Skip to content

feat(dataset-updater): Fallacies PT register polish task (#411) - #447

Merged
jsboige merged 1 commit into
masterfrom
fix/411-fallacies-pt-register-dataset-updater
Jun 7, 2026
Merged

feat(dataset-updater): Fallacies PT register polish task (#411)#447
jsboige merged 1 commit into
masterfrom
fix/411-fallacies-pt-register-dataset-updater

Conversation

@jsboige

@jsboige jsboige commented Jun 7, 2026

Copy link
Copy Markdown
Contributor

Summary

Add DatasetUpdaterConfig entry for Fallacies taxonomy PT register harmonization — the last of the 3 datasets (Virtues ✅, Scenarii ✅, Fallacies 🔜).

Changes

  • New task "Fallacies cosmetic polish PT register gpt-5.5" in DatasetUpdaterRootConfig.cs (lines 2587-2635)
  • Fields: text_pt, desc_pt, example_pt (3 PT text columns to polish)
  • Context fields: path, text_fr, text_en (for LLM reference)
  • Enabled = false — requires manual activation + OpenAI API key

Pattern

Exact same config as existing Virtues/Scenarii PT register tasks:

  • Model: gpt-5.5
  • SequentialChunks with ChunkSize = 6
  • Function calling enabled (UpdateRecord tool)
  • AutoCompare = true
  • Reuses existing prompt files: PromptCosmeticPolishPtRegisterUser.txt / Assistant.txt

Validation

  • dotnet build — 0 errors
  • dotnet test — 151 pass, 0 fail, 5 skip
  • ✅ Follows existing Virtues/Scenarii pattern exactly

Related

Post-merge

jsboige needs to:

  1. Set Enabled = true
  2. Ensure API key path resolves
  3. Run smoke test on small sample (e.g., SkipChunkNb = 0, TakeChunkNb = 2)
  4. Review AutoCompare output before full run

Add DatasetUpdater config for Fallacies taxonomy PT register harmonization.
Matches existing Virtues/Scenarii PT register task pattern:
- Fields: text_pt, desc_pt, example_pt
- Model: gpt-5.5, SequentialChunks (6), function calling
- Enabled = false (requires manual activation + API key)

Part of #411 Cat B — i18n cosmetic polish via DatasetUpdater.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

@clusterManager-Myia clusterManager-Myia left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[NanoClaw]

Straightforward config addition. Verified against the two existing PT register tasks (Virtues, Scenarii) and the broader Fallacies dataset config block.

Checks passed:

  • Pattern is a 1:1 copy of the Virtues/Scenarii PT register entries -- same model, chunk size, tokens, function calling, compare mode, prompt paths, all structural params
  • SourceDataset = KnownDataSets.FallaciesTaxonomy -- consistent with 11 other Fallacies tasks in the file
  • Field names (text_pt, desc_pt, example_pt) match the established Fallacies PT columns (lines 350-432 in master)
  • Context fields (path, text_fr, text_en) match every other Fallacies task
  • TargetPath = Argumentum Fallacies - Taxonomy.csv -- matches all Fallacies tasks
  • Enabled = false -- safe default, won't run without explicit activation
  • Prompt files (PromptCosmeticPolishPtRegisterUser.txt / Assistant.txt) are shared across all 3 PT register tasks, already in place
  • No credentials, no hardcoded secrets, no injection risk
  • 1 file, +49 lines, zero deletions -- minimal blast radius

No issues found. Ready to merge.

@jsboige
jsboige merged commit dc01445 into master Jun 7, 2026
3 checks passed
@jsboige
jsboige deleted the fix/411-fallacies-pt-register-dataset-updater branch June 7, 2026 05:21
jsboige added a commit that referenced this pull request Jun 7, 2026
…447)

Add DatasetUpdater config for Fallacies taxonomy PT register harmonization.
Matches existing Virtues/Scenarii PT register task pattern:
- Fields: text_pt, desc_pt, example_pt
- Model: gpt-5.5, SequentialChunks (6), function calling
- Enabled = false (requires manual activation + API key)

Part of #411 Cat B — i18n cosmetic polish via DatasetUpdater.

Co-authored-by: Your <your.email@example.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
jsboige added a commit that referenced this pull request Jun 15, 2026
…α resubmit) (#484)

Re-submit the α deliverable from #444 (closed stale) as a clean doc-only PR.
The original #444 bundled α (this assessment) + β (Memo Back loc fix = #446)
+ γ (gpt-5.5 PT task = #447). β and γ are already on master; γ additionally
carried a parasite gpt-5.5→5.4-mini downgrade on 12 sites (avoided). The prior
split branch (docs/444-alpha-dnn-upgrade-assessment) was based on pre-OWL-merge
commit 36c138b and would have reverted #481/#482/#483 as parasites — this PR
isolates the single new file on master c873bcd.

Related: #131 (DNN security/upgrade), #132 (DNN deployment), #134 (release v0.9.0).
Supersedes: #444 (closed stale; β=#446, γ=#447 already merged).

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants