 Celes Renata
|
a72f336ad1
|
feat: Intelligence Pipeline v3 — full implementation
Multi-stage evidence-grounded inference architecture replacing the
monolithic 9B model extraction pipeline. CPU-first specialist services
handle routine extraction while the 9B vLLM model is preserved for
semantic adjudication of ambiguous cases.
Key components:
- Capability-aware inference gateway (OpenAI-compatible + Ollama)
- Endpoint registry with DB migrations and REST API
- Sentence-aware document segmenter (property tests)
- Deterministic financial parsing with offset integrity
- Symbol resolution with ambiguity detection
- Specialist service (GLiNER2, dynamic batching, K8s deployment)
- Company-specific sentiment (FinBERT, calibration)
- Retrieval-based novelty and duplicate detection
- Confidence calibration pipeline
- Deterministic routing engine (property tests)
- 9B adjudication layer with VRAM gating
- Stock-specific impact model (features, labels, baseline, trained)
- Pipeline orchestrator (state machine, queues, leases, feature flags)
- Bounded parallelism (async workers, semaphore, load shedding)
- Observability (tracing, metrics, alerts)
- Compatibility adapter (v3→v2 golden mapping tests)
- Shadow/canary promotion framework
- Active learning and fine-tuning pipeline
Test results: 1,161 tests pass, ruff lint clean.
All 282 spec tasks completed.
|
2026-07-13 02:14:59 +00:00 |
|
|
Celes Renata
|
9aae57f3e1
|
docs: rewrite README and runbook for current platform state
README: updated architecture diagram, three signal layers, tracked
universe, autonomous trading engine, global news interpolation,
competitive intelligence, paper trading, notification service,
updated services table, project structure, deployment, endpoints.
Runbook: updated service overview, deployment via runmefirst.sh,
secrets management (keys in kube dir not repo), backup/restore
scripts, trading engine operations, signal layer toggles, database
nuke & rebuild, monitoring, CI/CD, removed hardcoded secrets.
|
2026-04-16 02:06:18 +00:00 |
|