gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
5,903 Commits 13 Branches 0 Tags
2c08b49b4f01b7e84b6eb364d598a4cf9fcbf557
Commit Graph

8 Commits

Author SHA1 Message Date
jgrusewski
7f065e4d02 feat(claude): sp-critical-reviewer agent (foxhunt) 
Replicates the user's second/third critical-review iteration cycle. Cites
every claim against a memory file. Enforces no-deferrals-for-complementary-
fixes, ISV-slot enumeration, smoke kill conditions, anti-pattern callouts.
Composes the four foxhunt auditor agents for domain-specific verification.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-10 22:19:28 +02:00
jgrusewski
127bcba599 feat(claude): code-hygiene-auditor agent (foxhunt) 
Pattern-cluster auditor for general code-quality rules: no stubs, no TODO,
no hiding, no legacy aliases, no feature flags, no partial refactors,
v7-gem methodology, invariant tests not observed-value tests, no deferrals
of complementary fixes. Bundles 12 feedback rules and 3 pearls.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-10 22:19:28 +02:00
jgrusewski
b3480fe0e3 feat(claude): reward-controller-auditor agent (foxhunt) 
Pattern-cluster auditor for reward composition and controller mechanics:
bilateral clamps, structural activations, asymmetric bounded clamps, event-
driven density alignment, one-unbounded-multiplicand, Thompson selector,
trail-on-pre_mag, Adam-normalized loss weights, per-bar vs segment PnL,
imbalance-bar EWMA wash-out, aux trunk separation, magnitude-trap.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-10 22:19:28 +02:00
jgrusewski
e18f97a474 feat(claude): isv-discipline-auditor agent (foxhunt) 
Pattern-cluster auditor for ISV-driven adaptive bounds, controller anchors,
EMA bootstrap, Wiener-α floors, blend formulas, per-branch budgets, per-group
Adam, Kelly floors, trail-stop. Bundles 2 feedback rules and 16 pearls.
Read-only; cites memory file by name on every finding.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-10 22:19:28 +02:00
jgrusewski
1b1b997be1 feat(claude): gpu-contract-auditor agent (foxhunt) 
Pattern-cluster auditor for CUDA/GPU host code. Bundles 6 feedback rules and
7 pearls (no atomicAdd, mapped-pinned, no nvrtc, f64/f32 ABI, no host branches
in graph capture, fused per-group stats, build.rs rerun, canary launch order).
Read-only; cites memory file by name on every finding.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-10 22:19:28 +02:00
jgrusewski
12fdd18223 refactor: remove entire CPU training path — 5,307 lines of dead code 
Deleted:
- DQN::compute_loss_internal (280 lines) — old Candle forward+loss
- DQN::train_step (55 lines) — old Candle training step
- DQN::compute_gradients (47 lines) — old gradient accumulation
- ComputeLossResult struct — only used by deleted functions
- RegimeConditionalDQN::train_step (65 lines) — old dispatch
- RegimeConditionalDQN::train_step_gpu_regime (100 lines) — old GPU path
- RegimeConditionalDQN::compute_gradients_gpu (130 lines) — old regime gradients
- RegimeConditionalDQN::compute_gradients (92 lines) — old dispatch
- DQNAgentType::train_step dispatch — dead
- DQNAgentType::compute_gradients dispatch — dead
- GpuDqnTrainer::upload_batch (71 lines) — old CPU→GPU upload
- train_step.rs (500 lines) — entire module including ensure_fused_ctx
- dqn_benchmark.rs — used old train_step
- examples.rs — used old train_step
- validation/adapters.rs (289 lines) — used old train_step
- dqn/trainable_adapter.rs — used old train_step
- gpu_smoketest.rs — tested old train_step
- Gradient accumulation path in training_loop.rs (144 lines)
- IQN d_h_s2().clone() → raw pointer (zero alloc)
- Causal intervention format! string alloc removed
- Dead HER relabel functions (320 lines)

Kept:
- ensure_fused_ctx logic inlined into training_loop.rs
- set_noise_sigma_scale re-added to RegimeConditionalDQN

Fixed:
- GpuReplayBuffer max_batch_size wired from batch_size parameter
  (was hardcoded 1024, blocking batch_size=8192)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-02 09:06:23 +02:00
jgrusewski
d501d53c9d chore(infra): remove dead Cockpit TF, CI-CD dashboards, stale Grafana configs 
- Delete infra/modules/cockpit/ and infra/live/production/cockpit/
  (Scaleway Cockpit replaced by self-hosted Grafana+Prometheus+Loki+Tempo)
- Delete CI-CD dashboards (foxhunt-ci-pipelines, gitlab-services) and
  grafana-dashboards-cicd ConfigMap from K8s
- Delete config/grafana/ — unreferenced old dashboards (15 files)
- Delete config/monitoring/grafana/ — unreferenced DQN staging dashboard
- Delete crates/ml/grafana/ — unreferenced ML performance dashboard
- Delete services/broker_gateway_service/grafana/ — unreferenced
- Delete .claude/agents/devops/ci-cd/ — GitHub Actions agent (we use GitLab CI)
- Fix grafana-values.yaml: dashboard folder GitLab → Foxhunt,
  hardcoded adminPassword → K8s secret (grafana-admin),
  gitlab-overview → node-exporter (correct name for gnetId 1860)
- Remove CI-CD group from import.sh ConfigMap groups and API fallback

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 15:13:40 +01:00
jgrusewski
2c1acda2f3 feat: DQN Rainbow enhancements with hyperopt results and test coverage 
- Update DQN trainer with gradient collapse detection warmup
- Add portfolio tracker improvements
- Include hyperopt trial results (multiple Sharpe ratio experiments)
- Add new test files for action/position sign convention, early stopping,
  cash reserve bugs, and portfolio execution
- Update trained model files
- Add Claude Code configuration and skills

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-27 14:45:25 +01:00