Commit Graph
6 Commits
Author SHA1 Message Date
Rohit C Prasad 45d58dc9a5 Add LM Studio as a local server provider
Joins llama.cpp and vLLM: address + optional key, window from its own listing.
Based on #434 by zalex666: name, model and help text.
2026-10-25 20:55:44 -07:00
Devika Verma 8f5d404582 Add GLM 5.3 via OpenRouter to the model matrix, sized for the Z.AI host (OPE-215)
The window is the Z.AI endpoint's own 1,048,576 (fp8, 131,072 max output), read from
openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints on 2026-10-01, because Z.AI is the
host a pinned run uses. Without a row the model falls back to DEFAULT_CONTEXT_WINDOW
(128,000) and compacts at 102,400, far inside what the endpoint serves, so any
comparison against a model with a correct row would partly measure compaction.

The matrix size guard moves from 70 to 75 for the three OpenRouter rows added under
OPE-215 (Nemotron 3 Ultra, Nemotron 3.5 Lightning, GLM 5.3). The pruning the guard's
note asks for before another raise is still owed and stays an owner call.
2026-10-02 16:38:50 +05:30
Devika Verma 2515b0b741 Add NVIDIA Nemotron 3 Ultra and 3.5 Lightning via OpenRouter to the model matrix (OPE-215) 2026-10-02 16:38:50 +05:30
Devika Verma 0a6cfcdacc Add Kimi K3 via OpenRouter to the model matrix (1,048,576 context)
Some sandbox hosts cannot reach api.together.xyz but can reach
openrouter.ai, which serves moonshotai/kimi-k3 through Together among other
hosts; a run can pin that host so the serving is unchanged. Row per
openrouter.ai/api/v1/models (read 2026-09-09); effort table gains the
lowercase slug.
2026-09-09 11:27:24 +05:30
Devika Verma 267c562fd1 Refresh Kimi, GLM and DeepSeek context windows from vendor catalogs (OPE-170 p1)
The GLM-5.2 rows (Z.ai, Together, Fireworks, OpenRouter) still carried
128,000 although the model shipped with a 1M window in June; DeepSeek V4 Pro
on Together is 512,000, not 128,000; Kimi K3 on Together is 1,048,576, not
the rounded 1,000,000; Kimi K2.6 / K2.7 Code on Together are 262,144.

Sources, all read 2026-09-08: Together's /v1/models `context_length` for
every Together row (exact, per model), docs.z.ai for the native GLM-5.2 row,
openrouter.ai/z-ai/glm-5.2, fireworks.ai/models/fireworks/glm-5p2. Rows
without a source consulted today (DeepSeek native, Fireworks/OpenRouter
DeepSeek and Kimi K2.6) are left as they were.

Effect: with the 250,000 compaction cap these rows all now compact at
250,000 instead of 102,400. Tests updated with the new values.
2026-09-08 17:52:28 +05:30
Devika Verma 2a5c169ac5 Add Claude 5 rows to the model matrix; warn on the 128k context fallback (OPE-170 p1)
`anthropic:claude-sonnet-5` and `anthropic:claude-fable-5-1` (the models in
active use) had no matrix row, so their context window fell back to the
128,000 guess and auto-compaction fired at 102,400 tokens — a tenth of their
real window — rebuilding the prompt cache each time (observed twice in one
33-minute Sonnet 5 run).

- matrix.py: rows for claude-fable-5-1, claude-opus-5 and claude-sonnet-5
  (1M context, vision + PDF), per platform.claude.com/docs/en/models/overview
  read 2026-09-08.
- engine.py: `_compaction_config` logs one warning per engine when a model
  has no matrix window and the fallback applies, naming the model, the
  assumed window and the resulting trigger.

Tests: tests/test_matrix_current_models.py — the current rows and their
windows; every provider's recommended model is a matrix row (Ollama
excepted) and the ones without a verified window are exactly the known
set (MiniMax M2.5, Muse Spark 1.1); every model in reports/reviewer-eval-*
has a window; trigger arithmetic; the fallback warning fires once for an
unlisted model, not for a listed one, and not when compaction settings
supply a window.
2026-09-08 17:34:07 +05:30