167 Commits

This Branch

This Branch

All Branches

• v3.9.1: sync src/translate-proxy.py
  admin · 2026-05-24 19:38:31 +00:00
  6d4800fe41
• v3.9.1: Fix Gemini stream hang when model returns only function calls
  admin · 2026-05-24 19:38:28 +00:00
  7234ac7d90
• v3.9.0: add multi-account rotation docs to README
  admin · 2026-05-24 19:33:28 +00:00
  3165658404
• v3.9.0: update CHANGELOG.md
  admin · 2026-05-24 19:32:39 +00:00
  3f3ed516c8
• v3.9.0: update install.sh
  admin · 2026-05-24 19:31:00 +00:00
  82b2e556c4
• v3.9.0: Multi-account changelog + version bump
  admin · 2026-05-24 19:30:49 +00:00
  08f3ab22f9
• v3.9.0: sync src/translate-proxy.py
  admin · 2026-05-24 19:29:44 +00:00
  ff89cd7ac2
• v3.9.0: Multi-account rotation for all OAuth providers
  admin · 2026-05-24 19:29:37 +00:00
  cc06df59aa
• v3.8.5: update install.sh
  admin · 2026-05-24 19:07:30 +00:00
  483691bbe6
• v3.8.5: sync src/translate-proxy.py with x-codebuff headers
  admin · 2026-05-24 19:06:59 +00:00
  140913005c
• v3.8.5: Add x-codebuff-model and x-codebuff-instance-id headers for codebuff API
  admin · 2026-05-24 19:06:48 +00:00
  0039f6c12a
• v3.8.4: Fix codebuff DeepSeek V4 tool-call reasoning_content round-trip

  - Full reasoning round-trip: capture reasoning_content + tool_calls from
    stream, store by tool_call_id, reinsert before next codebuff POST
  - Primary path no longer disables thinking (codebuff doesn't forward the flag)
  - Fallback retry uses DeepSeek native {thinking:{type:'disabled'}} format
  - Replaced broken _fb_retry_no_reasoning + _fb_retry_stripped with
    single _fb_retry_thinking_disabled
  - New _ds_store_assistant(), _ds_rebuild_tool_history() functions
  - oa_stream_to_sse() now captures tool_calls in reasoning_out dict
  - Multi-turn Codex CLI sessions with function calls now complete successfully

  admin · 2026-05-24 21:48:00 +04:00
  8fd6f280f2
• v3.8.3: Fix codebuff streaming — SSE events now reach Codex client

  - Root cause: _handle_codebuff streaming loop collected events but never
    wrote them to self.wfile (stream_buffered_events was not called)
  - Fix: Replaced manual loop with stream_buffered_events() + on_event callback
  - Confirmed working: raw API streaming, non-stream, and stream through proxy
  - Updated CHANGELOG.md, README.md, version labels to 3.8.3

  admin · 2026-05-24 19:30:10 +04:00
  2d4c1a9c2d
• v3.8.1: update CHANGELOG.md + README.md with codebuff docs
  admin · 2026-05-24 16:43:48 +04:00
  e265584af9
• v3.8.1: add .deb package (84KB) + update install.sh
  admin · 2026-05-24 16:41:43 +04:00
  eeaa2e6e19
• v3.8.1: codebuff integration + restore all provider presets

  - Add codebuff backend: free DeepSeek V4 Pro, V4 Flash, Kimi K2.6, MiniMax M2.7
  - codebuff backend auto-manages agent run lifecycle (start/finish)
  - Credential detection from ~/.config/manicode/credentials.json
  - Model-to-agent routing for codebuff free tier
  - Restore all provider presets (Command Code, Crof, OpenAdapter, OpenRouter, etc.)
  - Fix endpoints.json overwritten with only AG X entries
  - Version bump to 3.8.1
  - 54 self-tests passing

  admin · 2026-05-24 16:21:54 +04:00
  2ce0ab516f
• docs: update CHANGELOG, README, GUI changelog for v3.8.0 AI Monitoring

  - CHANGELOG.md: full v3.8.0 section with 3-tier system, 30 fault types, safety guards
  - README.md: AI Monitoring badge, features section, Phase 9 dev journey, troubleshooting rows
  - GUI CHANGELOG: v3.8.0 entry with 9 bullet points

  admin · 2026-05-22 23:22:26 +04:00
  6adabb67e6
• v3.8.0: AI Monitoring — self-healing watchdog with 3-tier response system

  - HealthWatcher thread: monitors proxy /health every 5s
  - LogAnalyzer thread: tails cc-debug.log for 18 failure signal patterns
  - Tier 1 rule engine: 14 rules for instant auto-recovery (< 1s)
  - Tier 2 incident store: JSON pattern database with success rates
  - Tier 3 AI diagnostic agent: calls configurable provider/model for novel failures
  - AIMonitoringWindow GUI: ON/OFF toggle, provider/model/API key selector, incident log
  - 30 fault types catalogued across 5 categories (A-E)
  - Enhanced /health endpoint with memory_mb, uptime_s, requests_total
  - Auto-restart proxy, auto-clear schema cache, kill stale processes
  - Safety: rate-limited AI calls, restart caps, cooldowns per pattern
  - AI Monitoring design spec (AI-MONITORING-DESIGN.md)
  - 54 self-test patterns passing

  admin · 2026-05-22 22:36:16 +04:00
  096d32bebd
• docs: AI Monitoring design spec v3.8.0 — self-healing watchdog with 3-tier response system
  admin · 2026-05-22 22:22:30 +04:00
  a56db90e68
• README: Intelligence Routing — Phase 8 dev journey + features + troubleshooting
  admin · 2026-05-22 16:35:08 +04:00
  9e0da5274e
• v3.7.0: Intelligence Routing — self-healing parser system

  Layer 1 (FIX 23): Deep URL extraction from nested JSON in explore_agent blocks.
  Layer 2 (FIX 24): Auto-proceed on require_escalation / request_escalation_permission.
  Layer 3 (FIX 25): Intent-based command synthesis with 5 heuristics when all parsers fail.
  
  Module-level _build_explore_cmd() for reuse across parser + stream path.
  54 self-test patterns (up from 41).

  admin · 2026-05-22 16:29:45 +04:00
  51b89e6d08
• fix: bare <explore_agent> tags (no closing tag) now trigger URL-based repo exploration fallback, fix _build_explore_cmd name error, add _last_user_urls tracking
  admin · 2026-05-22 16:09:51 +04:00
  979e0199c0
• hotfix: log_message crashes on do_GET — use getattr fallback for _session_id
  admin · 2026-05-22 13:26:03 +04:00
  6e4640eadc
• v3.6.0 — add per-session ID (8-char hex) to all proxy log lines
  admin · 2026-05-22 13:23:13 +04:00
  0cc5bc4b11
• v3.6.0 — bump GUI version label to 3.6.0
  admin · 2026-05-22 13:18:40 +04:00
  fb16a6a66b
• v3.6.0 — Performance & Stability Hardening

  P0: Connection pooling (http.client reuse per host), stream idle timeout
      (300s via selectors) on all streaming paths (OA/CC/Gemini/auto-continue)
  P1: Retry-After header support on all retry paths, preemptive OAuth token
      refresh (5min before expiry)
  P2: oa_convert_tools(strict=) for Responses vs Chat Completions, filter
      null/empty tool names
  P3: Response store TTL (600s eviction), bounded stream buffers (8MB cap),
      response.failed/error urgent flush, dual logging (proxy.log)
  
  .deb: v3.6.0 (71KB) — v3.5.0 and v3.3.0 kept as fallback

  admin · 2026-05-22 13:14:51 +04:00
  ee78d35aa7
• v3.5.0 — Major Release: Command Code Multi-Format Parser, AI Assist, Self-Revive Watchdog

  CC Adapter (17 fixes):
  - Multi-format tool-call parser chain: DSML → bash → explore → XML → raw JSON → fallback
  - Three-tier argument parser (direct/unescape/unicode_escape)
  - Recursive double/triple-wrap unwrapping (_unwrap_cmd)
  - Post-extraction sanitizer validation
  - DSML tag support (current CC model format)
  - Self-revive watchdog (50 restarts, progressive backoff)
  - Debug-to-file logging (cc-debug.log)
  - Inline self-test (19 tests via --self-test)
  - ErrorAnalyzer with 4xx learning on retry
  - Schema cache with 24h TTL
  
  Launcher:
  - AI Assist integration
  - Updated usage dashboard
  - Reasoning controls per-provider
  - Updated cleanup patterns
  
  .deb: v3.5.0 (70KB) — v3.3.0 kept as fallback

  admin · 2026-05-22 10:54:30 +04:00
  4bbfb4ada7
• v3.3.0: fix auto-continue class breakage, add MAX_TOKENS auto-continue for Gemini/Antigravity, bump version label
  Roman · 2026-05-20 22:00:49 +04:00
  e0cad357f2
• v3.3.0: Antigravity OAuth + Gemini CLI OAuth, full Codex agent loop with tool calls, history hardening, SSE fixes
  Roman · 2026-05-20 21:44:33 +04:00
  7aa1f10877
• v3.0.0: ThreadingHTTPServer, dynamic ports, health gating, atomic config, safe cleanup, buffered SSE, batched stats, graceful shutdown
  Roman · 2026-05-20 18:54:47 +04:00
  c0c4d7e420
• v2.7.0: Usage Dashboard redesign (OpenUsage-inspired), TCP_NODELAY streaming, Anthropic prompt caching
  Roman · 2026-05-20 18:11:39 +04:00
  cbd1f558dd
• v2.6.1: rebuild Google OAuth to emulate Gemini CLI

  - Uses Google's public OAuth client_id (no client_secret.json needed)
  - PKCE + CSRF state protection for secure auth
  - Scopes: cloud-platform, generative-language, userinfo
  - Just click OAuth Login -> browser -> authorize -> done
  - Zero setup required

  Roman · 2026-05-20 17:38:08 +04:00
  d55b0322e8
• v2.6.0: Usage Dashboard, per-provider tracking, OAuth file picker

  - Usage Dashboard: visual cards with success rate bars, token stats, latency
  - Per-model breakdown and error tracking per provider
  - Proxy records usage-stats.json after every request
  - Google OAuth: browse for client_secret.json instead of fixed path
  - Auto-copies selected file to ~/.cache/codex-proxy/

  Roman · 2026-05-20 17:23:14 +04:00
  bd4ccf1635
• v2.5.1: adaptive retry for 429/502/503, socket reuse, BGP retry

  - Exponential backoff retry (2s/4s/8s) for rate limits and transient errors
  - BGP routes retry before failing over to next route
  - Socket SO_REUSEADDR prevents 'Address already in use' crashes
  - Connection reset/broken pipe also retried
  - BGP route count shown at proxy startup

  Roman · 2026-05-20 17:10:40 +04:00
  0e70fa47f9
• v2.5.0: AI BGP multi-provider routing with automatic failover

  - New AI BGP pool manager (create/edit/delete pools)
  - Each pool has ordered routes from any configured endpoint
  - Failover: tries primary, falls back to next route on error
  - Pools appear in endpoint dropdown with shuffle icon
  - Pool editor with route add/remove/reorder
  - Fixed TOML breakage from multi-line paste
  - Added OpenAdapter preset with 0G models

  Roman · 2026-05-20 16:40:57 +04:00
  12ca136fba
• v2.4.0: fix TOML breakage from multi-line paste in api_key field
  Roman · 2026-05-20 15:40:29 +04:00
  0f333aab6e
• v2.4.0: OpenAdapter preset uses 0G models only
  Roman · 2026-05-20 15:30:55 +04:00
  dbfc480019
• v2.4.0: add OpenAdapter preset, fix dialog crash, smarter OAuth UX
  Roman · 2026-05-20 15:28:41 +04:00
  866c07c2b5
• v2.3.2: fix Add/Edit dialog crash, smarter Google OAuth UX

  - Fix missing _on_reasoning_toggled method (caused Add button crash)
  - Redesigned Google OAuth flow with proper dialog:
    - Shows clickable auth URL link in dialog
    - Auto-opens browser for Google authorization
    - Live status updates while waiting for callback
    - Success/error shown in dialog (no popup chain)
    - Spinner animation during auth wait
    - Better setup instructions if client_secret.json missing

  Roman · 2026-05-20 15:07:42 +04:00
  ea18535f1c
• v2.3.2: add Google Gemini provider with OAuth support

  - Two presets: API Key and OAuth modes
  - OAuth Login button: full Google OAuth2 flow with auto-refresh
  - Auto-refreshes expired access tokens using refresh_token
  - Gemini OpenAI-compatible endpoint works with existing proxy
  - Models: gemini-2.5-flash, gemini-2.5-pro, gemini-2.0-flash, etc.

  Roman · 2026-05-20 14:45:43 +04:00
  ea60d74527
• v2.3.0: adaptive Crof self-healing system

  - Per-model success/failure tracking with dynamic item limits
  - Proactive compaction when above learned limit
  - Auto-retry on finish_reason=length with aggressive re-compaction
  - Tested: kimi-k2.6 (27 items) and mimo-v2.5-pro both completed
  - All previous fixes included: _ts crash, connection reset, timeout, orphaned fco

  Roman · 2026-05-20 14:32:36 +04:00
  27b22f4fd8
• v2.2.1: add 180s upstream timeout to prevent hanging connections

  - All urlopen() calls now have timeout=180 to prevent infinite hangs
  - Crof upstream can idle between SSE chunks, causing proxy to block forever
  - Tested: kimi-k2.6 + mimo-v2.5-pro both stream completed successfully

  Roman · 2026-05-20 14:04:11 +04:00
  60106955ab
• v2.2.1: fix NameError _ts crash + catch stream disconnect errors

  - Fix NameError: _ts undefined in crof debug logging (caused ALL requests to crash)
  - Catch ConnectionResetError/BrokenPipeError during streaming (graceful client disconnect)
  - Tested: kimi-k2.6 + mimo-v2.5-pro streaming through proxy, both status=completed

  Roman · 2026-05-20 13:54:47 +04:00
  881f4f35d2
• 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