Commit Graph
7 Commits
Author SHA1 Message Date
thePR0M3TH3AN 811f45b3af Harden memory workflow to reduce merge conflicts 2026-02-26 08:18:47 -05:00
google-labs-jules[bot]andPR0M3TH3AN 003e18b93b Fix CI lint error in lock-publisher.mjs
- Ensure `src/lock-publisher.mjs` does not import `randomInt`.
- Clean up test output artifacts.
- Re-verify tests pass locally.

Co-authored-by: PR0M3TH3AN <[email protected]>
2026-02-21 20:48:15 +00:00
thePR0M3TH3AN 9fef4c4f46 update 2026-02-21 15:16:45 -05:00
thePR0M3TH3ANandClaude Sonnet 4.6 8a9080e7c3 fix(memory): close the content gap so agents can actually write and retrieve learnings
- run-selected-prompt.mjs: set SCHEDULER_MEMORY_FILE env var before spawning each agent so
  store.mjs has a well-known path to read from (memory-updates/<ts>__<agent>.md)
- retrieve.mjs: format memories.md using m.summary + date/tags in readable markdown sections
  instead of raw m.content blobs; agents can now scan injected context at a glance
- store.mjs: remove semantically-empty fallback placeholder events that polluted the store
  and degraded retrieval quality; also fix default cadence 'weekly' -> 'daily' to match retrieve
- scheduler-flow.md: replace vague "write insights" instruction with a concrete three-section
  template (Key findings / Patterns / Warnings) and clarify that $SCHEDULER_MEMORY_FILE is
  set by the scheduler automatically

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
2026-02-20 10:51:03 -05:00
google-labs-jules[bot]andPR0M3TH3AN 2a39713189 feat(scheduler): generate unique memory update files per run to avoid merge conflicts
- Modified `scripts/agent/run-scheduler-cycle.mjs` to generate a unique `memory-updates/<timestamp>__<agent>.md` path and pass it via `SCHEDULER_MEMORY_FILE` env var.
- Updated `scripts/memory/store.mjs` to prioritize `SCHEDULER_MEMORY_FILE` for ingestion.
- Updated `src/prompts/scheduler-flow.md` to instruct agents to write to the unique memory file.
- Updated `src/prompts/daily/torch-garbage-collection-agent.md` to include `memory-updates/*.md` in the cleanup scope.
- Moved existing `memory-update.md` to `memory-updates/legacy-memory-update-<timestamp>.md` to clear the root.

Co-authored-by: PR0M3TH3AN <[email protected]>
2026-02-17 15:19:52 +00:00
google-labs-jules[bot]andPR0M3TH3AN 44884cc0c0 Make memory system usable by agents via file-based I/O
Co-authored-by: PR0M3TH3AN <[email protected]>
2026-02-17 02:50:46 +00:00
google-labs-jules[bot]andPR0M3TH3AN d23e6ff0b3 Refactor memory scripts and fix configuration for new installs
- Replaced fragile inline Node.js scripts in `torch-config.json` with dedicated modules: `scripts/memory/retrieve.mjs` and `scripts/memory/store.mjs`.
- Updated `src/ops.mjs` initialization logic to dynamically configure `scheduler.memoryPolicyByCadence` with correct paths based on the installation directory.
- Added default memory policy configuration to `torch-config.example.json` to guide users.
- Injected `torch:memory:list` and `torch:memory:inspect` convenience scripts into the host `package.json` during `init`.
- Removed legacy shell scripts (`run-memory-retrieval.sh`, `run-memory-store.sh`).
- Verified memory scripts function correctly and pass linting.

Co-authored-by: PR0M3TH3AN <[email protected]>
2026-02-16 17:19:55 +00:00