Skip to content

Shadow idea-generation sidecar (first milestone of #43) #44

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
OnePunchMonk merged 1 commit into from
Oct 7, 2026
Merged

Shadow idea-generation sidecar (first milestone of #43) #44

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]

### Added
- Shadow idea-generation sidecar (`src/agent/idea_sidecar.py`, issue #43), behind `AGENTQUANT_IDEA_SIDECAR=1`. Non-learning: it replays a fixed heuristic or seeded random policy over the canonical parameter grid and logs a versioned observation/action/reward trajectory. No new dependencies; the default demo never imports it.
- Unified memory layer (`src/memory/`, [design](docs/MEMORY_LAYER_DESIGN.md)).
- Every backtested proposal is recorded as a trial, and holdout results are attached as out-of-sample evidence.
- Reads use a point-in-time `as_of` cutoff enforced in SQL. Beliefs are evidence-weighted: OOS first, in-sample deflated for the number of configs tried, weighted by regime similarity.
Expand Down
Loading
Loading