fix: make OpenAI fallback context window configurable + support external model lookup (#861)

* fix: make OpenAI fallback context window configurable and support external lookup table

Unknown OpenAI-compatible models fell back to a hardcoded 128k constant,
causing auto-compact to fire prematurely on models with larger windows
(issue #635 follow-up). Two escape hatches are added without touching the
built-in table:

- CLAUDE_CODE_OPENAI_FALLBACK_CONTEXT_WINDOW (number): overrides the 128k
  default for all unknown models.
- CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS (JSON object): per-model overrides that
  take precedence over the built-in OPENAI_CONTEXT_WINDOWS table; supports
  the same provider-qualified and prefix-matching lookup as the built-in path.
- CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS (JSON object): same pattern for output
  token limits.

This lets operators deploy new or private models without patching
openaiContextWindows.ts on every model release.

* docs: add new OpenAI context window env vars to .env.example

Document CLAUDE_CODE_OPENAI_FALLBACK_CONTEXT_WINDOW,
CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS, and
CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS with usage examples.

Addresses reviewer feedback on PR #861.

---------

Co-authored-by: opencode <dev@example.com>

.env.example

@@ -149,6 +149,23 @@ ANTHROPIC_API_KEY=sk-ant-your-key-here
 # Use a custom OpenAI-compatible endpoint (optional — defaults to api.openai.com)
 # OPENAI_BASE_URL=https://api.openai.com/v1
 
+# Fallback context window size (tokens) when the model is not found in the
+# built-in table (default: 128000). Increase this for models with larger
+# context windows (e.g. 200000 for Claude-sized contexts).
+# CLAUDE_CODE_OPENAI_FALLBACK_CONTEXT_WINDOW=128000
+
+# Per-model context window overrides as a JSON object.
+# Takes precedence over the built-in table, so you can register new or
+# custom models without patching source.
+# Example: CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS={"my-corp/llm-v3":262144,"gpt-4o-mini":128000}
+# CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS=
+
+# Per-model maximum output token overrides as a JSON object.
+# Use this alongside CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS when your model
+# supports a different output limit than what the built-in table specifies.
+# Example: CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS={"my-corp/llm-v3":8192}
+# CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS=
+
 
 # -----------------------------------------------------------------------------
 # Option 3: Google Gemini

src/utils/context.ts

@@ -12,7 +12,12 @@ export const MODEL_CONTEXT_WINDOW_DEFAULT = 200_000
 // Fallback context window for unknown 3P models. Must be large enough that
 // the effective context (this minus output token reservation) stays positive,
 // otherwise auto-compact fires on every message (issue #635).
-export const OPENAI_FALLBACK_CONTEXT_WINDOW = 128_000
+// Override via CLAUDE_CODE_OPENAI_FALLBACK_CONTEXT_WINDOW env var to avoid
+// hardcoding when deploying models not yet in openaiContextWindows.ts.
+export const OPENAI_FALLBACK_CONTEXT_WINDOW = (() => {
+  const v = parseInt(process.env.CLAUDE_CODE_OPENAI_FALLBACK_CONTEXT_WINDOW ?? '', 10)
+  return !isNaN(v) && v > 0 ? v : 128_000
+})()
 
 // Maximum output tokens for compact operations
 export const COMPACT_MAX_OUTPUT_TOKENS = 20_000

src/utils/model/openaiContextWindows.ts

@@ -413,16 +413,51 @@ const OPENAI_MAX_OUTPUT_TOKENS: Record<string, number> = {
   'moonshot-v1-128k':          32_768,
 }
 
-function lookupByModel<T>(table: Record<string, T>, model: string): T | undefined {
+// External context-window overrides loaded once at startup.
+// Set CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS to a JSON object mapping model name
+// → context-window token count to add or override entries without editing
+// this file.  Example:
+//   CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS='{"my-corp/llm-v2":200000}'
+const OPENAI_EXTERNAL_CONTEXT_WINDOWS: Record<string, number> = (() => {
+  try {
+    const raw = process.env.CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS
+    if (raw) {
+      const parsed = JSON.parse(raw)
+      if (typeof parsed === 'object' && parsed !== null) return parsed as Record<string, number>
+    }
+  } catch { /* ignore malformed JSON */ }
+  return {}
+})()
+
+// External max-output-token overrides.
+// Set CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS to a JSON object mapping model name
+// → max output token count.
+const OPENAI_EXTERNAL_MAX_OUTPUT_TOKENS: Record<string, number> = (() => {
+  try {
+    const raw = process.env.CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS
+    if (raw) {
+      const parsed = JSON.parse(raw)
+      if (typeof parsed === 'object' && parsed !== null) return parsed as Record<string, number>
+    }
+  } catch { /* ignore malformed JSON */ }
+  return {}
+})()
+
+function lookupByModel<T>(table: Record<string, T>, externalTable: Record<string, T>, model: string): T | undefined {
   // Try provider-qualified key first: "{OPENAI_MODEL}:{model}" so that
   // e.g. "github:copilot:claude-haiku-4.5" can have different limits than
   // a bare "claude-haiku-4.5" served by another provider.
   const providerModel = process.env.OPENAI_MODEL?.trim()
   if (providerModel && providerModel !== model) {
     const qualified = `${providerModel}:${model}`
+    // External table takes precedence over the built-in table.
+    const externalQualified = lookupByKey(externalTable, qualified)
+    if (externalQualified !== undefined) return externalQualified
     const qualifiedResult = lookupByKey(table, qualified)
     if (qualifiedResult !== undefined) return qualifiedResult
   }
+  const externalResult = lookupByKey(externalTable, model)
+  if (externalResult !== undefined) return externalResult
   return lookupByKey(table, model)
 }
 
@@ -446,7 +481,7 @@ function lookupByKey<T>(table: Record<string, T>, model: string): T | undefined
  * "gpt-4o-2024-11-20" resolve to the base "gpt-4o" entry.
  */
 export function getOpenAIContextWindow(model: string): number | undefined {
-  return lookupByModel(OPENAI_CONTEXT_WINDOWS, model)
+  return lookupByModel(OPENAI_CONTEXT_WINDOWS, OPENAI_EXTERNAL_CONTEXT_WINDOWS, model)
 }
 
 /**
@@ -454,5 +489,5 @@ export function getOpenAIContextWindow(model: string): number | undefined {
  * Returns undefined if the model is not in the table.
  */
 export function getOpenAIMaxOutputTokens(model: string): number | undefined {
-  return lookupByModel(OPENAI_MAX_OUTPUT_TOKENS, model)
+  return lookupByModel(OPENAI_MAX_OUTPUT_TOKENS, OPENAI_EXTERNAL_MAX_OUTPUT_TOKENS, model)
 }