apr 22, 2026
Review fix on PR #210: - Add #nullable enable at top of Prompt.cs — nullable annotations (`?`, `null!`) were present but produced CS8632 warnings outside a nullable context. Intent was already clear; just make it explicit. - Guard param.Name null check in CallFunction reflection — ParameterInfo.Name is declared nullable. Prevents CS8604 and handles the unlikely edge case of compiler-generated unnamed parameters defensively. Build: 55 -> 53 warnings, 0 errors. Tests: 43/44 pass unchanged. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This was referenced Apr 22, 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>
jsboige
added a commit
that referenced
this pull request
Jun 29, 2026
…sal (#609) Grounds #141 in the CURRENT taxonomy state (issue text is ~2 years old; DatasetUpdater + translation PRs have moved the state considerably). Census finding (read-only script on ba8e4a6, reproducible like #600/#606): - Non-card nodes: Fallacies 1232, Virtues 110 (Scenarii/Rules out of scope). - TEXT enrichment (desc/example/title x 8 langs) = 100% on both datasets => original #141 scope item 3 (descriptions + examples + translations) is DONE. No text-enrichment gap to script. - The "GPT-4 enrichment script" = already adapted: modern DatasetUpdater (PR #210, OpenAI SDK v2.10.0, gpt-5.5). Not a rewrite. Reframes #141: the genuinely-open residue is the AIF cross-reference graph (crossLink_* 8 relationship cols + AIF_skos* 4 SKOS mappings). Schema is READY (columns exist), content ~0% on non-cards: - Fallacies: crossLink 0.2%, AIF_skos 0.5% (barely started) - Virtues: crossLink_Opposes + skosDirectRef/MappingType 100% via #498 pilots, but 7 OTHER crossLink verbs = 0% - ~16700 empty cross-ref cells where schema is waiting. Proposal: 4-stage method (ground -> gpt-5.5 candidate via /v1/responses effort=low -> drift-free sidecar dry-run -> expert/jsboige ratification gate -> OWL/2sxc export). NOT auto-write: AIF/Walton mappings are specialised (memory: "Anti-Fab Validator: Walton scheme = WARN"), and Cards/ is frozen pre-tag. "Adapt the script" = add a crossLink prompt + task config to DatasetUpdater, GATED post-release on jsboige GO + schema decision (single decimal_path vs structured {target,note}). Overlaps #498 (AIF scale-up pilots produced the few filled cells). Feeds dependencies #141 declares: #130 (OWL/SKOS) + #136 (2sxc). Scope: docs + read-only script only. 0 write Cards/, 0 AssetConverter code change (pre-tag safe). Base ba8e4a6. Relates to #130, #136, #498. Co-authored-by: Your <your.email@example.com> Co-authored-by: Claude-Code <noreply@anthropic.com>
jsboige
added a commit
that referenced
this pull request
Jun 29, 2026
…or, 0 Cards/) (#610) * docs(taxonomy): #141 non-card census + AIF cross-ref enrichment proposal Grounds #141 in the CURRENT taxonomy state (issue text is ~2 years old; DatasetUpdater + translation PRs have moved the state considerably). Census finding (read-only script on ba8e4a6, reproducible like #600/#606): - Non-card nodes: Fallacies 1232, Virtues 110 (Scenarii/Rules out of scope). - TEXT enrichment (desc/example/title x 8 langs) = 100% on both datasets => original #141 scope item 3 (descriptions + examples + translations) is DONE. No text-enrichment gap to script. - The "GPT-4 enrichment script" = already adapted: modern DatasetUpdater (PR #210, OpenAI SDK v2.10.0, gpt-5.5). Not a rewrite. Reframes #141: the genuinely-open residue is the AIF cross-reference graph (crossLink_* 8 relationship cols + AIF_skos* 4 SKOS mappings). Schema is READY (columns exist), content ~0% on non-cards: - Fallacies: crossLink 0.2%, AIF_skos 0.5% (barely started) - Virtues: crossLink_Opposes + skosDirectRef/MappingType 100% via #498 pilots, but 7 OTHER crossLink verbs = 0% - ~16700 empty cross-ref cells where schema is waiting. Proposal: 4-stage method (ground -> gpt-5.5 candidate via /v1/responses effort=low -> drift-free sidecar dry-run -> expert/jsboige ratification gate -> OWL/2sxc export). NOT auto-write: AIF/Walton mappings are specialised (memory: "Anti-Fab Validator: Walton scheme = WARN"), and Cards/ is frozen pre-tag. "Adapt the script" = add a crossLink prompt + task config to DatasetUpdater, GATED post-release on jsboige GO + schema decision (single decimal_path vs structured {target,note}). Overlaps #498 (AIF scale-up pilots produced the few filled cells). Feeds dependencies #141 declares: #130 (OWL/SKOS) + #136 (2sxc). Scope: docs + read-only script only. 0 write Cards/, 0 AssetConverter code change (pre-tag safe). Base ba8e4a6. Relates to #130, #136, #498. Co-Authored-By: Claude-Code <noreply@anthropic.com> * tools(i18n): link_* langlinks resolver (sidecar candidate-URL generator, 0 Cards/) SECONDAIRE of ai-01 deep-queue dispatch. Extends the #600/#606 coverage track from MEASUREMENT to RESOLUTION. The existing probe (docs/taxonomy/192-link-coverage-langlinks-probe.py) measures the resolvable ceiling (~2919 cells, 57%, #600 §5.1) but discards the target title (returns only lang codes). This tool captures the target-language title via the MediaWiki langlinks API and emits the candidate fill URLs as a sidecar report — step 1 of #600 §6 methodology. For every node with an en.wikipedia.org/wiki/<Title> link_en missing link_<lang>, queries langlinks, captures the target title, emits: dataset,key,link_lang,resolved_url to stdout or --out <path>. NEVER writes under Cards/. Verified on a strided sample of 10 fallacies: 0 errors, 37 candidate fills (~57% rate, consistent with the probe ceiling), URLs correctly URL-encoded (Cyrillic %D0, PT accented %C3). Sample also surfaced the homonym risk #600 §6.4 warns about (English "Engagement" for a fallacy node) -> confirms human spot-validation is non-optional for AR/FA/ZH. Safety: - 0 write Cards/ (sidecar only, pre-tag freeze). - Public MediaWiki API, no key, 0.3s throttle, descriptive UA (default urllib UA is 403-forbidden). - Resolves FROM link_en (Wikipedia only); 433 non-Wikipedia curated sources excluded + preserved as-is (#600 §6.2). Next (post-release, gated): follow-up PR consumes the sidecar -> apply candidate URLs cell-by-cell (drift-free QUOTE_MINIMAL+CRLF, method #595), skip non-empty cells, human spot-validate ~5% residue (AR/FA/ZH, ~150). Relates to #600, #606. Co-Authored-By: Claude-Code <noreply@anthropic.com> --------- Co-authored-by: Your <your.email@example.com> Co-authored-by: Claude-Code <noreply@anthropic.com>
20 tasks
jsboige
added a commit
that referenced
this pull request
Jul 22, 2026
…fort (#141) (#852) #141 re-scope (po-2024, ai-01 coordinator GO msg-q9uhmf). The DatasetUpdater translation loop called Chat Completions (CompleteChatAsync), which for reasoning models (gpt-5.x) burns the token budget on HIDDEN reasoning and returns EMPTY Content. The dashboard API metric documents the intended config ("gpt-5.5 /v1/responses, reasoning:{effort:low}") — the code contradicted it. Add an opt-in Responses-API (/v1/responses) path alongside CompleteChatAsync (reversible: default off). Plumbs reasoning effort (low) so gpt-5.x returns usable output within budget. Function-calling carried over (all gpt-5.5 tasks are UseFunctionCalling=true). Why #141 as written was superseded: the 91 non-card taxonomy nodes (depth 1-3) are 100% complete (desc_*+text_* x8 langs, 0 empty) and the SDK was already modernized (PR #210). The real residual gap was /v1/responses routing — generic across all 48 tasks, not non-card-specific. Changes: - Prompt.cs: UseResponsesApi + ReasoningEffort props; lazy ResponsesClient (shares the OpenAIClient); SendViaResponses (items via options.InputItems, reasoning effort, function tools + tool-choice, FunctionCallResponseItem processing, GetOutputText). #pragma disable OPENAI001 (OpenAI.Responses is [Experimental]). - DatasetUpdaterConfig.cs: UseResponsesApi + ReasoningEffort config (default off/null). - PromptResponsesApiTests.cs: ParseReasoningEffort mapping (case-insensitive, unknown->Low fallback, no throw) + Responses knobs default off (legacy preserved). Governance: DatasetUpdater stays Enabled=false (0 run live, 0 prod CSV — T&A freeze). Reversible code plumbing, 637/0/5 tests green. Coordinator decision, not gated jsboige. Relates #141 #498. Co-authored-by: Your <your.email@example.com> Co-authored-by: Claude-Code <noreply@anthropic.com>
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.
Summary
Betalgo.OpenAI v8.1.0+Betalgo.OpenAI.Utilities v8.0.1with the officialOpenAI v2.10.0NuGet packagePrompt.csto useOpenAIClient/ChatClient/ChatTool/BinaryDataAPIsFunctionCallingHelperauto-reflection with manualFunctionToolDefclass + JSON schemaModels.Gpt_*constants to current model strings (gpt-4.1,gpt-4.1-mini)FunctionDescriptionattribute fromRecordsUpdater.UpdateRecordTest plan
dotnet build— 0 errors (warnings are pre-existing)dotnet test— 42 pass, 1 fail (pre-existingSimpleImageGeneratorTestsJSON serialization issue), 1 skipEnabled = trueon a task config to verify API calls still workUpdateRecordcorrectlyCloses #183
🤖 Generated with Claude Code