One call answers a question or a failing test's output with the spans
of the tree most likely to hold the cause, as path:start-end and their
lines, so an agent stops chaining grep and read.
Python is chunked by ast, other text in overlapping 40-line windows.
BM25 over code tokens is fused by reciprocal rank with the spans a
traceback's path:line frames name; when the query names a test file
the index holds, the code under test ranks first. Every search stats
the tree and re-chunks only what moved.
A dense stage (Qwen3-Embedding form, vectors cached by text hash) is
on only when HANZO_SEARCH_MODEL names a model: on the 42 dev tasks it
lifts span MRR .385 to .508, but a CPU query embedding takes seconds.
`python -m hanzo_search.server --root DIR` serves the tool alone over
stdio with the standard library, outside hanzo_mcp, whose import is
seconds long.
The `hanzo` mode lists it, so the default surface carries it; another
mode, `tool disable search` or HANZO_MCP_ENABLED_TOOLS decide it as they
decide every other tool.
The default surface was 34 tools, 61 KB, ~15,300 tokens of schema in every
prompt of every agent. The mode system already names what a session should
carry, but only the tools register_all_tools enumerates obeyed it: zsh,
curl, playwright and the helpers (ps, npx, uvx, jq, wget, cdp, open) stayed
on in every mode. A mode now decides every discovered tool, the `hanzo`
mode lists what a coding agent calls every few steps (18 tools, 32 KB,
~8,000 tokens), and the rest is a name away: HANZO_MCP_ENABLED_TOOLS=a,b
or =all, `tool enable`, or `mode`.
hanzo-tools-shell 0.6.6: run_shell kept every byte a foreground command
wrote until the command ended. `yes` for thirty seconds is gigabytes. It
keeps the first 16 MiB per stream and drains the rest.
The tests' session-wide patch of asyncio.create_subprocess_exec handed
every shell command a stream that never reached EOF; the first test to run
one read it in a loop until the machine was out of memory (22 GB, killed).
The patch is now opt-in and its process has exited.
bench/latency.py measures the cold start, the tools/list bill and the common
calls through a real MCP client over stdio. Interleaved rounds, wall and CPU
seconds, p50 over 6 cold starts:
cold wall cold CPU tools bytes ~tokens
installed 0.15.18 9.34 s 10.46 s 30 52,601 13,150
main 0.15.20 1.52 s 1.13 s 34 61,287 15,321
this 0.96 s 1.06 s 18 32,222 8,055
The installed environment's 9 s is its hanzoai 8.5.156, whose package init
imports the whole generated cloud client; hanzo-mcp >= 0.15.20 requires
hanzoai >= 8.5.624, which loads it lazily. Per-call latency is spawn-bound
(zsh 17.6 ms, git status 33 ms, fs.read 2.5 ms at p50) and moves with the
machine's load; no call path changed.
Every mode disables a registered tool it does not list, and llm was
listed nowhere but HEAVY_TOOLS, written when it pulled a 100 MB client.
It is an HTTP call to api.hanzo.ai now, so llm and kai_decide join the
essential set every personality carries, and the llm package maps to the
two tools it ships.
hanzo-mcp 0.15.19, on hanzo-tools 0.3.8 and hanzo-tools-llm 0.2.1.
Co-authored-by: Hanzo Dev <[email protected]>
The llm tool called upstream providers through the litellm fork, read
provider keys, and never reached the MCP surface: its register() was a
no-op and it skipped BaseTool's constructor. Kai had no Python tool.
hanzo-tools-llm now carries two HIP-0300 tools over HanzoCloud:
- llm (default action query): POST /v1/chat/completions with model
enso-auto unless named, "auto" for Enso's pick, max_cost and
max_latency_ms as X-Max-Cost and X-Max-Latency-Ms, returning id and the
model that served; models: GET /v1/models, one row per model with the
catalog's per-million prices, narrowed by family; feedback: POST
/v1/ai/feedback with request_id, signal and a 1-3 rating.
- kai_decide (default action decide): POST /v1/decisions with the
TypeScript tool's schema and shape checks.
The consensus, llm_manage and provider modules wrapped the upstream
client and were never registered, so they go, with hanzo-consensus and
the [full] extra. hanzo-tools-llm 0.2.1.
Co-authored-by: Hanzo Dev <[email protected]>
Enso reads its routing bounds from X-Max-Cost and X-Max-Latency-Ms on
/v1/chat/completions, and HanzoCloud could send no header but its own, so
no tool could bound a routed request. post() and the shared request path
now take extra headers that ride beside the bearer.
BaseTool runs `help` for a call that names no action. A tool with one
obvious act (llm's query, kai_decide's decide) now declares
DEFAULT_ACTION, which the call, the advertised schema's default and its
required list all read, so it answers the same no-action call the
TypeScript and Rust runtimes do. Every other tool keeps `help`.
hanzo-tools 0.3.8.
Co-authored-by: Hanzo Dev <[email protected]>
zeekay
