electron-rare/ai-novel-engine
1
0
Fork 0
Code Issues 3 Pull Requests Actions Packages Projects Releases Wiki Activity
15 Commits 1 Branch 0 Tags
main
Commit Graph

15 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
L'électron rare 5b052a8f70 feat(runtime): add orchestration, tracking, and ops tooling 2026-04-06 11:49:28 +02:00
L'électron rare a1a4fe92a0 docs(product): refresh writing assistance positioning 2026-04-06 11:43:48 +02:00
L'électron rare 62fe2b0943 feat(pipeline): per-model prompt profiles + mistral-nemo v2 variant wired end-to-end 
- PromptStore.render() accepts prompt_profile with fallback to v1
- GenerationPipeline passes prompt_profile to rewrite + repair stages
- cli/main.py reads ANE_PROMPT_PROFILE from env
- next_lots.py reads [prompt_profiles] from TOML, injects into smoke env
- Config: "ollama:mistral-nemo:latest" = "v2_nemo"
- v2_nemo prompts: less directive on closure, natural scene endings
- 156 tests pass

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 17:01:30 +01:00
L'électron rare 3af51d39ed feat(prompts): mistral-nemo variant + prompt_profile support in PromptStore 
- Add rewrite_v2_nemo.txt: less directive on scene closure, natural endings
- Add repair_v2_nemo.txt: same approach, avoids mechanical conclusion formulas
- PromptStore.render() now accepts prompt_profile kwarg with fallback to v1
- Config: [prompt_profiles] maps model to profile (e.g. mistral-nemo -> v2_nemo)
- Mark qwen2.5:7b as accepted baseline Ollama via Mascarade P2P
- Close 3 P0 TODOs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 16:55:47 +01:00
L'électron rare 0ae40f44e3 fix(lots): reorder — Mistral first, Ollama P2P second, Apple local last 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 16:46:45 +01:00
L'électron rare 290ead874d feat(runtime): route all via Mascarade + Qwen3-4B ref + Mistral cloud 
- Route everything through Mascarade :8100 (Mistral API, Apple CoreML, Ollama P2P)
- New local ref: qwen3-4b-instruct-2507-q4f16 (3x faster than previous)
- Add mistral:mistral-large-latest to priority_models and french_models
- Point ollama_openai_base_url to Mascarade instead of llama-server :8091
- Update auto-sync with current model status

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-23 16:45:31 +01:00
L'électron rare 5e63ceb782 Refactor rewrite prompt and update tests for narrative generation 
- Updated the rewrite prompt to remove markdown elements such as titles, bullet points, and code fences, ensuring a cleaner narrative output.
- Enhanced the GenerationPipeline tests to verify that code fences and chapter titles are stripped before manuscript promotion.
- Adjusted NextLots tests to include new functionality for command runners and added tests for deduplication of headings and timeout handling.
- Introduced new documentation files detailing project context and execution plans for March 2026, outlining current project status and objectives.
- Added operational memory documents to summarize project state and decisions for resuming work on the ai-novel-engine.
 2026-03-16 06:03:24 +01:00
L'électron rare 7f53fe3bcf refactor: nettoyer le .gitignore et supprimer des fichiers inutilisés 2026-03-16 06:03:09 +01:00
L'électron rare f7678514db fix(novel-engine): add missing modules, path validation, .gitignore 
- Add cli/__init__.py, core/__init__.py for proper Python packaging
- Create core/project/ with loader.py stub (ProjectState class)
- Sanitize chapter input against path traversal in cmd_intention_create
- Add .gitignore with standard Python ignores

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 06:15:20 +01:00
L'électron rare 85d966508c chore(gen): stage local generation workflow 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 00:04:43 +01:00
L'électron rare 1a3816d0c8 Implement local generation workflow and automation 2026-03-09 09:22:27 +01:00
Clément SAILLANT 19a3c25c77 Create my-agent.agent.md template 
Add template for custom agent configuration
 2026-02-01 01:14:38 +01:00
CILS 871d898bdc feat(cli): status, intention create and write command with intention gate 2026-02-01 01:05:42 +01:00
CILS 37969edf64 feat(core): add intention gate and CLI intention create command 2026-02-01 00:58:23 +01:00
CILS 0bc8d8c6a1 feat: initialisation du projet ai-novel-engine (v2 ready) 2026-02-01 00:35:08 +01:00