Steve Immanuel 0c32e83a35 fix(coding-agent): enable streaming usage for llama.cpp provider (#7258) ... llama-server supports OpenAI-spec stream_options.include_usage since b2b6b55a59 (Sep 2025); any server new enough for router mode sends the final usage chunk when requested. With the flag hardcoded to false the provider never requests it, so streamed responses record zero tokens and session/context accounting stays empty. Verified against llama-server b10094: with include_usage sent, the final chunk carries usage (incl. prompt_tokens_details.cached_tokens); without it, nothing.		2026-07-29 10:03:59 +02:00
..
bun	fix(coding-agent): bundle OAuth flows in Bun binaries	2026-07-16 15:36:16 +02:00
cli	feat: auth print (#7168)	2026-07-27 16:13:06 +02:00
core	***WIP it's a PoC *** fix(coding-agent): guard tree navigation during responses (#7022)	2026-07-28 14:46:30 +02:00
extensions	fix(coding-agent): enable streaming usage for llama.cpp provider (#7258)	2026-07-29 10:03:59 +02:00
modes	fix(coding-agent): show tool expansion status	2026-07-28 15:07:19 +02:00
utils	fix: await wl-copy exit code and fall through to xclip on failure (#7009)	2026-07-24 06:58:37 +02:00
cli.ts	fix(coding-agent): configure HTTP idle timeout (#4759)	2026-05-20 12:45:00 +02:00
config.ts	fix(coding-agent): install checked pi update version	2026-06-21 14:46:07 +02:00
index.ts	fix: complete extension usage accounting	2026-07-20 17:06:22 +02:00
main.ts	feat: auth print (#7168)	2026-07-27 16:13:06 +02:00
migrations.ts	fix(coding-agent): treat uppercase config values as literals	2026-06-13 21:24:22 +02:00
package-manager-cli.ts	feat(coding-agent): add model catalog refresh flag	2026-07-16 12:46:49 +02:00
rpc-entry.ts	fix: rpc-entry and bun support	2026-06-26 10:01:16 +02:00