Oliver/amazon-transcreation
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
29 commits 1 branch 0 tags 2.3 MiB
Commit graph

4 commits

Author SHA1 Message Date
DJP
5e0a148b96 feat: add token usage tracking, feedback highlighting, cost on cards, help page 
- Wire token usage from LLM agents through pipeline context to DB and frontend
- Agents 2 and 4 accumulate input/output tokens and cost into PipelineContext
- job_tasks.py saves token totals to locale instance after pipeline completion
- Monitoring cards show total tokens and estimated cost instead of broken 0/0
- Make feedback highlighting bolder: colored card borders, stronger button states
- Add estimated cost display to dashboard job cards
- Add Help page with full documentation and link in sidebar navigation
- Comprehensive README with ASCII architecture diagrams

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-10 16:47:36 -04:00
DJP
f2398e04c4 feat: add real-time progress tracking and admin job deletion 
Progress tracking:
- Add progress (0-100%) and current_stage columns to locale_instances
- Wire orchestrator on_progress callback to update DB at each pipeline stage
- Agent 4 reports batch-level sub-progress (e.g. "Translating batch 2/4")
- Frontend reads real progress/stage data instead of hardcoding 50%
- Stages: Loading Files → Matching TM → Ranking → Translating (per-batch) → Reviewing → Formatting → Complete

Job deletion:
- DELETE /jobs/{id} endpoint (admin-only, 403 for non-admins)
- Cannot delete running jobs (must cancel first)
- Cascades to locale instances, output rows, source lines
- Frontend: Delete button with confirmation on job monitoring page (admin only)

Also: compute live duration_seconds from started_at, map pipeline stages to UI status badges.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-10 16:18:59 -04:00
DJP
7a0971a029 feat: implement real LLM agents 2-5 for live transcreation pipeline 
Replace all stub agents with working Claude API-powered agents:
- Agent 2 (TM Retrieval): LLM semantic matching of source lines against TM entries
- Agent 3 (Ranker): Deterministic ranking with confidence tiers (high/moderate/low)
- Agent 4 (Transcreator): Batched creative transcreation with voice profiles, reference files, backtranslations
- Agent 5 (Compliance): Deterministic checks for character limits, blacklist terms, domain substitution

Also fixes TM file loader to handle real compact JSONL format (locale code regex-based parsing),
and adds file manifest resolution for reference files (glossary, blacklist, TOV, locale considerations).

Verified end-to-end: 53-line de-DE brief produces real German translations with TM matching,
confidence-based option counts (1/2/3), backtranslations, and compliance validation. ~$0.49 total cost.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-10 15:26:41 -04:00
DJP
98fa16bfc3 feat: complete Phase 1-2 scaffold — backend, frontend, pipeline skeleton 
Full-stack Amazon AI Transcreation Platform with:
- FastAPI backend (async, PostgreSQL, Redis, Celery) with 11 DB tables
- JWT auth (SSO-ready abstract provider pattern)
- 6-agent pipeline orchestrator with deterministic modules
- Next.js 14 frontend with Amazon branding (Ember fonts, orange/dark theme)
- Job wizard, monitoring HUD, output review, admin screens
- 154 TM/reference files imported, 12 locales configured
- Docker Compose for all services

Agents 2-5 (TM retrieval, ranker, transcreator, compliance) are stubs
pending Phase 3 LLM integration.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-04-10 12:31:43 -04:00