Pizza
11b49d3933
feat: milestone 3 complete + QA benchmark
...
Web UI (tinyclaw web):
- Flask + SSE real-time progress streaming
- Queue view: add/delete tasks, status colours, error display
- Live log panel with coloured output
- History tab with unified diffs (Rosé Pine theme)
- Model picker dropdown
- Auto-refresh every 5s
History (history.py):
- JSONL-based, records before/after content + unified diff
- Wired into driver for EDIT and CREATE actions
- Failed tasks also recorded
QA benchmark (tinyclaw qa <models...>):
- 5 fixed tasks: divide/greet/is_even/repeat/safe_get
- Scores syntax validity + instruction following
- Comparison table: pass%, syntax%, latency, cost
QA results (3 models):
- gemma-3-12b-it: 80% pass, 100% syntax, ~944ms ← winner
- gemma-3-4b-it: 60% pass, 100% syntax, ~917ms
- qwen2.5-coder-7b: 0% pass, 0% syntax (max_tokens issue — hits 512 limit mid-function)
2026-04-03 01:27:41 +00:00
Pizza
6e893c6362
feat: milestone 2 complete
...
- driver: .env auto-load, failure log (FAILURES.md), exponential backoff
on 429 (5x multiplier) and general errors
- cli: tinyclaw add subcommand, appends single task to QUEUE.md
- demo/: math_utils.py + QUEUE.md for end-to-end testing
- Verified: 3/3 tasks pass with google/gemma-3-4b-it, 96-135 prompt tokens each
- Queue markers [done]/[failed:N]/[skipped] persist correctly
2026-04-03 00:25:31 +00:00
Pizza
eb9b3fc85b
feat: milestone 1 core loop complete
...
- verifier.py: syntax check via ast.parse, verify_function_present
- queue.py: QUEUE.md parser, status markers [done]/[failed:N]/[skipped]
- driver.py: full run loop — extract, prompt, generate, verify, splice, commit
- EDIT/CREATE/DELETE/TEST actions
- retry logic (max 3), auto-commit per task, cost tracking
- cli.py: run/status/plan wired up; plan calls big model to decompose features
- QUEUE.md: example queue with commented-out demo tasks
- pyproject.toml: fix build backend
tinyclaw run --dry-run works end-to-end
2026-04-03 00:19:53 +00:00
Pizza
52d5c368fa
init: project scaffold with SmallClawPlus brain files
...
- Brain: STATUS, PLAN (4 milestones), ARCH (module design), CONTEXT, SESSIONS, DEPS
- Learnings: ERRORS.md, LEARNINGS.md (empty)
- Code: cli.py stub, pyproject.toml, __init__.py
- README with architecture diagram and queue format
- Queue format: EDIT/CREATE/DELETE/TEST actions
2026-04-02 21:19:38 +00:00