Commit Graph
9 Commits
Author SHA1 Message Date
kyleandornith-1.5-35b-a3b 91992b9743 loopd: the self-test checks the model's tags against the tokenizer
Co-Authored-By: ornith-1.5-35b-a3b <agent@wntrmute.dev>
2026-09-27 19:08:42 -07:00
kyleandClaude Opus 5.5 2b3ae080b4 proto becomes bxcore, the one shared crate (M5b task 00)
Done the way the owner asked and the spike mapped: the crate and the
manifests renamed, then what the build reported fixed. Layers: 138
"proto unresolved" errors across 169 files; cargo fmt reordering
imports; six fixture paths built as strings in brokerd's and bxctl's
tests, which the compiler cannot see, and comments naming
crates/proto/; the crate-dependency check and its self-test. One more
the spike did not reach: a `\nproto =` key inside a printf format in
the self-test, which a word-boundary replacement skips because `n` and
`p` are both word characters.

make gate: gate: ok, 944 tests; no new entry in /tmp.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-26 01:48:38 -07:00
kyle fd7ade9689 Add the tool port, registry, dispatch and the fake tools
Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
2026-09-18 18:12:45 -07:00
kyle 59cf89e7ba Add the per-slot gate and chat_with_retry
Implemented SlotGate (one request in flight per server slot, FIFO queue,
bounded) and chat_with_retry (retry only server-gone errors, jittered
backoff within a window and attempt budget). chat acquires the gate and
maps GateFull to Busy; Client gained a gate field.

Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
2026-09-18 14:45:45 -07:00
kyle a07c341cbb Add the thinking cap to Client::chat
Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
2026-09-18 14:06:11 -07:00
kyle 60557a0634 Add Client::chat with the first-byte wait, liveness and error mapping
Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
2026-09-18 13:37:01 -07:00
kyle 3663a1e4d5 Add props, slots, tokenize and the cache-loss check to the llama client
Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
2026-09-18 03:39:05 -07:00
kyle 3d876d4fa9 Add the assembler that folds streamed chunks into a completion
Implemented-By: GLM-5.3 (z.ai, default settings) via OpenCode
2026-09-18 02:56:31 -07:00
kyle f48999306e Add the llama client types and the chat request builder
Implemented-By: Laguna S 2.1 (OpenCode)
2026-09-18 02:40:35 -07:00