Skip to content

Releases: icebear0828/codex-proxy

2.0.71-beta.f022ae1

08 May 06:08
f022ae1

Choose a tag to compare

2.0.71-beta.f022ae1 Pre-release
Pre-release
  • fix(proxy): use global proxy for WS fallback
  • fix(proxy): close implicit-resume reverse mismatch + surface 4xx errors (#450)
  • fix(translation): preserve OpenAI function tool strict (#441)
  • feat(dev): tee stdout/stderr to logs/dev-YYYY-MM-DD.log (#444)
  • perf(proxy): WebSocket keepalive ping prevents middlebox idle drops (#442)
  • feat(proxy): WebSocket connection pool fixes prompt-cache hit-rate jitter (#440)
  • feat(dashboard): range hit-rate card + chart panel + 5min granularity, proxy diag logs (#439)
  • fix(self-update): guard against non-master branch and dirty tree (#438)
  • fix(translation): hint upstream model to omit empty pages on Read tool (#437)
  • feat: implicit resume via effectiveConversationId for chat/gemini routes (#432)
  • fix: correct Ollama context metadata for GPT-5.5 and GPT-5.4 models (#420)
  • fix(ci): checkout master in bump-electron.yml (#427)
  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor (#430)

2.0.70

07 May 18:03

Choose a tag to compare

  • feat(dev): tee stdout/stderr to logs/dev-YYYY-MM-DD.log (#444)
  • perf(proxy): WebSocket keepalive ping prevents middlebox idle drops (#442)
  • feat(proxy): WebSocket connection pool fixes prompt-cache hit-rate jitter (#440)
  • feat(dashboard): range hit-rate card + chart panel + 5min granularity, proxy diag logs (#439)
  • fix(self-update): guard against non-master branch and dirty tree (#438)
  • fix(translation): hint upstream model to omit empty pages on Read tool (#437)
  • feat: implicit resume via effectiveConversationId for chat/gemini routes (#432)
  • fix: correct Ollama context metadata for GPT-5.5 and GPT-5.4 models (#420)
  • fix(ci): checkout master in bump-electron.yml (#427)
  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor (#430)

2.0.70-beta.d79b779

06 May 14:35
d79b779

Choose a tag to compare

2.0.70-beta.d79b779 Pre-release
Pre-release
  • feat(dev): tee stdout/stderr to logs/dev-YYYY-MM-DD.log (#444)
  • perf(proxy): WebSocket keepalive ping prevents middlebox idle drops (#442)
  • feat(proxy): WebSocket connection pool fixes prompt-cache hit-rate jitter (#440)
  • feat(dashboard): range hit-rate card + chart panel + 5min granularity, proxy diag logs (#439)
  • fix(self-update): guard against non-master branch and dirty tree (#438)
  • fix(translation): hint upstream model to omit empty pages on Read tool (#437)
  • feat: implicit resume via effectiveConversationId for chat/gemini routes (#432)
  • fix: correct Ollama context metadata for GPT-5.5 and GPT-5.4 models (#420)
  • fix(ci): checkout master in bump-electron.yml (#427)
  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor (#430)

2.0.69

05 May 08:54

Choose a tag to compare

  • perf(proxy): WebSocket keepalive ping prevents middlebox idle drops (#442)
  • feat(proxy): WebSocket connection pool fixes prompt-cache hit-rate jitter (#440)
  • feat(dashboard): range hit-rate card + chart panel + 5min granularity, proxy diag logs (#439)
  • fix(self-update): guard against non-master branch and dirty tree (#438)
  • fix(translation): hint upstream model to omit empty pages on Read tool (#437)
  • feat: implicit resume via effectiveConversationId for chat/gemini routes (#432)
  • fix: correct Ollama context metadata for GPT-5.5 and GPT-5.4 models (#420)
  • fix(ci): checkout master in bump-electron.yml (#427)
  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor (#430)

2.0.69-beta.f187423

04 May 02:38
f187423

Choose a tag to compare

2.0.69-beta.f187423 Pre-release
Pre-release
  • feat(proxy): WebSocket connection pool fixes prompt-cache hit-rate jitter (#440)
  • feat(dashboard): range hit-rate card + chart panel + 5min granularity, proxy diag logs (#439)
  • fix(self-update): guard against non-master branch and dirty tree (#438)
  • fix(translation): hint upstream model to omit empty pages on Read tool (#437)
  • feat: implicit resume via effectiveConversationId for chat/gemini routes (#432)
  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor
  • fix: correct Ollama context metadata for GPT-5.5 and GPT-5.4 models (#420)
  • fix(ci): checkout master in bump-electron.yml (#427)

2.0.69-beta.9f62c88

02 May 06:18
9f62c88

Choose a tag to compare

2.0.69-beta.9f62c88 Pre-release
Pre-release
  • feat: implicit resume via effectiveConversationId for chat/gemini routes (#432)
  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor
  • fix: correct Ollama context metadata for GPT-5.5 and GPT-5.4 models (#420)
  • fix(ci): checkout master in bump-electron.yml (#427)

2.0.68

01 May 17:13

Choose a tag to compare

  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor (#430)

2.1.0-beta.a17a699

30 Apr 17:59

Choose a tag to compare

2.1.0-beta.a17a699 Pre-release
Pre-release
  • test: simulate version bump to 2.1.0 for beta testing
  • fix: smart version calculation in beta and docker workflows
  • fix: docker publish triggers and schema strictness
  • test(real): switch prompt-cache fixtures from codex to gpt-5.4

2.0.68-beta.6bb50eb

30 Apr 18:13

Choose a tag to compare

2.0.68-beta.6bb50eb Pre-release
Pre-release
  • fix: docker publish uses max(pkg, latest stable tag) + remove stale contributor
  • fix: correct Ollama context metadata for GPT-5.5 and GPT-5.4 models (#420)
  • fix(ci): checkout master in bump-electron.yml (#427)

2.0.67

29 Apr 21:13

Choose a tag to compare

  • fix: cache hit rate stuck at 0% + image_generation request counters + auto-precision display (#423)
  • feat: track image_generation tokens separately + real-upstream stress test (#422)
  • fix: recover from previous_response_not_found instead of passing it through (#418)