Repository files (latest commit first)

Filename	Latest commit message	Latest commit date
Meta Vens 4fe1fc963c Encoder: apply the Llama-3 chat header explicitly, and pin the identity at the worker's call site ... The child wraps every text with text_encoding.chat_header and tokenizes it itself, so the prompt form no longer rides on the model's _name_or_path. The identity names the assembly truthfully (header form included, as a hash of the template) and re-keys the cache. The worker builds its identity through live_identity and installed_versions, which the tests reach; the identity test now uses live-length revisions, so a truncated identity or key fails. An env-gated test compares a fresh child vector with Kimodo's own encoder loaded from the repo ids. Supersedes encoder-assembly-b (motion-pipeline:ruling:encoder-chat-header-on). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>		2026-10-23 17:20:01 +02:00
..
fixtures	Daemon: drop the unread worker.model; tests for grace, host default, relative models root, early death	2026-10-23 15:07:15 +02:00
kimodo-resident-worker.py	Encoder: apply the Llama-3 chat header explicitly, and pin the identity at the worker's call site	2026-10-23 17:20:01 +02:00
kimodo-text-encode.py	Encoder: apply the Llama-3 chat header explicitly, and pin the identity at the worker's call site	2026-10-23 17:20:01 +02:00
test-vili-daemon.mjs	Test: the retired provider-advertisement route answers 404	2026-10-23 15:28:55 +02:00
test_text_encoding.py	Encoder: apply the Llama-3 chat header explicitly, and pin the identity at the worker's call site	2026-10-23 17:20:01 +02:00
text_encoding.py	Encoder: apply the Llama-3 chat header explicitly, and pin the identity at the worker's call site	2026-10-23 17:20:01 +02:00
vili-daemon.mjs	Daemon: drop the unread worker.model; tests for grace, host default, relative models root, early death	2026-10-23 15:07:15 +02:00