arrow_backRetour aux issues
krapcys1-maker/adaptive-agent-memory-research
#17
Débutant
Ouvrirarrow_forward
Débutant
Ouvrirarrow_forward
Débutant
Ouvrirarrow_forward
Exclude the scratch tmp/ directory from the project-memory index
ecoDébutant
bug
good first issue
track:engine
effort:S
no-expertise-needed
descriptionDescription
## The problem
The project-memory index walks the repository and indexes text files, but `tmp/` is not excluded. That directory is gitignored scratch space, so disposable working files end up competing with real research documents in memory search results.
This is reproducible today:
```bash
python -c "
import sys; sys.path.insert(0,'.')
from tools.project_memory.memory_store import MemoryStore
s = MemoryStore('.')
print([h['id_or_path'] for h in s.search('packs', limit=30) if h['id_or_path'].startswith('tmp/')])
"
```
Current output includes five scratch files, for example `tmp/reuse-char-repeat/summary.json` and `tmp/pmlab-pack-characterization-v1-repeat/aggregates.json`.
This matters more than it looks. A context bundle has a fixed character budget, so every scratch file that wins a slot displaces a real source.
## The fix
`tools/project_memory/memory_store.py` already has two exclusion mechanisms near the top of the file:
- `EXCLUDED_PARTS` — directory names excluded at any depth (`node_modules`, `work`, `.index`, …)
- `EXCLUDED_PREFIXES` — paths excluded from the repository root (`data/snapshots`, `external/repos`, `sources/papers`)
`tmp` belongs in `EXCLUDED_PREFIXES`, because only the top-level `tmp/` is scratch. A directory named `tmp` deeper in the tree might be meaningful research data, so excluding the name everywhere would be too aggressive.
## Acceptance criteria
- [ ] Top-level `tmp/` is no longer indexed.
- [ ] A directory named `tmp` nested deeper in the tree is still indexed.
- [ ] A test covers both cases. `tests/test_project_memory.py::test_generated_work_directories_are_not_indexed` is a good pattern to copy.
- [ ] `python -m pytest -q` stays green.
## Getting started
```bash
git clone https://github.com/krapcys1-maker/adaptive-agent-memory-research
cd adaptive-agent-memory-research
python -m pip install -r requirements-dev.txt
python -m pytest -q
```
No background in memory research is needed for this one. If anything in the setup does not work, say so in this issue — that is useful feedback in itself.
Issues similaires
calkit/calkit
star53
Poids du dépôt moyen
VS Code extension should be robust to YAML parser errors
Seeing this error: ``` Failed to read calkit.yaml: YAMLParseError: A block sequence may not be used as an implicit map…
Python
bug
good first issue
fu351/Doberman-Core
star211
Poids du dépôt léger
dash: a manual Refresh control
The dashboard polls: `refreshStats()` (`src/doberman/dash/app.py:408`) every 5 s and `refreshPending()` (`:546`) every …
Python
enhancement
good first issue
fu351/Doberman-Core
star211
Poids du dépôt léger
dash: "Copy details" button on each pending-approval card
Each pending-approval card in the dashboard (`renderPending`, `src/doberman/dash/app.py:448-544`) shows the risk badge,…
Python
enhancement
good first issue