<feed xmlns='http://www.w3.org/2005/Atom'>
<title>newos4/modules/core/model-profiles.js, branch main</title>
<subtitle>newOS4 - the browser terminal that runs WebX11 user spaces</subtitle>
<id>https://newos.webx11.duckdns.org/newos4/atom?h=main</id>
<link rel='self' href='https://newos.webx11.duckdns.org/newos4/atom?h=main'/>
<link rel='alternate' type='text/html' href='https://newos.webx11.duckdns.org/newos4/'/>
<updated>2026-11-02T19:46:18+00:00</updated>
<entry>
<title>feat(newos4): configurable tool budgets, per-model defaults, real tool telemetry</title>
<updated>2026-11-02T19:46:18+00:00</updated>
<author>
<name>Agando</name>
<email>roduccomm@gmail.com</email>
</author>
<published>2026-11-02T19:46:18+00:00</published>
<link rel='alternate' type='text/html' href='https://newos.webx11.duckdns.org/newos4/commit/?id=44e390f3e08acb3ad13daea0dbf365424eeb7d95'/>
<id>urn:sha1:44e390f3e08acb3ad13daea0dbf365424eeb7d95</id>
<content type='text'>
Closes STEER-20261102-201234-7200 (read_file capped at 6000 while the schema
promised 32000).

Budgets (module-aiassist.js + new modules/core/model-profiles.js):
- one resolver, precedence: call arg -&gt; loop profile -&gt; model profile -&gt;
  ai-config -&gt; code default. Keys: read-page-chars, read-result-chars,
  tool-context-budget, fetch-chars.
- model classes tiny/small/mid/large keyed by id then by size token; `mid`
  reproduces the old numbers so nothing moves for a mid model.
- _clipToolResult now clips the `content` field, never the serialised JSON
  envelope: clipping the envelope deleted truncated/next_offset, so a 16k page
  lost its continuation pointer (the reported symptom).
- read_file's schema no longer promises a number the model class may not give.

Telemetry:
- _recordToolCall keeps sizes, duration, ok and a 120-char arg preview instead
  of the whole payload; ai-stats prints calls / ok% / avg ms / KB / truncation
  from localStorage webx11_tool_stats.

Server (api/proxy-api.py):
- /api/extract honours max_chars (default 12000, cap 100000) and returns
  content_chars + truncated; the bs4 branch is no longer uncapped while the
  regex fallback was silently cut at 10 000.

BEHAVIOUR CHANGE: num_ctx for a model with no explicit setting now follows the
class default (16384 -&gt; 65536 for cloud/large, 8192 for tiny). Cloud models bill
on tokens used, so cost is unchanged; local models get a bigger KV cache.

Two build traps, both now documented in AGENTS.md:
- model-profiles.js must be the FIRST entry in CORE_FILES and must export the
  MODEL_PROFILES global (a TDZ typeof throws; without the global every budget
  silently falls back to the code default).
- a budget key needs the setter branch AND the constructor loader at
  module-aiassist.js:49 - persisting without restoring looks fine until reload.

Verified: test-tool-context-bound 23/23 (RED before: E1-E4 + TypeError on
_toolLimit); live bundle read_page 32000 / result 12000 / budget 48000 /
fetch 12000 and _ctxTokens 65536 for gemma4:31b-cloud; /api/extract 28970 -&gt;
500 chars with truncated true; ai-config write+restore probe 6/6.
</content>
</entry>
</feed>
