diff --git a/.gitignore b/.gitignore
index 8656541..1ee3996 100644
--- a/.gitignore
+++ b/.gitignore
@@ -37,3 +37,4 @@ __pycache__/
 # Editor/OS noise
 *.swp
 .DS_Store
+third_party/
diff --git a/serverAppConfigs-docs/LLM/halogen-flash-server.md b/serverAppConfigs-docs/LLM/halogen-flash-server.md
index 73d3192..8d7f374 100644
--- a/serverAppConfigs-docs/LLM/halogen-flash-server.md
+++ b/serverAppConfigs-docs/LLM/halogen-flash-server.md
@@ -340,6 +340,16 @@ deployment:
   request is a 400 rather than a silent truncation. `max_tokens`,
   `max_completion_tokens` and `max_output_tokens` all work and must agree if
   more than one is sent.
+- **A budget above (window − compaction-threshold) is a guaranteed 400 zone.**
+  The fit check (`prompt + max_tokens <= HALOGEN_CTX`) refuses, and the harness
+  only compacts at its own threshold — with OMP at 70 % of a 200,192 window
+  (140,134), any prompt in (136,192, 140,134] with a 64,000 budget overflows
+  the window while sitting below the compaction trigger. That collided live on
+  2026-09-17 (prompt 138,898 + 64,000 = 202,898 > 200,192). The fix is
+  harness-side: keep the declared `maxTokens` at or under
+  `window − threshold` (57,344 chosen) so no pre-compaction request can miss
+  the fit check. Do not fix it by raising `HALOGEN_CTX` past pool/2 — that
+  breaks the two-resident-conversations property.
 - **`reasoning_effort`** is accepted at the top level and inside
   `chat_template_kwargs`: `minimal`, `low`, `medium`, `high`, `xhigh`. The
   model's default is `xhigh`. `minimal` aliases the template's `low` and still