hugpy_core
hugpy central, minimal. Workers (hugpy_worker, one per box, over fitevict)
register and heartbeat here; the registry is live in memory. /v1/chat/completions
picks an online worker that has the model (resident first; alloc.worker pins one)
and relays to its /infer/stream. No evict-to-fit, discovery, admission or DB
state — each box's fitevict owns placement and the call log.
hugpy-core --host 127.0.0.1 --port 7020
Benchmark call-log history
POST /llm/benchmark/run opens a core call-log row before validation or planning.
Accepted runs keep that row pending until their asynchronous outcome is known.
Rejected plans retain their constraint reasons in the core response and error.
The response and X-Hugpy-Request-Id expose its request ID.
Benchmark history/status read call_log; the JSON state and run archives are no
longer read or written. Existing files are left intact as legacy evidence and
are not converted into invented historical call records. Grading entries store
call pointers and verdicts. History resolves answers and measurements from the
referenced execution records. Each benchmark inference core row points back to
the orchestration row, and its execution pointer identifies the wrapper row.
Pending benchmark rows from a previous core process are marked interrupted.
The brain (failure auto-evaluation)
Ruling: toolserver instructions/hugpy/brain/brain-established-2026-10-06.
A brain lives in core: always present, callable, and it evaluates every
model-load failure automatically. hugpy-agent, when installed, adds features and
access on top (the agent-station TUI); without it, this brain does the work.
- Event: a
hugpy_wrapper.residentsrow whoseload_errorchanges firespg_notify('model_rows');brain.ensure()(started byapp.main) listens and evaluates it. No polling. - Classify: rules first, from the legacy taxonomy (
hard_load_failure,vram_fit,engine_unavailable,unreachable,vision_needs_slot,missing_dependency,other), plus pip-shaped signals (pip install X,No module named 'x', transformers' "requires the following packages"). - Infer: the brain model is asked only when the rules leave something open
(class
other, or an import name with no package name, e.g.cv2→opencv-python). The call goes through core's own/v1/chat/completionswithmetadata.intent = "brain-evaluate", so it is acall_logrow. The brain never overrules a class the rules determined. - Record: every evaluation is a Help ticket (
help_tickets, kindload-failure), de-duplicated per model/worker/error viaoccurrences. - Call it:
POST /llm/brain/evaluate {error, worker?, model_key?, file?};GET /llm/brainshows the model, policy and listener state.
Settings → Policies → Brain (settings_policies):
| key | meaning |
|---|---|
brain.model |
the brain's model (fallback HUGPY_BRAIN_MODEL, then the help agent's model) |
brain.auto |
auto-evaluate load failures (default on) |
brain.auto_grade_min |
grader score (0–100) a fix must reach to apply without approval; unset = every fix needs approval |
Not automated yet (same ruling, next step): the venv ladder for
missing_dependency — existing env profiles → a new overlay profile → an
isolated profile — each candidate test-loaded and graded, then designated
(model_workers.env_profile) only when the grade meets brain.auto_grade_min.
Never pip-install into a shared venv.
Verdicts priced at the pair's ctx and KV type
planner.refresh_worker passes each pair's user_settings to
measured_verdict.price: the verdict is priced at the pair's ctx_pct
(k% of the trained window, floored to 1024) and kv_cache_type
(f16 / q8_0 / q4_0). A knob write that touches either re-plans that worker
at once (modeldb.pair_knobs → planner.replan), so the console's Memory
distribution follows the knobs.
1 maintainer
Metadata
1 maintainer
Release files for hugpy-core 0.1.49
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| hugpy_core-0.1.49.tar.gz | 163.5 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| hugpy_core-0.1.49-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 332.1 kB
Release files / hugpy_core-0.1.49.tar.gz
| Download URL | hugpy_core-0.1.49.tar.gz |
|---|---|
| Size | 163.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4239c99f3112814477fc67053a14cb5e58e91eb92461e08018d9a6cb40f242f7
|
|
BLAKE2b-256 checksum How to use checksums |
fb40cd51a17b23f48a8d91bce31327e91adc884a3e06e0435f03d5fca6db2b02
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Release files / hugpy_core-0.1.49-py3-none-any.whl
| Download URL | hugpy_core-0.1.49-py3-none-any.whl |
|---|---|
| Size | 168.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3bac05e92c78689c3ca2fdd3e19c7077a0866c2ea64e1c4f810856d764ce0aed
|
|
BLAKE2b-256 checksum How to use checksums |
dfe5d4899467bcfdf66a7a7d913a6a5161bcec13af60b95d9f508d8e817db567
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
