24 Commits

This Branch

This Branch

All Branches

• v2.2.1: fix compaction orphaning tool outputs (tested, all 8 tests pass)

  - Compaction now walks tail boundary past fc/fco/assistant to keep pairs intact
  - All 8 pipeline tests pass: compaction, message translation, 5 Crof models
  - reasoning_effort=none confirmed working: 0 reasoning on mimo/kimi/deepseek
  - No orphaned function_call_output items after compaction

  Roman · 2026-05-20 13:23:06 +04:00
  0a3cd3fd7a
• v2.2.1: fix compaction orphaning tool outputs causing Crof incomplete

  - Fix compaction cutting between function_call and function_call_output pairs
  - Orphaned tool results confused Crof models causing finish_reason=length
  - reasoning_effort=none now always sends enable_thinking=false too
  - Added Crof upstream debug logging

  Roman · 2026-05-20 13:14:40 +04:00
  6c67642522
• v2.2.0: styled reasoning switch + error handling for dialogs

  - Reasoning switch: green ON, orange OFF, gentle rounded pill shape
  - Error handling on Add/Edit/Manage Endpoints dialogs
  - Updated CHANGELOG.md

  Roman · 2026-05-20 12:59:04 +04:00
  9bcb6998e0
• v2.2.0: style reasoning switch green=ON, orange=OFF with gentle rounded look
  Roman · 2026-05-20 12:28:33 +04:00
  96bf00213c
• v2.2.0: per-provider reasoning controls (on/off + effort level)

  - Add Reasoning On/Off toggle and Effort selector in endpoint editor
  - Proxy sends enable_thinking=false when reasoning is OFF
  - Proxy sends reasoning_effort level when reasoning is ON
  - Strip reasoning_content from output, force max_tokens=64000 minimum
  - Fixes Crof mimo-v2.5-pro and similar reasoning model token exhaustion

  Roman · 2026-05-20 12:20:33 +04:00
  9532ba40f3
• v2.1.3: fix Crof mimo-v2.5-pro reasoning_content token exhaustion

  - Strip reasoning_content from proxy output (Codex doesn't use it)
  - Force max_tokens=64000 minimum for openai-compat providers
  - Prevents models that emit large reasoning from running out of tokens

  admin · 2026-05-19 21:59:38 +04:00
  77423c5c35
• feat: auto-compaction for long conversations (like Claude Code/Codex /compact)

  Instead of just truncating old items, the proxy now auto-compacts
  them into a structured summary preserving key context:
  - User requests, assistant responses, tool calls made, files touched
  - Keeps original query + system messages + last 10 recent items
  - 38 items -> 14 items in testing, with summary of dropped turns
  - Similar to Claude Code's auto-compact and Codex CLI's /compact
  - No extra API calls needed, instant, zero cost

  admin · 2026-05-19 21:49:55 +04:00
  662d8e961e
• fix: truncate large tool outputs to prevent Crof incomplete responses

  Crof models (mimo, deepseek-v4-pro) return status=incomplete when
  tool results contain too much text (e.g. full HTML pages at 8500+ tokens).
  Auto-truncate tool outputs exceeding 8000 chars with truncation notice.
  Combined with the 30-item conversation trim from previous commit.

  admin · 2026-05-19 21:37:34 +04:00
  c90912ed07
• fix: Crof multi-turn tool calls + auto-trim long conversations

  Root cause: Codex sends function_call items with id=None, causing
  tool_call_id mismatch between tool calls and tool results. Proxy now
  resolves IDs by call_id + positional fallback.
  
  Auto-trim: conversations exceeding 30 items are trimmed automatically,
  keeping system messages, original user query, and most recent items.
  This prevents context overflow on providers with smaller context
  windows (Crof mimo-v2.5-pro stops responding at ~40 items).
  
  - Fix None tool IDs in oa_input_to_messages with positional matching
  - Auto-trim input to 30 items max (keeps head + tail)
  - Add request/response logging to ~/.cache/codex-proxy/requests.log
  - Proxy stderr visible in launcher terminal for debugging
  - v2.1.2

  admin · 2026-05-19 21:25:35 +04:00
  aa377024d9
• fix: add previous_response_id support for multi-turn tool calls (Crof fix)

  Codex Desktop uses previous_response_id to chain conversation turns.
  Without storing and resolving these, the proxy sent only the new
  function_call_output to upstream providers, missing the original user
  message and assistant tool call. This caused Crof.ai (and any provider
  using tool calls) to stop after the first response.
  
  - Add in-memory response store (50 entry LRU) keyed by response ID
  - resolve_previous_response() reconstructs full input chain on multi-turn
  - Fix orphan message output item when response has only tool calls
  - Applies to all backends: openai-compat, anthropic, command-code
  - v2.1.2

  admin · 2026-05-19 20:38:39 +04:00
  cb6381afe4
• fix: merge consecutive tool_calls into single assistant message for Crof/OpenAI-compat
  admin · 2026-05-19 19:48:40 +04:00
  389866a2c6
• add Command Code to Problem table in README
  admin · 2026-05-19 19:04:39 +04:00
  13a12d0763
• update CHANGELOG + README for Command Code backend
  admin · 2026-05-19 19:01:28 +04:00
  6596404d4b
• fix CC: use real UUID for threadId
  admin · 2026-05-19 18:41:22 +04:00
  df4f852566
• fix CC: map system->user, content string->array, strip tools, fix threadId UUID
  admin · 2026-05-19 18:38:00 +04:00
  573b640f91
• fix Command Code 403: add cc_version field + x-command-code-version header
  admin · 2026-05-19 18:28:56 +04:00
  ba9831db2d
• revert persona feature (caused MCP timeout), keep Command Code backend + developer role fix
  admin · 2026-05-19 18:12:00 +04:00
  a2dde4d331
• v2.2.0: agent persona selector, Command Code backend, per-provider identity
  admin · 2026-05-19 17:39:54 +04:00
  c176fb088d
• v2.1.1: fix developer role mapping for DeepSeek and other providers
  admin · 2026-05-19 17:12:07 +04:00
  ccc3054793
• v2.1.0: add Codex auth status detection and re-login
  admin · 2026-05-19 16:45:41 +04:00
  772255a188
• v2.0.1: Add Codex CLI/Desktop installation verifier

  - Detects codex CLI (via 'which codex' + --version) and Desktop (via /opt/codex-desktop/start.sh)
  - Shows green ✔ or yellow ✘ status bar on main page
  - 'Install' button opens guide dialog with install commands
  - Desktop/CLI launch buttons disabled when corresponding tool is missing
  - Dependency status logged on startup
  - _set_busy respects missing-state (won't re-enable disabled buttons)
  - Rebuilt .deb as v2.0.1

  admin · 2026-05-19 15:32:44 +04:00
  ac24fe6372
• Add in-app changelog viewer and repo CHANGELOG.md

  - Added CHANGELOG constant to launcher with version history
  - Added 'Changelog' button to header bar (opens formatted dialog)
  - Title bar now shows version number (v2.0.0)
  - Added CHANGELOG.md to repo root
  - Rebuilt .deb with latest sources

  admin · 2026-05-19 15:24:49 +04:00
  50ba552635
• Add .deb installer package (codex-launcher 2.0.0)

  - Installs to /usr/lib/codex-launcher/ with wrapper scripts in /usr/bin/
  - Desktop entry in /usr/share/applications/
  - Depends: python3, python3-gi, gir1.2-gtk-3.0, curl, lsof, bash
  - Postinst: creates config dirs, updates desktop database
  - Prerm: stops running launcher/proxy, optionally purges cache

  admin · 2026-05-19 15:19:44 +04:00
  c70c506452
• Initial commit: Codex Launcher — Any AI Provider

  Multi-provider integration for OpenAI Codex CLI/Desktop.
  
  - Translation proxy: Responses API ↔ Chat Completions / Anthropic Messages
  - GTK launcher with endpoint management, provider presets, Desktop/CLI launch
  - Codex Default mode (built-in OAuth, zero config)
  - Browser UA injection for Cloudflare-protected providers
  - Streaming SSE, tool calls, reasoning content support
  - Profile backup/import, model auto-fetch, bulk import
  - Zero pip dependencies (pure Python stdlib + GTK)

  admin · 2026-05-19 14:57:31 +04:00
  d1fef5d984