mirror of
https://github.com/fabro-sh/fabro.git
synced 2026-10-11 03:40:05 +00:00
f94955ede5
Compaction summarizes the conversation with the session's own model, but
hard-coded `max_tokens: Some(4096)` and sent no `reasoning_effort`. On a
reasoning model that ceiling covers thinking *and* visible output, so a
long conversation can exhaust it on reasoning alone and return a
successful response with empty content — silently replacing the compacted
history with an empty summary.
The Anthropic codec's existing clamp does not cover this path: it only
runs when the request carries a `reasoning_effort` and the model has no
native effort parameter. Compaction sends `reasoning_effort: None`, so
encoding falls through to the branch that injects `{"type": "adaptive"}`
for `levels` models with no clamp at all, and the openai_compatible and
openai_responses codecs pass `max_tokens` straight through.
Resolve the budget from the catalog instead. Models whose endpoint
reasons without being asked (`always_adaptive` natively, `levels` via
default adaptive thinking or the provider's default effort) get 16K of
reasoning headroom above the 4096-token summary allowance, capped at the
model's own `max_output`. Models with no reasoning-effort feature never
reason on this path and keep the existing 4096.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| fabro-acp | ||
| fabro-agent | ||
| fabro-automation | ||
| fabro-checkpoint | ||
| fabro-dump | ||
| fabro-environment | ||
| fabro-github | ||
| fabro-graphviz | ||
| fabro-hooks | ||
| fabro-install | ||
| fabro-interview | ||
| fabro-llm | ||
| fabro-manifest | ||
| fabro-mcp | ||
| fabro-mcp-store | ||
| fabro-sandbox | ||
| fabro-slack | ||
| fabro-store | ||
| fabro-tool | ||
| fabro-tracker | ||
| fabro-validate | ||
| fabro-variable | ||
| fabro-workflow | ||