taodeng/ocp
1
0
Fork 0
mirror of https://github.com/dtzp555-max/ocp.git synced 2026-07-26 15:35:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(docs,test): restore the dropped Opus 4.8 line; assert the window CEILING

Browse Source 
Two review findings from the independent Iron-Rule-10 reviewer, both confirmed
before applying:

1. docs/lan-mode.md: the sample `ocp update` output lost `ocp/claude-opus-4-8`
   entirely — the edit substituted the id instead of inserting the new one, so
   the block listed 6 bullets while line 219 of the same document claims
   "7 models available". Self-contradictory. Restored; the block is 7 again.

2. test-features.mjs: "every contextWindow is 200000" was too rigid and
   contradicted ADR 0009, which states the budget "scales automatically — no
   code change". Asserting every entry turned that documented no-code-change
   path into a must-edit-tests path, and would have failed on a future entry
   with a legitimately SMALLER window. Now asserts the MAX instead: raising the
   ceiling (the actual hazard, since the budget is global) still fails, while a
   smaller-window model stays legal.

Verified the reformulation is strictly better, not just different:
  - raise a window to 1000000  -> 2 failures (ceiling + derivePromptCharBudget SPOT)
  - add a legitimate 128k model -> 452 passed, 0 failed   (old test would have failed here)

Tests: 452 passed, 0 failed.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017gbqUZ8HfBZpjjbzQ85oH8
This commit is contained in:
taodeng
2026-07-26 22:11:45 +10:00
co-authored by Claude Opus 5
parent ca14e6e834
commit 2823f34c7d
2 changed files with 13 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/lan-mode.md
+1
View File
@@ -247,6 +247,7 @@ OCP Connect v1.3.0
Provider: ocp
Models:
• ocp/claude-opus-5
• ocp/claude-opus-4-8
• ocp/claude-opus-4-7
• ocp/claude-opus-4-6
• ocp/claude-sonnet-5
test-features.mjs
+12 -9
View File
@@ -4089,15 +4089,18 @@ test("models.json: claude-opus-5 is present in models[] (the entry this PR adds)
});
// The prompt-char budget is GLOBAL (max across every entry × 3 chars/token), not
// per-model — see lib/prompt.mjs derivePromptCharBudget. A future entry declaring a
// native 1M window would therefore raise the truncation ceiling for claude-haiku-4-5
// too (genuinely 200k), turning OCP-side truncation into an upstream API rejection.
// Adding one is a deliberate ADR-level change; this pins the current invariant.
test("models.json: every contextWindow is 200000 (global prompt-budget invariant)", () => {
for (const m of _spotModels.models) {
assert.equal(m.contextWindow, 200000,
`${m.id} declares contextWindow=${m.contextWindow}; a non-200k entry re-scales MAX_PROMPT_CHARS for ALL models (see lib/prompt.mjs)`);
}
// per-model — see lib/prompt.mjs derivePromptCharBudget. An entry declaring a native 1M
// window would therefore raise the truncation ceiling for claude-haiku-4-5 too (genuinely
// 200k), turning OCP-side truncation into an upstream API rejection.
//
// Asserts the MAX, deliberately, not every entry: ADR 0009 states the budget "scales
// automatically — no code change", so a future entry with a SMALLER window (say a 128k
// model) must stay legal and must not fail this suite. Only raising the ceiling is the
// hazard, and that is an ADR-level decision requiring per-model budgets first.
test("models.json: max contextWindow is 200000 (global prompt-budget ceiling)", () => {
const windows = _spotModels.models.map(m => m.contextWindow);
assert.equal(Math.max(...windows), 200000,
`max contextWindow re-scales MAX_PROMPT_CHARS for ALL models incl. the 200k-native haiku (see lib/prompt.mjs + ADR 0009)`);
});
test("models.json: every aliases value resolves to a real models[].id (referential integrity)", () => {