hermes-agent/hermes_cli
teknium1 df0745fb86 fix: improve Kimi model selection — auto-detect endpoint, add missing models
Kimi Coding Plan setup:
- New dedicated _model_flow_kimi() replaces the generic API-key flow
  for kimi-coding. Removes the confusing 'Base URL' prompt entirely —
  the endpoint is auto-detected from the API key prefix:
    sk-kimi-* → api.kimi.com/coding/v1 (Kimi Coding Plan)
    other     → api.moonshot.ai/v1 (legacy Moonshot)

- Shows appropriate models for each endpoint:
    Coding Plan: kimi-for-coding, kimi-k2.5, kimi-k2-thinking, kimi-k2-thinking-turbo
    Moonshot:    full model catalog

- Clears any stale KIMI_BASE_URL override so runtime auto-detection
  via _resolve_kimi_base_url() works correctly.

Model catalog updates:
- Added kimi-for-coding (primary Coding Plan model) and kimi-k2-thinking-turbo
  to models.py, main.py _PROVIDER_MODELS, and model_metadata.py context windows.

- Updated User-Agent from KimiCLI/1.0 to KimiCLI/1.3 (Kimi's coding
  endpoint whitelists known coding agents via User-Agent sniffing).
2026-03-12 05:57:08 -07:00
..
__init__.py
auth.py refactor: remove LLM_MODEL env var dependency — config.yaml is sole source of truth 2026-03-11 22:04:42 -07:00
banner.py
callbacks.py
checklist.py fix: skip hanging tests + add global test timeout 2026-03-12 01:23:28 -07:00
clipboard.py
codex_models.py
colors.py
commands.py
config.py merge: resolve conflicts with origin/main 2026-03-12 00:29:04 -07:00
cron.py
curses_ui.py
doctor.py fix(doctor): skip /models health check for MiniMax providers 2026-03-11 08:29:35 -07:00
gateway.py
main.py fix: improve Kimi model selection — auto-detect endpoint, add missing models 2026-03-12 05:57:08 -07:00
models.py fix: improve Kimi model selection — auto-detect endpoint, add missing models 2026-03-12 05:57:08 -07:00
pairing.py
runtime_provider.py
setup.py merge: resolve conflicts with origin/main 2026-03-12 00:29:04 -07:00
skills_config.py
skills_hub.py
skin_engine.py
status.py
tools_config.py
uninstall.py