Replace the recompute approach from #146 with per-token outlier
detection. Entries whose energy, FLOPs, or dollar savings exceed
generous per-token thresholds (~1000x legitimate values) are hidden
from the leaderboard entirely. All displayed values come directly
from the database — no rewriting of submitted data.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Energy and FLOPs are now derived from total_tokens on the leaderboard
display using Claude Opus 4.6 constants, rather than trusting submitted
DB values. This prevents gaming (e.g. TotallyNoire submitting 14B Wh
from 15M tokens). Dollar savings are clamped at the theoretical max
($25/1M tokens) on both the leaderboard and frontend submission side.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The energy_wh_saved and flops_saved values were orders of magnitude too
high because a scaling factor that grows linearly with N was applied to
the energy calculation, making it scale as O(N³) instead of O(N²).
Replace the buggy scale-factor approach with a direct FLOP-to-energy
conversion using each provider's per-token constants. Add regression
tests to prevent recurrence.
Closes#95
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: create learning subdirectory structure (routing, agents, intelligence)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: extract classify_query to routing/_utils.py
Move the classify_query() function and its regex patterns into a shared
utility module so multiple routing policies can import it without
depending on the full trace_policy module.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: move routing files to learning/routing/ subdirectory
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: create LearnedRouterPolicy merging trace-driven + SFT routing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add conditional Algolia DocSearch integration
Add Algolia DocSearch as an optional search upgrade — native lunr.js
search remains the default until credentials are configured. Includes
CDN assets, Jinja2 conditional config injection, init script with
graceful fallback, light/dark theme CSS, improved search tokenization
for snake_case/dotted identifiers, and search boosts for key pages.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: move agent_evolver and skill_discovery to learning/agents/
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: move learning/orchestrator to learning/intelligence/orchestrator
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: delete removed learning policies, rewrite __init__.py, clean up api_routes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add SFT/GRPO/DSPy/GEPA config dataclasses, update LearningConfig
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add general-purpose SFT trainer (intelligence/sft_trainer.py)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: update stale imports in multi_model_router example
Update imports to use new learning/routing/ paths after the
subdirectory reorganization. Replace BanditRouterPolicy with
LearnedRouterPolicy.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add general-purpose GRPO trainer (intelligence/grpo_trainer.py)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add DSPy agent optimizer (agents/dspy_optimizer.py)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add GEPA agent optimizer (agents/gepa_optimizer.py)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add learning-dspy and learning-gepa optional dependency extras
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: update integration test to check for learned policy instead of grpo
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: clean up stale APIs and unused params in examples
- deep_research: remove system_prompt and max_turns params not accepted
by Jarvis.ask(), inline system prompt into the query instead
- doc_qa: remove unused --top-k CLI arg that was never passed to the API
- multi_model_router: fix select_model() call to match single-arg signature
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: import SFT/GRPO trainers in intelligence/__init__.py for registry
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: remove .md file changes from PR
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: restore search boost frontmatter for key docs pages
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
