* feat(codex): support native Anthropic Messages protocol as upstream (farion1231#5071)

* feat(codex): support native Anthropic Messages protocol as upstream

Allow gateways that only expose the native Anthropic Messages protocol
(/v1/messages) to be used by Codex: the local proxy performs bidirectional
request/response/streaming conversion between Responses and Anthropic.

Backend:
- Add two conversion modules: transform_codex_anthropic / streaming_codex_anthropic
- codex.rs: add routing detection and auth: ANTHROPIC_AUTH_TOKEN→Bearer (default),
  ANTHROPIC_API_KEY→x-api-key, mutually exclusive
- handlers.rs: add handle_codex_anthropic_to_responses_transform
- forwarder.rs: support optional Claude Code client fingerprint impersonation
  (User-Agent / anthropic-beta / x-app / system prompt first-line injection)
  and /responses→/v1/messages rewriting
- codex_config: the anthropic format reuses the NativeResponses profile to strip
  custom tools
- ProviderMeta: add impersonateClaudeCode

Frontend:
- CodexApiFormat: add "anthropic"; the form adds auth field selection and an
  impersonation toggle
- Add en/ja/zh/zh-TW copy

Robustness:
- Downgrade when tool history / forced tool_choice conflicts with extended
  thinking, avoiding upstream 400s
- Emit cache_creation_input_tokens in usage and use saturating_add to guard
  against overflow
- Append a unique suffix to non-streaming/streaming output-item ids to avoid
  multi-segment text/thinking overwriting each other

* fix(codex): harden Anthropic bridge against empty text blocks and truncated streams

- Drop empty/whitespace-only text content blocks when rebuilding Anthropic
  messages from Responses history; Anthropic 400s on empty text blocks (e.g. an
  empty assistant text emitted alongside a tool_use), which broke follow-up and
  tool-result requests. Also drop messages left without content.
- Do not report a truncated Anthropic stream as completed: when the SSE
  connection ends before message_stop with no stop_reason, emit an incomplete
  response if partial output exists, or a failed (stream_truncated) response
  otherwise, mirroring the chat converter's EOF handling.

* fix(codex): resolve Anthropic-bridge review findings

Blocking:
1. Defer stripping the [1m] long-context marker until after catalog matching and model write-back, re-stripping it on the final Codex→Anthropic body and setting a flag to emit the context-1m-2025-08-07 beta header, so the marker is no longer lost or overridden by the default model.
2. Gate Anthropic thinking on the trailing turn only (via trailing_turn_allows_thinking) instead of scanning full history, so a Codex session that resends history each round no longer permanently loses thinking after the first tool call.
3. Inject 5m ephemeral cache_control on the Codex→Anthropic body by reusing cache_injector (handling the system string→array conversion), so system/tools/history are cached instead of re-sent at full price every round.
4. Add a shared base_url_is_full_endpoint helper (normalizing whitespace/query/fragment/trailing slash) used by both the Anthropic and Chat paths, so a base URL already ending in /v1/messages is treated as a full endpoint instead of double-appending to /v1/messages/v1/messages.
5. Align the catalog tool-profile predicate with the routing predicate so resolve_codex_catalog_tool_profile returns the Anthropic profile whenever the request converts to Anthropic, preventing freeform tools like apply_patch from being silently filtered by a ProxyChat catalog.
6. Explicitly disable native web_search for the Anthropic profile (including the no-catalog branch) via set_codex_native_web_search_field, so Codex no longer treats it as available while the transform silently drops it.
7. Only forward tool_choice when tools survive filtering, dropping it otherwise, to avoid a non-retryable 400 from upstream when tool_choice is sent with no tools.
8. Lower the fallback default to max_tokens=8192 (only when max_output_tokens is omitted) and clamp the thinking budget to max_tokens/2, disabling thinking below the 1024 floor, to avoid hard 400s on low-output-ceiling models/gateways.

Minor:
9. Centralize the Codex/OpenAI fingerprint-header denylist in is_codex_client_fingerprint_header so impersonating Claude Code uniformly drops originator/session_id/conversation_id/chatgpt-account-id/x-client-request-id/openai-* and the x-stainless-*/x-codex-* prefixes.
10. Retain content_block_start.input as start_input and fall back to it at block close when no input_json_delta arrived, so a gateway that carries the full tool input on the start event no longer yields empty tool arguments.
11. Extract a shared codex_responses_sse module as the single Responses SSE envelope builder that both the chat and anthropic streaming emitters delegate to, with byte-for-byte-unchanged wire output, so future event-format fixes touch one place instead of two.

* fix(codex): add per-provider max_output_tokens override for Codex→Anthropic path

Codex does not forward model_max_output_tokens in the request body,
causing the proxy to fall back to a conservative 8192 default. This
truncates long or thinking-heavy responses (stop_reason=max_tokens).

- Add maxOutputTokens field to ProviderMeta (Rust + TypeScript)
- Inject the value into the Anthropic request body before transform,
  taking precedence over request-supplied and default values
- Add numeric input in Codex form fields (Anthropic format only)
- Add i18n entries for label, placeholder, and hint (en/zh/zh-TW/ja)
- Include roundtrip and omission unit tests for the new field

* fix(codex): harden Anthropic protocol bridge

* fix(codex): address Anthropic bridge review

* fix(codex): preserve flattened Anthropic inputs

* fix(codex): harden Anthropic recovery paths

* fix(ci): satisfy Rust clippy

---------

Co-authored-by: Jason <[email protected]>

* fix: exclude Fable model env from Claude common config (farion1231#4272) (farion1231#5206)

* Add test for Fable model env key exclusion

Add regression test to ensure Fable model env keys are excluded from common config.

* Add Fable model to CLAUDE_MODEL_OVERRIDE_ENV_KEYS

* Add files via upload

* Delete .github/workflows/build-windows-unsigned.yml

* Fix/opencode known field editors (farion1231#2907)

* fix: add opencode model limit editor

* fix: add opencode headers editor

* style: refine opencode advanced field layout

* fix: preserve valid opencode headers

* fix: preserve opencode extra options and sync translations

---------

Co-authored-by: wzk <[email protected]>
Co-authored-by: Jason Young <[email protected]>
Co-authored-by: Jason <[email protected]>

* fix: handle missing provider keys and tool schema types (farion1231#5069)

* fix: handle missing api keys and tool schema types

* fix: preserve nested tool schemas

---------

Co-authored-by: Jason <[email protected]>

* fix(usage): 修复 Codex 子代理使用量未计入统计 (farion1231#5187)

* fix(usage): count Codex subagent session tokens

* fix(usage): address Codex subagent review feedback

* fix(usage): preserve Codex migration history

* fix(usage): harden Codex subagent migration

* fix(usage): reimport late Codex subagents

* fix(usage): guard late Codex rollup reimport

* refactor(usage): simplify Codex subagent accounting fix

* fix(proxy): inject a single auth placeholder on managed Claude takeover (farion1231#5095)

Switching the Claude provider from a third-party (DeepSeek/MiMo/...) to a
managed Codex provider wrote both ANTHROPIC_API_KEY and
ANTHROPIC_AUTH_TOKEN as PROXY_MANAGED into ~/.claude/settings.json,
making Claude Code warn "Both ANTHROPIC_AUTH_TOKEN and ANTHROPIC_API_KEY
set - auth may not work as expected" on every run.

The double key is an accretion artifact: the ManagedAccount takeover
policy originally injected only ANTHROPIC_API_KEY (Copilot, farion1231#1049), and
the Codex fix that preserved ANTHROPIC_AUTH_TOKEN to avoid the login
prompt (farion1231#3784 / PR farion1231#3789) added the token on top without removing the
API key insert.

Inject exactly one placeholder instead: AUTH_TOKEN for Codex-managed
providers (keeps the farion1231#3784 fix), API_KEY for Copilot (keeps the farion1231#1049
behavior). Local-proxy auth is unaffected - the forwarder resolves the
PROXY_MANAGED placeholder from either header.

Updates the three Codex takeover tests to assert API_KEY is absent and
adds a regression test for the exact third-party -> Codex switch from
the report.

Fixes farion1231#4919

* feat(pricing): seed GPT-5.6 Sol/Terra/Luna pricing

Add the three GPT-5.6 tiers to seed_model_pricing, cross-checked against
OpenAI's official pricing page and OpenRouter:

  gpt-5.6-sol    5 / 30 / 0.50 (cache read)
  gpt-5.6-terra  2.50 / 15 / 0.25
  gpt-5.6-luna   1 / 6 / 0.10

cache_write is "0": OpenAI publishes only a cached-input (read) rate and no
separate cache-write price, matching the gpt-5.x family convention. Base ids
only for now — effort-suffix variants are deferred until the upstream logging
suffix set for 5.6 is confirmed. New model, so seed only (no repair branch,
no SCHEMA_VERSION bump).

* feat(pricing): seed Tencent Hunyuan Hy3 pricing

Add Hunyuan Hy3 (released 2026-07-06, 256K context) to seed_model_pricing
under both the hunyuan-hy3 and hy3 ids, since the upstream billing id isn't
yet confirmed and one of the two should match logged usage.

Prices come from Tencent's launch-day list price (CNY 1 / 4 / 0.25 per 1M
input / output / cache-hit), converted at 1 USD ~= 7.14: 0.14 / 0.56 / 0.035.
cache_write is "0" (no published write rate). Hy3 actually uses input-length
tiered billing (<16K / 16-32K / >=32K); the single-price table holds the
lowest tier, so long-context requests are under-billed until this is revisited
against the official billing page. New model, so seed only.

* feat(codex): add default model field to provider form

Expose the top-level `model` key of config.toml as an editable field in
the Codex provider form, so users can switch to newly released models
(e.g. gpt-5.6) without waiting for a preset update — preset updates only
affect newly added providers, existing ones keep their saved TOML.

The field syncs bidirectionally with the TOML editor (mirroring the
base-URL pattern), suggests models from the mapping catalog plus the
provider's /models endpoint, and offers a one-click "add to mapping"
action when the value is outside a non-empty catalog. Hidden for
official providers.

Details:

- Save-time catalog sync now only backfills the first mapping row into
  the top-level model when the field was left empty, so the explicit
  field wins over the implicit row-0 sync
- Escape model names (and base_url) with TOML basic-string escaping and
  strip control characters from field input: /models ids are remote
  data and unescaped interpolation could inject config.toml lines
  (e.g. a forged [mcp_servers.*] command)
- The strict model-line matcher now recognizes escaped output, empty
  strings and single-quoted literals, keeping extract/set round-trips
  stable; deliberately no key-only loose matching (it would misfire on
  assignment-looking text inside multiline strings)
- Invalidate the fetched model list whenever the request identity
  changes (base URL, full-URL toggle, API key, custom UA) and discard
  in-flight responses via a sequence guard, so the dropdown never shows
  a previous provider's models
- i18n for zh/en/ja/zh-TW

* feat(profiles): add setting to toggle project switcher on main page

Add a show/hide toggle for the header project profile switcher under
the Homepage Display section in settings. Defaults to visible so
existing users keep the current behavior.

* refactor(health-check): remove per-provider test config

* fix(usage): account for cache-write tokens across schema versions

Parse cache_write_tokens from OpenAI usage details and preserve cache creation data across Chat, Responses, and Anthropic conversion paths.

Add explicit input-token semantics to request logs and rollups so legacy rows subtract cache reads only while new total-inclusive rows subtract both cache reads and writes. Migrate v12 databases, normalize rollups to fresh input, and cover historical backfill behavior with regression tests.

* fix(proxy): harden Responses reasoning and tool-call conversion

Round-trip encrypted Responses reasoning items through bridge-owned Anthropic thinking blocks, discard orphaned reasoning-only history, and consume the official reasoning text event vocabulary.

Track concurrent streaming items by stable IDs and output indexes, reuse a dedicated fallback block for keyless legacy reasoning, recover tool arguments from done events, and close blocks in protocol order.

Normalize empty or incomplete non-streaming tool arguments, reject malformed completed calls, and persist upstream usage before returning terminal conversion errors.

* fix(cache): surface unsupported breakpoint counts

Warn when caller-provided cache breakpoints already exceed the supported total of four while preserving the original markers and upgrading their TTLs.

Clarify that automatic injection is governed by the remaining breakpoint budget, and add regression coverage proving excess caller markers are never deleted or reordered.

* feat(proxy): session-based prompt_cache_key routing for Codex Chat bridge

Codex always sends prompt_cache_key in its Responses requests, but the
Responses -> Chat Completions conversion dropped it, breaking session
cache affinity on upstreams that route by key (e.g. Kimi Coding).

- Re-inject prompt_cache_key after conversion in the forwarder: an
  explicit client key wins, otherwise a client-provided session ID;
  generated per-request UUIDs are never sent upstream.
- Provider-aware gating: "auto" enables only known-compatible upstreams
  (api.openai.com, api.kimi.com/coding) because strict gateways reject
  unknown fields with HTTP 400 (e.g. Fireworks); an advanced
  Auto/Enabled/Disabled override is available on the Codex form in all
  four locales.
- Kimi For Coding preset opts in explicitly.

* fix(proxy): harden Responses and Anthropic protocol bridges

Fail closed on HTTP 2xx failure envelopes and pre-output SSE failures so semantic upstream errors can trigger failover instead of becoming empty successful replies.

Finalize incomplete and truncated streams explicitly, handle clean EOF and whole JSON responses, and keep tool-call stop reasons and terminal event ordering consistent.

Preserve structured tool results, URL images, documents, system roles, and signed thinking across both conversion directions. Drop incomplete historical tool calls safely and classify malformed completed arguments as non-retryable client requests.

Keep Codex-to-Anthropic prompt caching enabled by default while honoring the dedicated cache-injection switch.

* fix(cache): strengthen prompt cache breakpoint injection

Honor both the optimizer master switch and the cache-injection sub-switch before mutating native optimizer requests.

Use the available four-breakpoint budget across tools, system content, the latest cacheable message, and an older user anchor for long tool-heavy conversations.

Preserve caller-owned breakpoint limits, avoid thinking blocks as cache targets, normalize configured TTLs, and add regression coverage for disabled optimization and long histories.

* fix(usage): account for Anthropic cache write TTLs

Parse and retain Anthropic's ephemeral 5-minute and 1-hour cache-creation token buckets while preserving the existing aggregate cache-write metric for compatibility.

Price 1-hour writes at the documented premium relative to the configured 5-minute write rate, clamp inconsistent provider details safely, and include TTL buckets in usage diagnostics.

Persist 1-hour cache-write tokens with schema version 14 so zero-cost backfills and later pricing updates retain the original TTL semantics. Keep session import paths compatible through zero-valued detail fields.

* feat(codex): route native ChatGPT sessions through proxy takeover

Allow the built-in Codex official provider to participate in takeover mode while preserving Codex's native OAuth or API-key credentials instead of persisting them into provider records.

Project official routing into a dedicated TOML provider, normalize inline tables, clean stale managed placeholders, and fail closed when the live configuration cannot be transformed safely.

Validate forwarded authorization, make official 401/403 responses non-retryable, avoid circuit-breaker pollution, and share the first-party ChatGPT endpoint across the Codex and Claude adapters.

* fix(providers): skip reachability probes for official OAuth entries

Do not derive unauthenticated health-check targets from runtime adapter defaults for official providers. Batch checks now skip official entries, and direct base-URL resolution fails explicitly instead of probing first-party endpoints without credentials.

Cover the Codex official provider in the stream-check regression tests so future adapter changes cannot silently reintroduce these probes.

* feat(codex): expose official routing and restore the built-in provider

Let users switch between the built-in OpenAI provider and third-party Codex providers directly from the provider panel while takeover mode remains active.

Centralize the frontend capability predicate so only the fixed codex-official seed receives native-login routing support, and keep copied UUID-based official entries clearly marked as unsupported.

Add an idempotent backend command that recreates the deleted official seed, wire it into the add-provider flow, refresh localized guidance, and add mutation and provider-action regression coverage.

* feat(codex): declare gpt-5.6 context window for Claude Code takeover

- Update Codex OAuth presets to the gpt-5.6 family (haiku -> gpt-5.6-luna)
  and bump the custom Codex template default model
- Inject CLAUDE_CODE_MAX_CONTEXT_TOKENS / CLAUDE_CODE_AUTO_COMPACT_WINDOW
  (372000, the ChatGPT Codex catalog window with a ~353K effective budget,
  openai/codex#31860) into effective live settings so Claude Code stops
  assuming a 200K window and compacts before the upstream rejects the prompt
- Gate the injected defaults on every configured model being gpt-5.6*:
  gpt-5.5's upstream catalog oscillates between 272K and 372K and must not
  inherit them; explicit user values always win
- Strip the injected values on switch-away backfill (mirror-inverse of the
  injection conditions) so program defaults never harden into per-provider
  explicit values, and keep both keys out of the shared common-config snippet

* feat(pricing): seed gpt-5.6 alias rows and 1.25x cache-write rates

- Add the bare gpt-5.6 row (official Sol alias) plus effort-suffix variants
  mirroring the gpt-5.5 accounting shape, priced at Sol rates
- The GPT-5.6 family charges cache writes at 1.25x the uncached input rate
  (new for OpenAI; earlier GPT models keep their correct zero): set
  6.25 / 3.125 / 1.25 for Sol / Terra / Luna across seed rows
- Repair earlier zero-value gpt-5.6 tier seeds in existing databases,
  matching only untouched rows so user-customized prices survive

* feat(kimi): declare the 256K context window for Kimi For Coding

Claude Code caps unknown model ids at 200K, so the preset's standalone
CLAUDE_CODE_AUTO_COMPACT_WINDOW=262144 was clamped by min(window, value)
and never took effect. Pair it with CLAUDE_CODE_MAX_CONTEXT_TOKENS and
route the endpoint's kimi-for-coding alias on every tier, since both
context envs are ignored for claude-* prefixed model ids.

Saved providers get the same context defaults injected into effective
live settings at switch time, with a mirror-inverse strip on backfill so
injected values never harden into provider config. Explicit user values
always win over the injected defaults.

* refactor(presets): pin context window values instead of form fields

Drop the Max Context Tokens / Auto Compact Window template inputs from
the Codex and Kimi For Coding presets and hardcode the values in the
preset env (372000 / 262144). The rare user who wants different numbers
can edit them directly in the JSON editor.

Both keys stay on purpose: the compact window resolves as
min(model window, value), so matching the window is behavior-neutral
today, but the explicit env pins compaction locally against
remote-config experiments dialing it down.

* fix(proxy): align Codex OAuth client identity

ChatGPT's Codex backend routes model availability by the originator and version header pair. Requests identifying as cc-switch without a version were assigned to a cohort where gpt-5.6-luna resolved to an unavailable internal engine, resulting in a misleading 404 Model not found response.

Identify takeover requests as codex_cli_rs and send version 0.144.1, satisfying luna's minimal_client_version requirement of 0.144.0. A direct HTTP A/B test confirmed the existing headers returned 404 while the aligned identity completed successfully, so no WebSocket transport workaround is required.

* feat(presets): promote SudoCode to paid sponsor across six clients

Replace the legacy sudocode.us provider (a name collision) with the new
paid sponsor SudoCode on sudocode.chat, updated in place across six
clients: Claude Code, Codex, Claude Desktop, OpenCode, OpenClaw, Hermes.

- Switch endpoints to api.sudocode.chat, add isPartner +
  partnerPromotionKey, and add four-locale partnerPromotion copy
- Claude Code / Desktop use direct passthrough (no model mapping)
- Codex / OpenCode / OpenClaw / Hermes use gpt-5.6-sol
- Remove the Gemini entry (outside sponsor scope)
- Replace the provider icon with the new brand PNG

* fix(codex): infer image capability for generated catalogs and resync takeover live on save

Mapped GPT models were rejected by Codex clients with "model does not
support image inputs". Two root causes:

- Catalog entries for native-Responses/Anthropic providers cloned a
  template whose input_modalities defaulted to ["text"], so every mapped
  model was advertised text-only. model_catalog_json replaces Codex's
  built-in model table wholesale, and both the TUI and the IDE extension
  block images pre-send when the current model is found without "image".
- Editing the current Codex provider during proxy takeover only refreshed
  the DB backup, so removing the mapping left a stale model_catalog_json
  pointer (and its text-only catalog file) active in live config.

Changes:

- New shared model_capabilities module: explicit row declaration first,
  then a confirmed text-only registry (exact tail match only — prefix
  matching removed, variants enumerated so future -vl/-vision models fail
  open), everything else unknown.
- Catalog generation writes input_modalities from that inference for all
  tool profiles: unknown models fail open to ["text","image"]; only
  confirmed text-only models are advertised as ["text"], giving users a
  clear client-side prompt instead of silent image stripping.
- Live catalog reverse-import collapses modalities that match current
  inference, so registry corrections are not frozen into hidden row
  overrides and the rectifier's heuristic opt-out keeps working.
- Saving the current Codex provider while takeover owns live now
  re-projects the live config (mirrors the hot-switch path), so mapping
  edits and removals take effect immediately.
- Media rectifier delegates to the shared module; its preflight toggle is
  documented (4 locales) as proxy-request-only, never affecting catalog
  capability declarations.

* revert(proxy): drop the 1-hour cache TTL option and TTL-bucketed write accounting

The forced 1-hour cache_control TTL (schema v14) was a mistake. Injected
breakpoints return to Anthropic's standard 5-minute TTL, caller-owned
markers are preserved verbatim instead of having their TTLs rewritten,
and the 5m/1h cache-write buckets are removed from usage parsing and
pricing (back to the single aggregate cache-creation rate). The cache
TTL selector is removed from the rectifier settings panel along with its
i18n keys in all four locales.

SCHEMA_VERSION returns to 13: the unreleased cache_creation_1h_tokens
column and the v13->v14 migration are removed. The feature never shipped
in a release and the introducing commit was never pushed, so no
databases were stamped v14 outside this machine (local DB verified at
user_version 13).

* chore(release): v3.17.0

* docs(release): add v3.17.0 release notes

* fix(i18n): add missing proxyReasonAnthropicMessages key across locales

The routing-required toast for Anthropic-format Codex providers only had
a Chinese defaultValue in code; non-Chinese locales showed a mixed-language
message. Add the reason string to zh/en/ja/zh-TW following the phrasing of
the sibling proxyReason* keys.

* docs(guides): add Codex + Claude local routing guide in three languages

Step-by-step guide for the v3.17.0 native Anthropic Messages upstream:
add a custom Codex provider pointed at a Claude-family /v1/messages
gateway, pick the anthropic upstream format, enable local routing, and
verify the chain. Covers the auth-field choice (Bearer vs x-api-key),
the Claude Code impersonation toggle, the 8192 max-output fallback, and
a FAQ entry for gateways that restrict keys to Claude Code only.

Includes four UI screenshots captured from the real 3.17.0 app with
sample data, and links the guide from the v3.17.0 release notes in all
three languages.

* feat(copilot): support GPT-5.6 1M max effort

---------

Co-authored-by: Yeeyzy <[email protected]>
Co-authored-by: Jason <[email protected]>
Co-authored-by: Dawn <[email protected]>
Co-authored-by: v2v <[email protected]>
Co-authored-by: wzk <[email protected]>
Co-authored-by: Jason Young <[email protected]>
Co-authored-by: Komi <[email protected]>
Co-authored-by: 白喵喵喵喵 <[email protected]>
Co-authored-by: 风少1227 <[email protected]>

* fix: add opencode model limit editor

* fix: add opencode headers editor

* style: refine opencode advanced field layout

* fix: preserve valid opencode headers

* fix: preserve opencode extra options and sync translations

---------

Co-authored-by: wzk <[email protected]>
Co-authored-by: Jason Young <[email protected]>
Co-authored-by: Jason <[email protected]>

- fix(usage): Codex 子代理使用量未计入统计 (#5187)
- fix: handle missing provider keys and tool schema types (#5069)
- Fix/opencode known field editors (#2907)
- fix: exclude Fable model env from Claude common config (#4272) (#5206)

Co-Authored-By: Claude Fable 5 <[email protected]>