pjandro/OmniRoute
1
0
Fork 0
mirror of https://github.com/diegosouzapw/OmniRoute.git synced 2026-07-26 09:52:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix(registry): cap gpt-5.5 codex OAuth contextLength at 400K (not 1.05M)

Browse Source 
The codex OAuth backend (chatgpt.com/backend-api/codex/responses) caps
the gpt-5.5 context window at 400 000 tokens, not the 1 050 000 advertised
by the public OpenAI API. Clients reading /v1/models for prompt-budget
math (e.g. Capy computing compression thresholds) would otherwise allow
prompts beyond the OAuth backend's actual capacity, triggering
silent truncation or upstream 400s.

Per-entry override of GPT_5_5_CODEX_CAPABILITIES (which spreads
contextLength=1050000 from the shared constant) — the constant itself
is unchanged because it's also consumed by the github provider's
gpt-5.5 entry where DB sync provides the canonical 400K/128K values.

max_output_tokens=128000 is informational only — the codex OAuth
backend strips max_output_tokens server-side (LiteLLM and Codex CLI
both confirm this). Advertising a realistic value still helps clients
that read it for token-budget heuristics.

References :
- openai/codex#19208 "1M context window gone after GPT-5.5 release"
- openai/codex#19319 — 258 400 effective context window observation
- openai/codex#19464 — Support 1M for GPT-5.5 in Codex (feature ask)
- opencode#24171 — GPT-5.5 Codex 400K vs API 1M
- BerriAI/litellm#21193 — codex backend rejects unsupported params
- openai/codex#4138 — model_max_output_tokens not wired up

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
OmniRoute Ops
2026-05-11 15:34:05 +00:00
parent fa3b6d18ac
commit ef1022e9c8
1 changed files with 9 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
open-sse/config/providerRegistry.ts
View File

@@ -462,11 +462,15 @@ export const REGISTRY: Record<string, RegistryEntry> = {
tokenUrl: "https://auth.openai.com/oauth/token",
},
models: [
{ id: "gpt-5.5", name: "GPT 5.5", ...GPT_5_5_CODEX_CAPABILITIES },
{ id: "gpt-5.5-xhigh", name: "GPT 5.5 (xHigh)", ...GPT_5_5_CODEX_CAPABILITIES },
{ id: "gpt-5.5-high", name: "GPT 5.5 (High)", ...GPT_5_5_CODEX_CAPABILITIES },
{ id: "gpt-5.5-medium", name: "GPT 5.5 (Medium)", ...GPT_5_5_CODEX_CAPABILITIES },
{ id: "gpt-5.5-low", name: "GPT 5.5 (Low)", ...GPT_5_5_CODEX_CAPABILITIES },
// gpt-5.5 codex OAuth backend caps context at 400K (not the public-API
// 1.05M). Public refs : openai/codex#19208, #19319, #19464 ;
// opencode#24171. max_output_tokens is stripped server-side
// (litellm#21193, codex#4138) so 128K is informational only.
{ id: "gpt-5.5", name: "GPT 5.5", ...GPT_5_5_CODEX_CAPABILITIES, contextLength: 400000, maxOutputTokens: 128000 },
{ id: "gpt-5.5-xhigh", name: "GPT 5.5 (xHigh)", ...GPT_5_5_CODEX_CAPABILITIES, contextLength: 400000, maxOutputTokens: 128000 },
{ id: "gpt-5.5-high", name: "GPT 5.5 (High)", ...GPT_5_5_CODEX_CAPABILITIES, contextLength: 400000, maxOutputTokens: 128000 },
{ id: "gpt-5.5-medium", name: "GPT 5.5 (Medium)", ...GPT_5_5_CODEX_CAPABILITIES, contextLength: 400000, maxOutputTokens: 128000 },
{ id: "gpt-5.5-low", name: "GPT 5.5 (Low)", ...GPT_5_5_CODEX_CAPABILITIES, contextLength: 400000, maxOutputTokens: 128000 },
{ id: "gpt-5.4", name: "GPT 5.4", targetFormat: "openai-responses" },
{ id: "gpt-5.4-mini", name: "GPT 5.4 Mini", targetFormat: "openai-responses" },
{ id: "gpt-5.3-codex-spark", name: "GPT 5.3 Codex Spark" },