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.
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.
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.
`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.