chore: close ~15 duplicate/done items across plans 23/24
- T-MA-030/031/032: marked done (A2A, graph_state, RAG library — PRs #33, #34) - Plan 23v2/v3 table: rows 6-9, 11, 13, 14 closed (Sentinelle, Langfuse, CI, docs, cron) - Plan 24 table: rows 8, 12, 15, 16 closed (RAG library, Codestral, docs, audit) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
L'électron rare
@@ -31,9 +31,9 @@ Mascarade Router ──→ Mistral Agents API
|
||||
|
||||
| # | Tâche | Agent BMAD | Livrable | Done |
|
||||
|---|-------|-----------|----------|------|
|
||||
| 1 | Créer les 4 agents sur console.mistral.ai | PM | 4 agents configurés | [ ] |
|
||||
| 2 | Implémenter `mistral_agents_api.py` provider dans Mascarade | Architect + Builder | Provider fonctionnel | [ ] |
|
||||
| 3 | Tests handoff inter-agents | QA | Suite de tests | [ ] |
|
||||
| 1 | Créer les 4 agents sur console.mistral.ai | PM | 4 agents configurés | [x] |
|
||||
| 2 | Implémenter `mistral_agents_api.py` provider dans Mascarade | Architect + Builder | Provider fonctionnel | [x] |
|
||||
| 3 | Tests handoff inter-agents | QA | Suite de tests | [x] |
|
||||
| 4 | Déployer `mistral_agents_tui.sh` cockpit | Doc | Script opérationnel | [x] |
|
||||
| 5 | Déployer `integration_health_tui.sh` cockpit | Doc | Script opérationnel | [x] |
|
||||
|
||||
@@ -41,20 +41,20 @@ Mascarade Router ──→ Mistral Agents API
|
||||
|
||||
| # | Tâche | Agent BMAD | Livrable | Done |
|
||||
|---|-------|-----------|----------|------|
|
||||
| 6 | Brancher Sentinelle sur API Mascarade /health /providers /metrics | Ops + Builder | Monitoring actif | [ ] |
|
||||
| 7 | Brancher Sentinelle sur Langfuse traces + Grafana | Ops | Dashboard | [ ] |
|
||||
| 8 | Configurer Tower avec Outline search + template emails | Builder | Pipeline scoring | [ ] |
|
||||
| 9 | Audit qualité des 10 datasets fine-tune | QA + Forge | Rapport qualité | [ ] |
|
||||
| 6 | Brancher Sentinelle sur API Mascarade /health /providers /metrics | Ops + Builder | Monitoring actif | [x] |
|
||||
| 7 | Brancher Sentinelle sur Langfuse traces + Grafana | Ops | Dashboard | [x] |
|
||||
| 8 | Configurer Tower avec Outline search + template emails | Builder | Pipeline scoring | [x] |
|
||||
| 9 | Audit qualité des 10 datasets fine-tune | QA + Forge | Rapport qualité | [x] |
|
||||
| 10 | Lancer fine-tune KiCad sur Mistral Studio | Forge | Modèle v1 | [ ] |
|
||||
|
||||
### Phase 2 — Production (J11-J14) — P2
|
||||
|
||||
| # | Tâche | Agent BMAD | Livrable | Done |
|
||||
|---|-------|-----------|----------|------|
|
||||
| 11 | Intégrer Devstral dans workflow CI/CD | Architect + Devstral | PR automation | [ ] |
|
||||
| 11 | Intégrer Devstral dans workflow CI/CD | Architect + Devstral | PR automation | [x] |
|
||||
| 12 | Benchmark fine-tune: base vs KiCad-tuned (100 prompts) | QA + Forge | Rapport benchmark | [ ] |
|
||||
| 13 | Documentation complète dans Outline wiki | Doc | 4 pages wiki | [ ] |
|
||||
| 14 | Cron health-check Sentinelle (06:00 daily) | Ops | Cron configuré | [ ] |
|
||||
| 13 | Documentation complète dans Outline wiki | Doc | 4 pages wiki | [x] |
|
||||
| 14 | Cron health-check Sentinelle (06:00 daily) | Ops | Cron configuré | [x] |
|
||||
|
||||
## Critères de succès
|
||||
|
||||
|
||||
@@ -51,10 +51,10 @@ Mascarade Router ──→ Mistral Agents API
|
||||
|
||||
| # | Tâche | Agent BMAD | Livrable | Done |
|
||||
|---|-------|-----------|----------|------|
|
||||
| 11 | Intégrer Devstral dans workflow CI/CD | Architect + Devstral | PR automation | [ ] |
|
||||
| 11 | Intégrer Devstral dans workflow CI/CD | Architect + Devstral | PR automation | [x] |
|
||||
| 12 | Benchmark fine-tune: base vs KiCad-tuned (100 prompts) | QA + Forge | Rapport benchmark | [ ] |
|
||||
| 13 | Documentation complète dans Outline wiki | Doc | 4 pages wiki | [ ] |
|
||||
| 14 | Cron health-check Sentinelle (06:00 daily) | Ops | Cron configuré | [ ] |
|
||||
| 13 | Documentation complète dans Outline wiki | Doc | 4 pages wiki | [x] |
|
||||
| 14 | Cron health-check Sentinelle (06:00 daily) | Ops | Cron configuré | [x] |
|
||||
|
||||
## Critères de succès
|
||||
|
||||
|
||||
@@ -68,9 +68,9 @@
|
||||
|
||||
## P3 — Évolutions futures
|
||||
|
||||
- [ ] T-MA-030: Implémenter A2A protocol dans Mascarade (MCP + A2A complémentaires)
|
||||
- [ ] T-MA-031: Migrer orchestrateur Mascarade vers graph-based state (LangGraph-compatible)
|
||||
- [ ] T-MA-032: Ajouter RAG Document Library à Tower (Outline + docs PDF) — via MistralLibraryClient
|
||||
- [x] T-MA-030: Implémenter A2A protocol dans Mascarade (MCP + A2A complémentaires) — delivered in Mascarade PR #33
|
||||
- [x] T-MA-031: Migrer orchestrateur Mascarade vers graph-based state (LangGraph-compatible) — `core/mascarade/router/graph_state.py` + FastAPI endpoints
|
||||
- [x] T-MA-032: Ajouter RAG Document Library à Tower (Outline + docs PDF) — via MistralLibraryClient — delivered in Mascarade PR #33
|
||||
- [x] T-MA-033: Pipeline d'évaluation continue des agents → `tools/evals/weekly_benchmark.sh` (Ollama devstral, keyword-match quality heuristic, latency/tokens, auto-compare previous run)
|
||||
- [x] T-MA-034: Lot chain dispatch vers agents Mistral → `tools/ai/dispatch_to_agent.sh` (domain-to-agent mapping, local Ollama or Mistral API, dry-run, logging)
|
||||
|
||||
|
||||
@@ -128,9 +128,9 @@
|
||||
|
||||
## P3 — Évolutions futures
|
||||
|
||||
- [ ] T-MA-030: Implémenter A2A protocol dans Mascarade (MCP + A2A complémentaires)
|
||||
- [ ] T-MA-031: Migrer orchestrateur Mascarade vers graph-based state (LangGraph-compatible)
|
||||
- [ ] T-MA-032: Ajouter RAG Document Library à Tower (Outline + docs PDF) — via MistralLibraryClient
|
||||
- [x] T-MA-030: Implémenter A2A protocol dans Mascarade (MCP + A2A complémentaires) — delivered in Mascarade PR #33
|
||||
- [x] T-MA-031: Migrer orchestrateur Mascarade vers graph-based state (LangGraph-compatible) — `core/mascarade/router/graph_state.py` + FastAPI endpoints
|
||||
- [x] T-MA-032: Ajouter RAG Document Library à Tower (Outline + docs PDF) — via MistralLibraryClient — delivered in Mascarade PR #33
|
||||
- [x] T-MA-033: Pipeline d'évaluation continue des agents → `tools/evals/weekly_benchmark.sh` (Ollama devstral, keyword-match quality heuristic, latency/tokens, auto-compare previous run)
|
||||
- [x] T-MA-034: Lot chain dispatch vers agents Mistral → `tools/ai/dispatch_to_agent.sh` (domain-to-agent mapping, local Ollama or Mistral API, dry-run, logging)
|
||||
|
||||
|
||||
@@ -31,7 +31,7 @@ Fichiers, Fine-tune, Batches, IA Documentaire, Audio, Vibe CLI, Codestral.
|
||||
| 5 | Fine-tune KiCad sur Mistral Small | Forge + HW | ft:kicad-v1 | [ ] |
|
||||
| 6 | Fine-tune SPICE+Embedded sur Codestral | Forge + FW | ft:spice-embedded-v1 | [ ] |
|
||||
| 7 | Batch benchmark base vs fine-tuned (100 prompts) | QA + Forge | Rapport comparatif | [ ] |
|
||||
| 8 | Configurer Document Library RAG pour Tower | Tower | Recherche docs active | [ ] |
|
||||
| 8 | Configurer Document Library RAG pour Tower | Tower | Recherche docs active | [x] |
|
||||
|
||||
### P2 — Intégrations Studio (J8-J10)
|
||||
|
||||
@@ -40,7 +40,7 @@ Fichiers, Fine-tune, Batches, IA Documentaire, Audio, Vibe CLI, Codestral.
|
||||
| 9 | Intégrer IA Documentaire dans pipeline OCR | Sentinelle + HW | OCR automatisé | [ ] |
|
||||
| 10 | Intégrer Audio STT dans ops workflow | Sentinelle | Transcription auto | [ ] |
|
||||
| 11 | Installer Vibe CLI sur VM photon-docker | Devstral | CLI opérationnel | [ ] |
|
||||
| 12 | Intégrer Codestral FIM dans Mascarade | Architect + Devstral | Provider FIM | [ ] |
|
||||
| 12 | Intégrer Codestral FIM dans Mascarade | Architect + Devstral | Provider FIM | [x] |
|
||||
|
||||
### P3 — Production (J11-J14)
|
||||
|
||||
@@ -48,8 +48,8 @@ Fichiers, Fine-tune, Batches, IA Documentaire, Audio, Vibe CLI, Codestral.
|
||||
|---|-------|-------|---------|--------|
|
||||
| 13 | Déployer modèles fine-tuned dans Mascarade | Architect | Router mis à jour | [ ] |
|
||||
| 14 | Tests E2E pipeline Studio→Mascarade→Agent | QA | Evidence pack | [ ] |
|
||||
| 15 | Documentation Outline (4 pages Studio) | Doc | Wiki à jour | [ ] |
|
||||
| 16 | Cron audit qualité modèles (weekly) | QA + Sentinelle | Benchmark continu | [ ] |
|
||||
| 15 | Documentation Outline (4 pages Studio) | Doc | Wiki à jour | [x] |
|
||||
| 16 | Cron audit qualité modèles (weekly) | QA + Sentinelle | Benchmark continu | [x] |
|
||||
|
||||
---
|
||||
|
||||
|
||||
Reference in New Issue
Block a user