gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
4,983 Commits 13 Branches 0 Tags
b4e26a3b45fd7d2b2e8d4e94d307c6dba504aea7
Commit Graph

8 Commits

Author SHA1 Message Date
jgrusewski
08d070bb95 refactor: rename JWT issuer foxhunt-api-gateway → foxhunt-api, drop compat aliases 
- JWT issuer now foxhunt-api across all 16 files (services, tests, config, docker-compose)
- Remove serde alias api_gateway_url from FxtConfig (no backwards compat)
- Remove api_gateway CLI alias from e2e orchestrator
- All services must deploy simultaneously for JWT validation to match

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-05 00:22:04 +01:00
jgrusewski
075f715fa1 refactor: replace all api_gateway/web-gateway references across codebase 
- Rename test functions, variables, bench names (api_gateway → api)
- Update e2e orchestrator executable path (target/debug/api)
- Clean Grafana dashboards: remove dead web-gateway panels, fix trailing
  pipes/commas, update pod selectors
- Update metrics_validation test metric prefixes (api_gateway_ → api_)
- Fix .gitlab-ci.yml remaining path reference
- Fix FXT CLI test flag and function names
- Keep JWT issuer foxhunt-api-gateway (cross-service auth compat)
- Keep serde alias api_gateway_url (config backwards compat)

cargo check --workspace passes cleanly.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-05 00:18:58 +01:00
jgrusewski
5fe3608d92 fix(fxt,infra): production hardening — OTLP telemetry, TUI fixes, K8s infra 
- Remove opentelemetry-otlp internal-logs feature (OTLP feedback loop)
- Switch trace sampling from AlwaysOn to 10% ratio-based
- Add RUST_LOG filtering (opentelemetry/h2/tonic/hyper=warn) to all 8 services
- Wire per-service latency measurement via health check → proto metadata → TUI
- Replace Vec::remove(0) with VecDeque ring buffers (O(1) vs O(n))
- Add Arc<AtomicBool> connected_sent for first-connected detection across 12 streams
- Add MAX_RECONNECT_ATTEMPTS (10) uniformly to all stream spawners
- Change kill switch/circuit breaker fields to Option types with N/A display
- Wire data_cache to real download status stream, remove dead cluster_events
- Remove ServiceData::new() hardcoded stubs, add honest placeholders
- Fix nanos_to_hms zero/negative guard, total_records semantic fix
- Fix RwLock held across yield in broker_gateway stream_account_state
- Add break after yield Err in broker/trading stream generators
- Fix connected_at advancing per tick in stream_session_status
- Tempo: replace emptyDir with 10Gi PVC, bump memory to 512Mi/2Gi
- Remove Prometheus gitlab-annotated-pods duplicate scrape job
- Wire 6 new gRPC streaming adapters (risk, trading, ml, data-acquisition)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 10:39:56 +01:00
jgrusewski
eed268c230 chore: update Cargo.lock and regenerated e2e proto 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-03 02:02:20 +01:00
jgrusewski
2aedc2ae1a feat(ml): comprehensive GPU saturation audit — 58 fixes across all 10 models 
Phase 1 — Fix broken models (P0):
- Diffusion: wire optimizer_step to actually apply gradients (was no-op)
- TLOB: connect forward pass to projection layers (was Tensor::zeros)
- Mamba2: F64→F32 migration across 5 files (~30x faster on L40S tensor cores)

Phase 2 — Eliminate hot-path GPU sync stalls:
- Mamba2: keep dt on GPU in discretize_ssm (4 functions, no CPU round-trip)
- TFT: gate attention weight logging to eval only (8 syncs/forward eliminated)
- Mamba2: defer loss scalar after backward (pipeline stall removed)
- Mamba2: delete dead gradient clipping (4N wasted GPU syncs removed)

Phase 3 — Enable BF16 for supervised models:
- Flip mixed_precision defaults to true in 4 config locations
- Fix cuda_layer_norm to support BF16/F16 via F32 intermediate

Phase 4 — Raise hyperopt bounds for datacenter GPUs:
- 7 adapters with VRAM-aware tiers (TFT, Liquid, TGGN, KAN, xLSTM,
  Diffusion, TLOB) — L40S gets full hidden_dim range
- Fix L40S tier boundary (was excluded at <48000, now >=40000)

Phase 5 — Update memory estimates:
- 10 param_count estimates updated (DQN 200K→12M, TFT 2M→50M, etc.)
- Fix power-of-two rounding (was wasting up to 49% of budget)
- Correct MODEL_OVERHEAD_MB in DQN/PPO/TFT adapters

Phase 6 — Fix per-epoch CPU bottlenecks:
- PPO: deduplicate double advantage normalization (correctness fix)
- PPO: GPU tensor reward normalization + explained variance
- Fuse per-parameter grad norm to single GPU sync (xLSTM, KAN, TGGN)

Phase 7 — Data pipeline:
- GpuBufferPool: use from_slice (eliminate staging buffer copy)

Phase 8 — Correctness:
- TFT: remove broken .detach() in forward_checkpointed (restore gradients)
- Update stale RTX 3050 Ti doc references

33 files changed, 2451 tests pass, 0 clippy warnings.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 15:41:23 +01:00
jgrusewski
de8d7b86f8 chore: commit generated proto stubs for on-demand training RPCs 
The e2e test crate uses pre-generated proto code (no build.rs).
Missing stubs for: ReportJobCompletion, ListPendingPromotions,
ApprovePromotion, RejectPromotion + message types.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-26 13:55:40 +01:00
jgrusewski
d7f11449f4 fix(e2e): mark infrastructure-dependent tests as #[ignore] 
E2E framework tests require running services (database, JWT, ML
pipeline) that aren't available in CI unit test stage.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-25 14:00:49 +01:00
jgrusewski
9c3d741a08 refactor: restructure repo — crates/, bin/, testing/ layout 
Move 17 library crates into crates/, CLI binary into bin/fxt,
consolidate 10 test crates into testing/, split config crate
from deployment config files.

Root directory reduced from 38+ to ~17 directories.
All Cargo.toml paths and build.rs proto refs updated.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-25 11:56:00 +01:00