chore(main): release 0.2.3 (#638)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

.github/workflows/release.yml

@@ -4,9 +4,6 @@ on:
   push:
     branches:
       - main
-  release:
-    types:
-      - published
 
 concurrency:
   group: auto-release-${{ github.ref }}
@@ -15,7 +12,6 @@ concurrency:
 jobs:
   release-please:
     name: Release Please
-    if: ${{ github.event_name == 'push' }}
     runs-on: ubuntu-latest
     permissions:
       contents: write
@@ -34,7 +30,8 @@ jobs:
 
   publish-npm:
     name: Publish to npm
-    if: ${{ github.event_name == 'release' }}
+    needs: release-please
+    if: ${{ needs.release-please.outputs.release_created == 'true' }}
     runs-on: ubuntu-latest
     environment: release
     permissions:
@@ -44,7 +41,7 @@ jobs:
       - name: Checkout release tag
         uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
         with:
-          ref: ${{ github.event.release.tag_name }}
+          ref: ${{ needs.release-please.outputs.tag_name }}
           fetch-depth: 0
 
       - name: Set up Node.js
@@ -84,8 +81,8 @@ jobs:
       - name: Release summary
         run: |
           {
-            echo "## Released ${{ github.event.release.tag_name }}"
+            echo "## Released ${{ needs.release-please.outputs.tag_name }}"
             echo
             echo "- npm: https://www.npmjs.com/package/@gitlawb/openclaude"
-            echo "- GitHub: https://github.com/Gitlawb/openclaude/releases/tag/${{ github.event.release.tag_name }}"
+            echo "- GitHub: https://github.com/Gitlawb/openclaude/releases/tag/${{ needs.release-please.outputs.tag_name }}"
           } >> "$GITHUB_STEP_SUMMARY"

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.2.1"
+  ".": "0.2.3"
 }

CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## [0.2.3](https://github.com/Gitlawb/openclaude/compare/v0.2.2...v0.2.3) (2026-04-12)
+
+
+### Bug Fixes
+
+* prevent infinite auto-compact loop for unknown 3P models ([#635](https://github.com/Gitlawb/openclaude/issues/635)) ([#636](https://github.com/Gitlawb/openclaude/issues/636)) ([aeaa658](https://github.com/Gitlawb/openclaude/commit/aeaa658f776fb8df95721e8b8962385f8b00f66a))
+
+## [0.2.2](https://github.com/Gitlawb/openclaude/compare/v0.2.1...v0.2.2) (2026-04-12)
+
+
+### Bug Fixes
+
+* **read/edit:** make compact line prefix unambiguous for tab-indented files ([#613](https://github.com/Gitlawb/openclaude/issues/613)) ([08cc6f3](https://github.com/Gitlawb/openclaude/commit/08cc6f328711cd93ce9fa53351266c29a0b0a341))
+
 ## [0.2.1](https://github.com/Gitlawb/openclaude/compare/v0.2.0...v0.2.1) (2026-04-12)
 
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gitlawb/openclaude",
-  "version": "0.2.1",
+  "version": "0.2.3",
   "description": "Claude Code opened to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models",
   "type": "module",
   "bin": {

src/services/compact/autoCompact.test.ts

@@ -0,0 +1,46 @@
+import { describe, expect, test } from 'bun:test'
+import {
+  getEffectiveContextWindowSize,
+  getAutoCompactThreshold,
+} from './autoCompact.ts'
+
+describe('getEffectiveContextWindowSize', () => {
+  test('returns positive value for known models with large context windows', () => {
+    // claude-sonnet-4 has 200k context
+    const effective = getEffectiveContextWindowSize('claude-sonnet-4')
+    expect(effective).toBeGreaterThan(0)
+  })
+
+  test('never returns negative even for unknown 3P models (issue #635)', () => {
+    // Previously, unknown 3P models got 8k context → effective context was
+    // 8k minus 20k summary reservation = -12k, causing infinite auto-compact.
+    // Now the fallback is 128k and there's a floor, so effective is always
+    // at least reservedTokensForSummary + buffer.
+    process.env.CLAUDE_CODE_USE_OPENAI = '1'
+    try {
+      const effective = getEffectiveContextWindowSize('some-unknown-3p-model')
+      expect(effective).toBeGreaterThan(0)
+      // Must be at least summary reservation (20k) + buffer (13k) = 33k
+      expect(effective).toBeGreaterThanOrEqual(33_000)
+    } finally {
+      delete process.env.CLAUDE_CODE_USE_OPENAI
+    }
+  })
+})
+
+describe('getAutoCompactThreshold', () => {
+  test('returns positive threshold for known models', () => {
+    const threshold = getAutoCompactThreshold('claude-sonnet-4')
+    expect(threshold).toBeGreaterThan(0)
+  })
+
+  test('never returns negative threshold even for unknown 3P models (issue #635)', () => {
+    process.env.CLAUDE_CODE_USE_OPENAI = '1'
+    try {
+      const threshold = getAutoCompactThreshold('some-unknown-3p-model')
+      expect(threshold).toBeGreaterThan(0)
+    } finally {
+      delete process.env.CLAUDE_CODE_USE_OPENAI
+    }
+  })
+})

src/services/compact/autoCompact.ts

@@ -45,7 +45,12 @@ export function getEffectiveContextWindowSize(model: string): number {
     }
   }
 
-  return contextWindow - reservedTokensForSummary
+  // Floor: effective context must be at least the summary reservation plus a
+  // usable buffer. If it goes lower, the auto-compact threshold becomes
+  // negative and fires on every message (issue #635).
+  const autocompactBuffer = 13_000 // must match AUTOCOMPACT_BUFFER_TOKENS
+  const effectiveContext = contextWindow - reservedTokensForSummary
+  return Math.max(effectiveContext, reservedTokensForSummary + autocompactBuffer)
 }
 
 export type AutoCompactTrackingState = {

src/tools/FileEditTool/prompt.ts

@@ -11,7 +11,7 @@ export function getEditToolDescription(): string {
 
 function getDefaultEditDescription(): string {
   const prefixFormat = isCompactLinePrefixEnabled()
-    ? 'line number + tab'
+    ? 'line number + arrow'
     : 'spaces + line number + arrow'
   const minimalUniquenessHint =
     process.env.USER_TYPE === 'ant'

src/utils/context.test.ts

@@ -107,9 +107,23 @@ test('MiniMax-M2.7 uses explicit provider-specific context and output caps', ()
   expect(getMaxOutputTokensForModel('MiniMax-M2.7')).toBe(131_072)
 })
 
-test('unknown openai-compatible models still use the conservative fallback window', () => {
+test('unknown openai-compatible models use the 128k fallback window (not 8k, see #635)', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
 
-  expect(getContextWindowForModel('some-unknown-3p-model')).toBe(8_000)
+  expect(getContextWindowForModel('some-unknown-3p-model')).toBe(128_000)
+})
+
+test('MiniMax-M2.5 and M2.1 use explicit provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('MiniMax-M2.5')).toBe(204_800)
+  expect(getContextWindowForModel('MiniMax-M2.5-highspeed')).toBe(204_800)
+  expect(getContextWindowForModel('MiniMax-M2.1')).toBe(204_800)
+  expect(getContextWindowForModel('MiniMax-M2.1-highspeed')).toBe(204_800)
+  expect(getModelMaxOutputTokens('MiniMax-M2.5')).toEqual({
+    default: 131_072,
+    upperLimit: 131_072,
+  })
 })

src/utils/context.ts

@@ -9,6 +9,11 @@ import { getOpenAIContextWindow, getOpenAIMaxOutputTokens } from './model/openai
 // Model context window size (200k tokens for all models right now)
 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
+
 // Maximum output tokens for compact operations
 export const COMPACT_MAX_OUTPUT_TOKENS = 20_000
 
@@ -73,8 +78,9 @@ export function getContextWindowForModel(
   }
 
   // OpenAI-compatible provider — use known context windows for the model.
-  // Unknown models get a conservative 8k default so auto-compact triggers
-  // before hitting a hard context_window_exceeded error.
+  // Unknown models get a conservative 128k default. This was previously 8k,
+  // but that caused auto-compact to fire on every turn because the effective
+  // context (8k minus output reservation) became negative (issue #635).
   const isOpenAIProvider =
     isEnvTruthy(process.env.CLAUDE_CODE_USE_OPENAI) ||
     isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI) ||
@@ -86,10 +92,10 @@ export function getContextWindowForModel(
       return openaiWindow
     }
     console.error(
-      `[context] Warning: model "${model}" not in context window table — using conservative 8k default. ` +
+      `[context] Warning: model "${model}" not in context window table — using conservative 128k default. ` +
       'Add it to src/utils/model/openaiContextWindows.ts for accurate compaction.',
     )
-    return 8_000
+    return OPENAI_FALLBACK_CONTEXT_WINDOW
   }
 
   const cap = getModelCapability(model)

src/utils/file.test.ts

@@ -0,0 +1,51 @@
+import { afterEach, describe, expect, mock, test } from 'bun:test'
+
+async function importFileModuleWithKillswitchEnabled(
+  killswitchEnabled: boolean,
+) {
+  mock.module('../services/analytics/growthbook.js', () => ({
+    getFeatureValue_CACHED_MAY_BE_STALE: () => killswitchEnabled,
+  }))
+
+  return import(`./file.js?ts=${Date.now()}-${Math.random()}`)
+}
+
+afterEach(() => {
+  mock.restore()
+})
+
+describe('addLineNumbers', () => {
+  test('uses unambiguous arrow compact prefix and preserves leading tabs', async () => {
+    const { addLineNumbers } = await importFileModuleWithKillswitchEnabled(false)
+
+    const result = addLineNumbers({
+      content: '\tfirst\n\t\tsecond',
+      startLine: 41,
+    })
+
+    expect(result).toBe('41→\tfirst\n42→\t\tsecond')
+  })
+
+  test('keeps padded arrow format when compact mode is disabled', async () => {
+    const { addLineNumbers } = await importFileModuleWithKillswitchEnabled(true)
+
+    const result = addLineNumbers({
+      content: 'alpha\nbeta',
+      startLine: 1,
+    })
+
+    expect(result).toBe('     1→alpha\n     2→beta')
+  })
+})
+
+describe('stripLineNumberPrefix', () => {
+  test('strips compact arrow, padded arrow, and legacy tab prefixes', async () => {
+    const { stripLineNumberPrefix } = await importFileModuleWithKillswitchEnabled(
+      false,
+    )
+
+    expect(stripLineNumberPrefix('41→\tfirst')).toBe('\tfirst')
+    expect(stripLineNumberPrefix('     2→beta')).toBe('beta')
+    expect(stripLineNumberPrefix('7\t\tlegacy-tab')).toBe('\tlegacy-tab')
+  })
+})

src/utils/file.ts

@@ -267,7 +267,7 @@ export async function suggestPathUnderCwd(
 }
 
 /**
- * Whether to use the compact line-number prefix format (`N\t` instead of
+ * Whether to use the compact line-number prefix format (`N→` instead of
  * `     N→`). The padded-arrow format costs 9 bytes/line overhead; at
  * 1.35B Read calls × 132 lines avg this is 2.18% of fleet uncached input
  * (bq-queries/read_line_prefix_overhead_verify.sql).
@@ -303,7 +303,7 @@ export function addLineNumbers({
 
   if (isCompactLinePrefixEnabled()) {
     return lines
-      .map((line, index) => `${index + startLine}\t${line}`)
+      .map((line, index) => `${index + startLine}→${line}`)
       .join('\n')
   }
 

src/utils/model/openaiContextWindows.ts

@@ -104,9 +104,19 @@ const OPENAI_CONTEXT_WINDOWS: Record<string, number> = {
   'devstral-latest':          256_000,
   'ministral-3b-latest':      256_000,
 
-  // MiniMax
+  // MiniMax (all M2.x variants share 204,800 context, 131,072 max output)
   'MiniMax-M2.7':             204_800,
+  'MiniMax-M2.7-highspeed':   204_800,
+  'MiniMax-M2.5':             204_800,
+  'MiniMax-M2.5-highspeed':   204_800,
+  'MiniMax-M2.1':             204_800,
+  'MiniMax-M2.1-highspeed':   204_800,
   'minimax-m2.7':             204_800,
+  'minimax-m2.7-highspeed':   204_800,
+  'minimax-m2.5':             204_800,
+  'minimax-m2.5-highspeed':   204_800,
+  'minimax-m2.1':             204_800,
+  'minimax-m2.1-highspeed':   204_800,
 
   // Google (via OpenRouter)
   'google/gemini-2.0-flash':1_048_576,
@@ -223,9 +233,19 @@ const OPENAI_MAX_OUTPUT_TOKENS: Record<string, number> = {
   'mistral-large-latest':     32_768,
   'mistral-small-latest':     32_768,
 
-  // MiniMax
+  // MiniMax (all M2.x variants share 131,072 max output)
   'MiniMax-M2.7':            131_072,
+  'MiniMax-M2.7-highspeed':  131_072,
+  'MiniMax-M2.5':            131_072,
+  'MiniMax-M2.5-highspeed':  131_072,
+  'MiniMax-M2.1':            131_072,
+  'MiniMax-M2.1-highspeed':  131_072,
   'minimax-m2.7':            131_072,
+  'minimax-m2.7-highspeed':  131_072,
+  'minimax-m2.5':            131_072,
+  'minimax-m2.5-highspeed':  131_072,
+  'minimax-m2.1':            131_072,
+  'minimax-m2.1-highspeed':  131_072,
 
   // Google (via OpenRouter)
   'google/gemini-2.0-flash':   8_192,