DeepSeek released V4 flash/pro; legacy IDs deepseek-chat / deepseek-reasoner
now alias to deepseek-v4-flash and will be deprecated.
- Update claude/hermes/opencode/openclaw presets to v4-pro / v4-flash,
context 128K -> 1M; Claude Anthropic-compat endpoint routes OPUS/SONNET
to v4-pro and HAIKU to v4-flash, plus an explicit modelsUrl override.
- Seed deepseek-v4-flash ($0.14/$0.28 per 1M) and deepseek-v4-pro
($1.68/$3.36 per 1M) into model_pricing; older v3.x / chat / reasoner
rows kept for historical usage stats (INSERT OR IGNORE).
- Refresh user-manual (zh/en/ja) pricing table and note that legacy model
IDs are billed at v4-flash rates.
Providers like DeepSeek, Kimi, Zhipu GLM and MiniMax expose the
Anthropic-compatible API on a subpath (e.g. /anthropic) while the
OpenAI-style /models endpoint lives at the API root. The previous
heuristic blindly appended /v1/models to the Base URL, so every such
provider returned 404 and the UI mislabeled it as "provider does not
support fetching models".
Backend now generates a candidate list and tries them in order:
preset override -> baseURL /v1/models -> stripped-subpath /v1/models ->
stripped-subpath /models. Non-404/405 responses (auth, network) stop
immediately so we never retry against hostile status codes. Known
compat suffixes are kept in a length-descending constant so the
longest match wins; response bodies are truncated to 512 chars to
avoid HTML 404 pages bloating the error string.
Preset type gains an optional modelsUrl (DeepSeek points at
https://api.deepseek.com/models). Frontend threads the override
through fetchModelsForConfig when the current Base URL still matches
the preset default. A new fetchModelsEndpointNotFound i18n key
replaces the misleading "not supported" toast for exhausted-candidate
and 404/405 cases (zh/en/ja).
Copilot upstream returns model_not_supported when the client sends
dash-form Claude IDs (claude-sonnet-4-6, claude-sonnet-4-6[1m]) while
/models only accepts dot form (claude-sonnet-4.6, -1m suffix).
- Add copilot_model_map: syntax normalize (dash->dot, [1m]->-1m) plus
live /models exact match and family-version fallback, reusing the
existing 5 min auth cache. Returns None when the whole family is
absent so upstream surfaces an explicit error instead of silently
switching families.
- Wire into forwarder Copilot hook; runs before anthropic_to_openai
conversion.
- Default Opus slot in the Copilot preset maps to Sonnet 4.6: Pro
dropped all Opus on 2026-04-20 and Pro+ bills Opus 4.7 at 7.5x.
Users who want real Opus can switch manually in the UI.
Refs: https://github.com/farion1231/cc-switch/issues/2016
- Add v3.14.1 release notes (en/zh/ja) covering tray usage visibility,
Codex OAuth stability fixes, Skills import/install reliability, and
removal of the Hermes config health scanner
- Cut [Unreleased] into [3.14.1] in CHANGELOG with PR references
- Bump version in package.json, Cargo.toml, Cargo.lock, tauri.conf.json
dc04165f surfaced tray usage badges for Claude/Codex/Gemini official
OAuth only. Chinese coding-plan providers already expose 5h + weekly
windows through coding_plan::get_coding_plan_quota, but two gaps kept
the tray from rendering them.
- format_script_summary read only data.first(), truncating the tier-
flattened UsageResult to a single window. Detect plan_name matching
TIER_FIVE_HOUR / TIER_WEEKLY_LIMIT and emit the "🟢 h12% w80%" layout
used by format_subscription_summary; worst utilization drives the
emoji. Copilot / balance / custom scripts keep the legacy single-
bucket output via fallback.
- usage_script previously required manual activation through
UsageScriptModal. Auto-inject meta.usage_script on Claude provider
creation when ANTHROPIC_BASE_URL matches a known coding plan, so the
tray lights up without the user opening the modal. Does not overwrite
existing usage_script on update.
Extract the URL route table out of UsageScriptModal into a shared
codingPlanProviders module so the modal, the creation hook, and the
Rust coding_plan::detect_provider mirror all agree on one list.
Add TIER_WEEKLY_LIMIT alongside TIER_FIVE_HOUR and a createUsageScript()
factory to collapse the duplicated default fields across four call
sites and drop the remaining stringly-typed tier names.
The Hermes config.yaml schema has stabilized and users have migrated to
the current provider fields, so the value of scanning for model.provider
dangling references, custom_providers shape errors, v12 migration residue
etc. no longer justifies the maintenance surface — and the scan produces
false positives when users keep some providers under Hermes' v12+
providers: dict (Hermes' runtime merges both shapes, but CC Switch's
scanner only looked at the list form).
Removes the whole HermesHealthWarning type, scan_hermes_config_health
command, HermesHealthBanner React component, useHermesHealth hook,
warnings field on HermesWriteOutcome, and the three helper functions
(yaml_as_non_empty_str, collect_mapping_string_keys, hermes_warning)
that only served the scanner. Drops the matching i18n keys in
zh/en/ja and the fixInWebUI button label that only the banner used.
* feat: add Rust-side write-through usage cache
Introduce an in-memory UsageCache on AppState that the existing usage
query commands populate on success. The cache is read-only to the rest
of the app today; the next commit consumes it from the tray menu.
- New services::usage_cache module with split maps: subscription keyed
by AppType, script keyed by (AppType, provider_id).
- AppType gains Eq + Hash so it can be used as a HashMap key.
- commands::subscription::get_subscription_quota now takes State<AppState>
and writes through on success (signature change is invisible to the
frontend — Tauri injects State automatically).
- commands::provider::queryProviderUsage body extracted into an inner
async fn; the public command wraps it with write-through, covering
Copilot, coding-plan, balance, and generic script paths uniformly.
Cache is in-memory only; auto-query interval and the upcoming tray
refresh action rebuild it after restarts.
* feat(tray): surface cached usage in the system tray menu
Read UsageCache populated by the previous commit and render it in three
places, scoped to whatever TRAY_SECTIONS covers (Claude/Codex/Gemini):
1. Inline suffix on each provider submenu item
"AnyProvider · 🟢 5h 18% / 7d 23%"
2. Disabled summary row per visible app under "Show Main"
"Claude · Anthropic Official · 🟢 5h 18% / 7d 23%"
3. "Refresh all usage" menu item that triggers get_subscription_quota +
queryProviderUsage for every applicable provider, then rebuilds the
tray menu via the existing refresh_tray_menu path.
Color encoding uses emoji (🟢 <70% / 🟠 70-89% / 🔴 ≥90%) since Tauri 2
tray labels are plain text. Missing cache entry leaves the label
unchanged — tray never issues network requests when opened. Three new
i18n-ready strings live in TrayTexts (en/zh/ja), following the existing
pattern for tray text.
Closes#2178.
* feat(usage): bridge tray UsageCache writes to frontend React Query
Why: tray hover triggers backend-only refresh that wrote to UsageCache but
never notified the frontend, leaving main UI stale while tray showed fresh
numbers. Emit a payload-carrying event after each cache write so React Query
can setQueryData directly, keeping both views in sync without duplicate fetches.
* fix(tray): skip hidden apps on hover refresh and drop stale disabled-script cache
Address P2 findings from automated review on #2184:
1. refresh_all_usage_in_tray now filters TRAY_SECTIONS by settings.visible_apps
before scheduling subscription/script queries, matching create_tray_menu and
preventing wasted external API calls (and rate-limit/auth-error log noise)
for apps the user has hidden.
2. format_usage_suffix only trusts the script cache when provider.meta.usage_script
is still enabled; when a script is disabled/removed the cached suffix is now
invalidated so the tray label no longer shows stale data indefinitely.
* refactor: consolidate codex provider helpers and fix test semantics
- Add Provider::is_codex_oauth() and Provider::codex_fast_mode_enabled()
to eliminate duplicated meta extraction in claude.rs and stream_check.rs
- Fix non-codex-oauth tests to pass codex_fast_mode=false (was true, harmless
but semantically misleading)
- Remove redundant is_dir() guard after resolve_skill_source_dir already
guarantees the returned path is a directory
* style: apply cargo fmt
* fix(tray): reflect failed refreshes in cache and support Gemini flash-lite
Follow-up to the tray usage-display feature addressing review feedback:
- Write snapshots for both Ok(success:false) and Err paths in
queryProviderUsage / get_subscription_quota so stale success data
no longer persists across failed refreshes; the original Err is
still returned to the frontend onError handler.
- Include gemini_flash_lite tier in the tray summary with label "l".
Matches the frontend SubscriptionQuotaFooter and keeps the worst
emoji correct when lite is the highest utilization.
- Add TIER_GEMINI_PRO / _FLASH / _FLASH_LITE constants in
services/subscription.rs and reuse them in classify_gemini_model
and sort_order.
- Extract Provider::has_usage_script_enabled() to remove the
duplicated meta.usage_script chain at two call sites.
- Use db.get_provider_by_id in refresh_all_usage_in_tray instead of
materialising the full provider map, and parallelise subscription
and script futures via futures::future::join.
- Narrow refresh_all_usage_in_tray to each section's effective
current provider (script if enabled, else subscription when the
provider is official). Hover refreshes now issue at most
TRAY_SECTIONS.len() outbound requests.
- Add 10 unit tests in tray::tests covering Claude/Codex h/w dispatch,
Gemini p/f/l dispatch (including lite-only and lite-worst cases),
and success/failure guards.
---------
Co-authored-by: Jason <farion1231@gmail.com>
* Add Codex OAuth FAST mode toggle
* fix(codex-oauth): default FAST mode to off to avoid surprise quota burn
service_tier="priority" consumes ChatGPT subscription quota at a higher
rate. Users must now opt in explicitly rather than inherit FAST mode
silently when this feature ships.
---------
Co-authored-by: Jason <farion1231@gmail.com>
* Stabilize Codex OAuth cache routing
Codex OAuth-backed Claude proxy requests now reuse a client-provided session identity for prompt cache routing and send Codex-like session headers when that identity exists. Generated proxy UUIDs are intentionally excluded so they do not fragment cache locality.\n\nThe same path exposed two runtime issues during validation: rustls needed an explicit process crypto provider, and Codex OAuth can return Responses SSE even when the original Claude request is non-streaming. Those are handled so cache-routed requests can complete instead of panicking or being parsed as JSON.\n\nConstraint: Official Codex uses conversation identity and Responses session headers for prompt cache routing.\nRejected: Always use generated proxy session IDs | generated IDs change per request and reduce cache reuse.\nConfidence: medium\nScope-risk: moderate\nDirective: Do not remove the client-provided-session guard unless generated session IDs become stable per conversation.\nTested: cargo test codex_oauth\nTested: Local dev app health check on 127.0.0.1:15721\nTested: Local proxy logs showed cache_read_tokens after restart\nNot-tested: Full cargo test without local cc-switch port conflict\nRelated: #2217
* feat(proxy): aggregate forced Codex OAuth SSE into JSON for non-streaming clients
Narrow override on top of #2235's streaming fallback.
Codex OAuth always forces upstream openai_responses into SSE, even
when the original Claude request is stream:false. #2235 handles this
by routing such responses through the streaming transform so the
client receives text/event-stream — that avoids the 422 that JSON
parsing would produce, and it also protects any other provider that
unexpectedly returns SSE (the response.is_sse() guard).
But for Claude SDK callers that sent stream:false, returning SSE
still violates the Anthropic non-streaming contract. This commit
adds an override on exactly one combination — non-streaming client
+ codex_oauth + openai_responses — to aggregate the upstream
Responses SSE into a synthetic Responses JSON and then run the
regular responses_to_anthropic non-streaming transform. All other
paths, including the generic response.is_sse() fallback, remain
on the streaming path from #2235.
The aggregator reuses proxy::sse::take_sse_block / strip_sse_field,
which support both \n\n and \r\n\r\n delimiters; a hand-rolled
split("\n\n") would silently fail on real HTTPS upstreams.
Tests cover the happy path, CRLF delimiters, response.failed
errors, and the missing response.completed defensive branch.
---------
Co-authored-by: Jason <farion1231@gmail.com>
* fix(codex): use TOML parser instead of regex for model extraction
Regex only matched model=... on first line, TOML parser handles
multiline TOML correctly.
Fixes#2222
* fix(stream_check): drop unused regex::Regex import
The previous commit replaced the only Regex usage in stream_check.rs
with toml::Table parsing, leaving `use regex::Regex;` orphaned.
Without this removal, `cargo clippy -- -D warnings` (run in CI)
fails with `unused import: regex::Regex`.
---------
Co-authored-by: Jason <farion1231@gmail.com>
Moonshot's official USD pricing for kimi-k2.6 is $0.95 input /
$4.00 output / $0.16 cache-hit per 1M tokens (~58-60% higher than
K2.5). The previous commit copied K2.5's $0.60/$2.50/$0.10, which
would have under-billed K2.6 traffic in the usage dashboard.
No migration needed since this version is unreleased; INSERT OR
IGNORE will write the correct values on first launch.
Bump model id and display name from K2.5 to K2.6 in Hermes, OpenClaw,
OpenCode, and Claude (direct api.moonshot.cn) presets. Pricing,
context window, and base URL are unchanged.
Add kimi-k2.6 row to model_pricing seed; no migration needed since
seed_model_pricing uses INSERT OR IGNORE and runs on every startup
via ensure_model_pricing_seeded. Old kimi-k2.5 row is kept to
preserve historical usage stats.
Nvidia aggregator forwards (moonshotai/kimi-k2.5) intentionally keep
the K2.5 SKU until Nvidia's catalog confirms K2.6.
Hermes providers were routed through check_additive_app_stream, the
OpenClaw dispatcher, which reads camelCase fields (baseUrl/apiKey/api)
and emits "OpenClaw is missing ..." errors. Hermes stores snake_case
fields (base_url/api_key/api_mode) with different protocol tags, so
users saw "OpenClaw provider is missing baseUrl" even after filling in
every Hermes field correctly.
Introduce check_hermes_stream with Hermes-specific extractors. Route
api_mode (chat_completions / anthropic_messages / codex_responses) to
the matching check_claude_stream api_format, and return bedrock_converse
as unsupported. Resolve api_mode before extracting URL/API key so users
who picked bedrock_converse see the real cause first rather than a
misleading "missing base_url" message.
When the Hermes Web UI probe fails, the toolbar entry now opens an info
confirm dialog offering to run `hermes dashboard` in the user's preferred
terminal. Accepting spawns it via a temp bash/batch script; `hermes
dashboard` itself opens the browser once ready, so we do not poll.
The Memory panel and Health banner keep the existing toast behavior.
Also corrects the stale `hermes web` hint in the offline toast (the real
command is `hermes dashboard`) and reorders Linux terminal detection to
try `which` before stat'ing /usr/bin, /bin, /usr/local/bin.
Wire hermes through SkillApps struct, DAO SQL, command parser, and
SKILLS_APP_IDS. Add a Skills entry to the Hermes toolbar. Simplify
skill_sync test fixtures to use SkillApps::default().
Hermes 0.10.0 tightened custom_providers validation (commit 2cdae233):
invalid base_urls are rejected, unknown fields produce warnings, and
new fields (rate_limit_delay, bedrock_converse, key_env) landed.
- Add bedrock_converse to the api_mode selector (and i18n labels)
- Expose rate_limit_delay in a provider-level advanced panel
- Validate base_url client-side (URL shape, template-token friendly)
- Drop per-model max_tokens — not in _VALID_CUSTOM_PROVIDER_FIELDS
- Round-trip test asserts set_provider preserves rate_limit_delay /
key_env / any unknown forward-compat field
Three unrelated test failures surfaced after rebase:
- McpFormModal expected the apps boolean set without `hermes`; Hermes MCP
support is now wired, so the fixture must include `hermes: false`.
- therouter Gemini preset was bumped to `gemini-3.1-pro` in a later
commit; update the assertions to match current config.
- openclaw_config tests mutate process-level `CC_SWITCH_TEST_HOME` and
`HOME` inside a module-local Mutex, but hermes_config does the same
under its own separate Mutex. Running both modules in parallel let the
env races corrupt hermes_config's `with_test_home`. Tag the four
env-mutating openclaw tests with `#[serial]` so they serialize across
modules via serial_test's process-wide default key.
Hermes' built-in api_mode detection only matches a handful of official
endpoints (api.openai.com, api.anthropic.com, api.x.ai, AWS Bedrock);
third-party / proxy endpoints silently fall back to chat_completions,
which causes opaque 401/404s on Anthropic-protocol or Codex-Responses
providers. The "Auto" option was misleading for the common third-party
case.
- Drop the "Auto" option from the API Mode dropdown; remove the
HermesApiModeChoice sentinel type so writes always emit api_mode.
- Default new providers and legacy entries lacking api_mode to
chat_completions (only persisted on user save).
- Deeplink imports now write api_mode: chat_completions explicitly
instead of relying on URL heuristics; test renamed accordingly.
- Rename the "Codex Responses (Copilot / OpenCode)" label to
"OpenAI Responses" to match OpenAI's /v1/responses naming.
After /simplify review of the P1-3 second wave, two small cleanups:
- Lift the `_cc_source` / `providers_dict` magic strings out of
ProviderCard into a shared helper (`isHermesReadOnlyProvider`) and
named constants in hermesProviderPresets.ts. Front-end and back-end
now document the same marker contract in two mirrored places
instead of drifting strings.
- Replace the duplicate `is_dict_only_provider` + `format!` branches
at the top of `set_provider` / `remove_provider` with a single
`ensure_provider_writable(config, name, verb)` guard. Future error
copy tweaks only have to happen once.
No behaviour change; all 52 hermes_config tests stay green.
Hermes v12+ migrated some provider entries from the `custom_providers:`
list into a `providers:` dict (keyed by id). CC Switch previously
ignored that source entirely, leaving users blind to providers they had
configured via Hermes' own Web UI; the only feedback was a generic
migration warning in the health banner.
`get_providers()` now unions both sources, matching upstream
`get_compatible_custom_providers` dedup order (list wins on name
collision). Entries coming from the dict carry a `_cc_source =
"providers_dict"` marker plus the original `provider_key`, which the
UI layer will use to render them read-only. `set_provider` and
`remove_provider` now refuse to touch dict-only entries, steering the
user to Hermes Web UI. `sanitize_hermes_provider_keys` strips the UI
markers on write so they never reach YAML.
The `schema_migrated_v12` health warning copy reframes the situation:
entries are shown read-only in CC Switch rather than invisible.
DeepLink Hermes import was emitting camelCase (baseUrl / apiKey /
apiMode) that the Hermes runtime does not recognise, poisoning
`custom_providers:` entries on activation. The MCP sync path was
also stripping `auth: oauth` on round-trip, silently downgrading
OAuth-type servers to unauthenticated calls.
The Hermes deeplink branch now emits snake_case via a dedicated
builder; `sanitize_hermes_provider_keys` runs on both `set_provider`
and `get_providers` so legacy DB records heal on next access.
`HERMES_EXTRA_FIELDS` preserves `auth`. The `api_mode` dropdown gains
`codex_responses` (Copilot / OpenCode), and the schema-migrated
warning copy no longer hard-codes "v12" (upstream `_config_version`
is now 19).
Drops the v11→v12 providers-dict compat layer: CC Switch now only
reads/writes `custom_providers:`, leaving migrated `providers:` dict
entries to Hermes Web UI for reconciliation (Hermes' runtime already
merges both shapes via `get_compatible_custom_providers`). The
`schema_migrated_v12` health warning now points users there when a
dict-migrated config is detected.
Adds forward-compat merge to `set_provider`: when updating an existing
entry, on-disk fields the UI payload didn't submit (e.g. Hermes-only
`request_timeout_seconds`, `key_env`) are carried over. Without this,
editing one field via CC Switch would silently strip the rest.
Adds `set_memory_enabled` + `set_hermes_memory_enabled` Tauri command
for the upcoming memory-switch UI. Writes go through a merge-aware
section replacement so character budgets and external-provider fields
survive toggle operations.
Removes four dict-only helpers (`normalize_providers_dict_entry_for_read`,
`rename_alias_key`, `json_obj_non_empty_str`,
`resolve_provider_name_from_yaml_entry`) and the multi-section write
helper. Simplifies `get_providers` / `remove_provider` / health scan
back to list-only. Replaces nine obsolete dict-related tests with
`set_provider_preserves_unknown_fields_on_update` and
`set_memory_enabled_preserves_other_fields`.
Hermes has no slash-prompt concept (templates live as Skills), so the
Prompts tab for the Hermes app was always empty. Swap the toolbar Book
button for a Brain button that opens a new Memory panel editing
~/.hermes/memories/{MEMORY,USER}.md — Hermes' first-class memory store
which its Web UI exposes only as on/off toggles, never as an editor.
The panel shows each file in its own tab with a character-budget bar
read from config.yaml's nested memory.* section (memory_char_limit /
user_char_limit, default 2200 / 1375). Edits are written atomically;
Hermes picks them up on the next session start per MemoryStore.
Also extract useDarkMode to src/hooks/useDarkMode.ts — the codebase
already repeats the same MutationObserver pattern in 12+ places; this
PR introduces the shared hook and uses it once, leaving the migration
of the other copies to a follow-up.
Slim the Hermes surface in CC Switch to match its core positioning —
cross-client provider switching and shared MCP/prompts/skills — and
delegate deep configuration (model, agent, env, skills, cron, logs)
to the Hermes Web UI at http://127.0.0.1:9119.
- Drop AgentPanel/EnvPanel/ModelPanel and their mutation commands,
hooks, types, and i18n keys across zh/en/ja.
- Add open_hermes_web_ui Tauri command that probes /api/status and
launches the URL in the system browser. Hermes injects its own
session token into the returned HTML, so CC Switch doesn't need
to touch auth.
- Surface the launcher from the Hermes toolbar and the health banner
via a shared useOpenHermesWebUI() hook; the offline error code is
defined once per side and referenced across the contract.
- Keep read-only access to model.provider so ProviderList can still
highlight the active supplier; apply_switch_defaults continues to
write the top-level model section when switching providers.
Net diff: +152 / -1253.
Writing to the v12+ `providers:` dict broke every anthropic_messages
provider. Hermes `runtime_provider.py::_get_named_custom_provider` has a
bug in its `providers:` branch: the returned entry drops `api_mode`,
`transport`, `models`, and singular `model:`, and
`_resolve_named_custom_runtime` then falls back to `chat_completions` —
so an Anthropic-format endpoint receives OpenAI-format requests and
returns 404.
Keep using the legacy `custom_providers:` list; its normalization path
(`_normalize_custom_provider_entry`) preserves every field. In addition,
write a singular `model:` alongside the plural `models:` dict so the
Hermes runtime and `/model` picker see the default model id.
Also keep the `apply_switch_defaults` fix from the prior attempt:
`model.provider` is always updated, and `model.default` is only
overwritten when the new provider declares at least one model — so
switching to an incomplete provider no longer silently no-ops.
Hermes custom_providers entries now carry an ordered models array
(id / context_length / max_tokens) plus suggestedDefaults. The backend
serializes the array to the YAML dict shape Hermes expects on write and
inverts it on read, preserving insertion order via the preserve_order
feature on serde_json.
When a user switches providers, switch_normal calls apply_switch_defaults
so the top-level model.default / model.provider follow the selected
provider's first model. Previously switching a Hermes provider only
shuffled custom_providers[] and left Hermes pointing at whatever
model.provider was set before.
Seven existing Hermes presets now ship with a curated models list so
switching lands on a working default without a detour through the
Model panel.
Copilot routes through OpenAI-compatible endpoints that reject Anthropic's
thinking and redacted_thinking blocks. Previously the request would fail
upstream, burning one premium interaction, and only then trigger
thinking_rectifier to retry. This adds a proactive strip_thinking_blocks
pass in the Copilot optimization pipeline (step 3.5, after tool_result
merging). Signature fields and top-level thinking are left alone — those
are the reactive rectifier's job on the error path.
Also fixes a default-value inconsistency where CopilotOptimizerConfig's
Default impl used "gpt-4o-mini" while the serde default function returned
"gpt-5-mini" (aligned to gpt-5-mini, matching the reference implementation).
Aligned with yuegongzi/copilot-api's /v1/messages handler behavior.
- OpenClaw: replace opus-4-6 with opus-4-7 across 17 aggregator presets
(id, name, primary, modelCatalog); AWS Bedrock entry rewritten to new
SKU anthropic.claude-opus-4-7 (drops -v1 and dated suffix per official
4.7 model card) and pricing corrected to $5/$25/$0.50/$6.25 during the
SKU swap, aligning with schema.rs source of truth
- OpenCode: same replacement for 13 aggregators plus
OPENCODE_PRESET_MODEL_VARIANTS entries for @ai-sdk/amazon-bedrock and
@ai-sdk/anthropic, plus AWS Bedrock provider models map
- OpenRouter / TheRouter / GitHub Copilot in claudeProviderPresets use
dot-style id; update to anthropic/claude-opus-4.7 (missed by 509d2250)
- omo: switch agent/category recommended to opus-4-7; replace key in
OMO_BACKGROUND_TASK_PLACEHOLDER priority map
- hermes_config.rs: update doc comments and test fixtures to opus-4-7;
Hermes ModelPanel placeholder and i18n defaultHint examples follow
- i18n unspecifiedHigh category description bumped to 'Claude Opus 4.7
max variant' to match omo recommended
- Test fixtures updated: therouter preset assertion and opencode Bedrock
variant lookup now check for opus-4-7
- Sonnet 4.6 / Haiku 4.5 untouched - no official 4.7 release for them
- Seed claude-opus-4-7 pricing (same tier as 4.6: $5 / $25 / $0.50 /
$6.25 per million tokens). Relies on incremental INSERT OR IGNORE
seeding; no SCHEMA_VERSION bump needed.
- Whitelist opus-4-7 in thinking optimizer so it uses adaptive
thinking + max effort + 1M context beta, matching 4.6 behavior.
- Bump default OPUS model in PIPELLM and AWS Bedrock (AKSK / API Key)
presets to 4.7. Bedrock SKU drops the -v1 suffix per the official
4.7 model card (anthropic.claude-opus-4-7 and
global.anthropic.claude-opus-4-7).
Add mcp/hermes.rs with bidirectional MCP format conversion:
- convert_to_hermes_format: strip type field, infer from command/url
- convert_from_hermes_format: infer type, strip Hermes-specific fields
- Merge-on-write: existing Hermes fields (tools, sampling, timeout,
roots, enabled) preserved when user has customized them
- update_mcp_servers_yaml: closure-based read-modify-write under write
lock to prevent TOCTOU races in concurrent sync operations
- 9 unit tests for format conversion and merge logic
Wire up all MCP service dispatch:
- Replace Hermes TODO stubs with real sync/remove calls
- Remove Hermes from sync_all_enabled skip list
- Enable deep link hermes MCP flag (apps.hermes = true)
- Add Hermes import to import_mcp_from_apps command
Add hermes_config.rs (~1190 lines) with YAML section-level replacement
that preserves comments and formatting in unmanaged sections:
- Type definitions: HermesModelConfig, HermesAgentConfig, HermesEnvConfig
- YAML section finder (find_yaml_section_range) with column-0 key detection
- Provider CRUD on custom_providers array (indexed by name field)
- Model/Agent config get/set via yaml<->json conversion
- .env dotenv read/write preserving comments and line ordering
- Health check, backup with rotation, write lock (OnceLock<Mutex>)
- MCP section access stubs for Phase 4
- 19 unit tests
Add commands/hermes.rs with 10 Tauri commands registered in lib.rs.
Replace all Hermes TODO stubs in services/provider/live.rs with real
implementations (import, remove, write-to-live, read-live-settings).
- Bump SCHEMA_VERSION from 9 to 10
- Add enabled_hermes column to mcp_servers and skills tables
- Add migrate_v9_to_v10 with table_exists guard for skills (may not
exist in databases migrated from very old versions)
- Update dao/mcp.rs to fully read/write enabled_hermes in all queries
- Update dao/skills.rs: don't SELECT enabled_hermes (Hermes doesn't
support Skills yet), keep column indices clean
Register AppType::Hermes across the entire Rust backend:
- Add Hermes variant to AppType enum with additive mode and MCP support
- Add hermes field to McpApps, SkillApps, CommonConfigSnippets, and all
per-app structs (McpRoot, PromptRoot, VisibleApps, AppSettings)
- Create minimal hermes_config.rs with get_hermes_dir() respecting
settings override, matching the pattern of other app config modules
- Update all match arms in commands, services, deeplink, proxy, mcp,
session_manager, and test files
- Extract shared build_additive_app_settings() to eliminate duplication
between OpenClaw and Hermes deep link handling
- Combine identical OpenClaw/Hermes proxy match arms into unified arms
ANTHROPIC_REASONING_MODEL was a non-official env var that forced all
requests with thinking params to use a single "reasoning model",
overriding the user's /model selection. Since new Claude Code versions
send adaptive thinking by default, this caused /model to silently fail.
- Remove reasoning_model field and has_thinking_enabled() from model_mapper
- Simplify map_model() to pure type-based matching (haiku/sonnet/opus)
- Remove reasoning model UI field from provider form
- Retain ANTHROPIC_REASONING_MODEL in ENV_EXCLUDES and override-key
cleanup lists so legacy configs don't leak into common config
* fix: launch Ghostty via shell command
Use Ghostty's shell execution path instead of injecting raw terminal input so Claude resume commands run reliably when opening a session terminal.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(ghostty): pass cwd via --working-directory instead of shell string
Use Ghostty's native --working-directory flag to set the working
directory, matching the pattern used by Alacritty. This avoids shell
expansion of special characters (e.g. $VAR, spaces) in project paths.
The command is now passed directly to -c without a cd prefix.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat(copilot): add GitHub Enterprise Server support
* fix(copilot): address GHES PR review findings (P1 + 2×P2)
- P1: Use composite account ID (domain:user_id) for GHES to prevent
cross-instance ID collisions; github.com keeps plain numeric ID for
backward compatibilit
- P2-a: Use get_api_endpoint() for model list URL with automatic
fallback to static URL when dynamic endpoint resolution fails
- P2-b: Add normalize_github_domain() as backend SSOT for domain
normalization (lowercase, strip protocol/path/query, reject userinfo)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
`import_from_apps()` saves skills to the database but does not create
symlinks/copies in the target app directories (e.g. `~/.claude/skills/`).
This causes skills to appear as "installed" in the UI while the actual
files are missing from the app directories.
Add `sync_to_app_dir()` calls after `db.save_skill()` in the import
loop, matching the pattern used by `install()` and `toggle_app()`.
* refactor(proxy): extract take_sse_block helper with CRLF delimiter support
Replace inline `buffer.find("\n\n")` SSE splitting logic across streaming,
streaming_responses, response_handler, and response_processor with a shared
`take_sse_block` function that handles both `\n\n` and `\r\n\r\n` delimiters.
* feat(proxy): add Gemini Native URL builder and full-URL resolver
Introduce gemini_url module that normalizes legacy Gemini/OpenAI-compatible
base URLs into canonical models/*:generateContent endpoints. Supports both
structured Gemini URLs (auto-normalized) and opaque relay URLs (pass-through
with query params only).
* feat(proxy): add Gemini Native schema, shadow store, transform, and streaming
- gemini_schema: Gemini generateContent request/response type definitions
- gemini_shadow: session-scoped shadow store for thinking signature and
tool-call state replay across streaming chunks
- transform_gemini: bidirectional Anthropic Messages ↔ Gemini Native
request/response conversion with thinking block and tool-use support
- streaming_gemini: Gemini SSE → Anthropic SSE streaming adapter with
incremental thinking/text/tool_use delta emission
* feat(proxy): wire Gemini Native format into proxy core and Claude adapter
Integrate gemini_native api_format throughout the proxy pipeline:
- ClaudeAdapter: detect Gemini provider type, Google/GoogleOAuth auth
strategies, and suppress Anthropic-specific headers for Gemini targets
- Forwarder: Gemini URL resolution, shadow store threading, endpoint
rewriting to models/*:generateContent with stream/non-stream variants
- Handlers: route Gemini streaming through streaming_gemini adapter and
non-streaming through transform_gemini converter
- Server/State: add GeminiShadowStore to shared ProxyState
- StreamCheck: support gemini_native health check with proper auth headers
* feat(ui): add Gemini Native provider preset and api format option
- Add gemini_native to ClaudeApiFormat type and ProviderMeta.apiFormat
- Add "Gemini Native" provider preset with default Google AI endpoints
- Show Gemini-specific endpoint hints and full-URL mode guidance
- Add gemini_native option to API format selector in ClaudeFormFields
- Add i18n strings for zh/en/ja
* feat(proxy): add Gemini Native tool argument rectification
* feat(proxy): update Gemini streaming and transformation logic
* fix(proxy): align shadow turns to tail on client history truncation
* fix: revert unrelated cache_key change in claude proxy transform
Restore .unwrap_or(&provider.id) fallback for cache_key to match main
branch behavior. Only gemini_native related changes should be in this branch.
* Prevent Gemini review regressions in streaming and tool rectification
PR #1918 review feedback exposed two correctness issues in the Gemini Native adapter path. Gemini SSE buffering was still using lossy UTF-8 decoding, which could corrupt split multibyte payloads and drop streamed output. Tool arg rectification also removed top-level parameters eagerly, which broke tools that legitimately define a parameters field.
This change moves Gemini SSE buffering onto the existing append_utf8_safe path and makes parameters flattening conditional on the schema actually expecting nested extraction. The old Skill rectification path stays intact, and new regression tests cover both the preserved parameters case and UTF-8-split JSON payloads.
Constraint: Existing PR #1918 review feedback must be fixed without staging unrelated local docs and artifact files
Rejected: Keep String::from_utf8_lossy in Gemini SSE buffering | corrupts split multibyte payloads and can drop JSON chunks
Rejected: Always preserve the parameters wrapper | regresses the existing nested-parameters rectification path for Skill-style tools
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Keep Gemini SSE buffering on the UTF-8-safe accumulator path and only unwrap parameters when the target schema does not declare it as a legitimate field
Tested: cargo fmt --manifest-path src-tauri/Cargo.toml --all; cargo test --manifest-path src-tauri/Cargo.toml preserves_utf8_boundaries_when_json_payload_spans_chunks; cargo test --manifest-path src-tauri/Cargo.toml gemini_to_anthropic_rectifies_tool_args_from_schema_hints; cargo test --manifest-path src-tauri/Cargo.toml rectifies_streamed_skill_args_from_nested_parameters; cargo test --manifest-path src-tauri/Cargo.toml gemini_to_anthropic_preserves_legitimate_parameters_arg
Not-tested: Full src-tauri test suite; live end-to-end Gemini relay traffic against upstream services
* Keep Gemini tool replay stable across Claude request boundaries
Claude Code follow-up requests were still falling back to locally reconstructed functionCall parts, which dropped Gemini thought signatures and triggered INVALID_ARGUMENT errors from the official Gemini API. The replay path needed to survive real Claude request boundaries, not just idealized in-process test flows.
This change makes Claude requests reuse X-Claude-Code-Session-Id as the shadow session key, records streamed Gemini tool turns before tool_use events are fully drained, and matches assistant tool_use turns to shadow state by tool_use id and normalized tool name before positional fallback. Together these fixes keep thoughtSignature-bearing Gemini tool calls available for the next request in the loop.
Constraint: Claude Code sends a stable X-Claude-Code-Session-Id header while metadata.session_id may be absent on follow-up requests
Rejected: Rely on metadata-only Claude session extraction | generated fresh session ids and broke cross-request shadow replay
Rejected: Record Gemini shadow only after streaming completes | loses the race when the client sends the next request immediately after tool_use
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: Preserve Gemini shadow continuity across requests by keying Claude sessions from the header first and persisting tool-call shadow before yielding tool_use events downstream
Tested: cargo fmt --manifest-path src-tauri/Cargo.toml --all; cargo test --manifest-path src-tauri/Cargo.toml test_extract_session_from_claude_header; cargo test --manifest-path src-tauri/Cargo.toml test_extract_session_from_claude_header_precedes_metadata; cargo test --manifest-path src-tauri/Cargo.toml stores_tool_shadow_before_tool_use_events_are_fully_drained; cargo test --manifest-path src-tauri/Cargo.toml shadow_replay_matches_tool_use_turn_by_id_when_position_drifts; cargo test --manifest-path src-tauri/Cargo.toml shadow_replay_aligns_to_latest_turns_after_client_truncation
Not-tested: Full src-tauri test suite without test filters; live end-to-end Gemini relay after this exact commit hash
* style: apply cargo fmt to pass Backend Checks CI
Wrap prompt_cache_key chained call across lines per rustfmt default
formatting. Pure formatting change, no behavior difference.
* fix(proxy/gemini): synthesize unique ids for no-id tool calls + enforce object params schema
P1 — Parallel tool calls without Gemini-assigned ids no longer collapse.
Gemini 2.x native parallel `functionCall` entries may omit the `id` field.
The previous `merge_tool_call_snapshots` fell back to matching by `name`,
which silently merged two parallel calls to the same function into one
entry — dropping the first call's args. The non-streaming path and shadow
store further bottlenecked on empty-string ids: multiple `tool_use` blocks
shared the same id, and `tool_name_by_id.get("")` could only return one
mapping, causing later `tool_result` round-trips to fail with
`Unable to resolve Gemini functionResponse.name` or bind to the wrong tool.
Fix: introduce `synthesize_tool_call_id()` producing `gemini_synth_<uuid>`.
Both streaming and non-streaming response paths now guarantee every
Anthropic-visible tool_use carries a unique id. `merge_tool_call_snapshots`
matches by id first, falling back to the `parts` array position (for the
cumulative-streaming case) while preserving the synthesized id across
chunks. `convert_message_content_to_parts` detects the synthetic prefix
and strips the id from outbound `functionCall`/`functionResponse` so the
internal identifier never leaks upstream. `shadow_parts` performs the
same strip when replaying a recorded assistant turn.
P2 — Vertex AI rejects empty `parameters` schemas. When an Anthropic tool
arrives with missing or empty `input_schema`, the proxy used to emit
`"parameters": {}` (no `type`), which fails Vertex AI validation with
`functionDeclaration parameters schema should be of type OBJECT`.
Contrary to the automated-review suggestion, the fix is not to omit
`parameters` (that too is rejected) but to normalize to the canonical
empty-object form `{type: "object", properties: {}}`.
Refs: google-gemini/generative-ai-python#423, BerriAI/litellm#5055.
Fix: new `ensure_object_schema` helper in `gemini_schema` promotes
missing `type` to `"object"` and adds empty `properties` when absent,
while leaving atomic (non-object) schemas untouched.
Tests: seven new regressions covering parallel no-id calls, cumulative
chunk id reuse, synthetic-id round-trip both directions, shadow replay
id stripping, and the three Vertex-AI schema shapes.
The two existing wrapper functions (`gemini_to_anthropic` and
`gemini_to_anthropic_with_shadow`) gain `#[allow(dead_code)]` to clear
a pre-existing clippy -D warnings failure — they are part of the public
transform API surface and intentionally kept for future callers.
Addresses Codex review P1/P2 on #1918.
* fix(proxy/gemini): narrow URL normalization + guard empty OAuth access_token
P2a — Preserve opaque relay URLs that contain `/v1/models/` prefixes.
`should_normalize_gemini_full_url` previously flagged any full URL whose
path merely contained `/v1beta/models/` or `/v1/models/` as a structured
Gemini endpoint, forcing rewrite to `.../v1beta/models/{model}:method`.
This silently dropped legitimate relay route segments (e.g.
`https://relay.example/v1/models/invoke` → `.../v1beta/models/...:generateContent`,
losing `/invoke`) and sent traffic to the wrong upstream path.
Replace the bare `contains(...)` checks with
`matches_structured_gemini_models_path`, which requires the
`/models/` segment to be followed by a canonical Gemini method call
(`*:generateContent` or `*:streamGenerateContent`). The
`matches_bare_gemini_models_path` helper is generalized (and renamed) to
handle both `/v1beta/models/` and `/v1/models/` alongside the original
bare `/models/` shape.
P2b — Reject empty Gemini OAuth access_tokens before they reach the
bearer header.
`GeminiAdapter::parse_oauth_credentials` accepts refresh-token-only JSON
(and surfaces `{"access_token": "", ...}` for expired credentials) with
`access_token` defaulting to `""`. The Claude adapter's GeminiCli branch
then called `AuthInfo::with_access_token(key, creds.access_token)`
unconditionally, so the bearer-header builder at
`AuthStrategy::GoogleOAuth` resolved to `Authorization: Bearer ` — a
deterministic 401 from upstream.
CC Switch does not currently exchange the refresh_token for a fresh
access_token (`OAuthCredentials::needs_refresh` / `can_refresh` are
annotated `#[allow(dead_code)]`). Until that exists, only attach
`access_token` when it is non-empty; fall back to plain GoogleOAuth
strategy with the raw key and log a warn pointing users at
`~/.gemini/oauth_creds.json` so the failure mode is observable.
Tests:
- gemini_url.rs: three new regressions — opaque `/v1/models/invoke`,
opaque `/v1beta/models/route`, and the positive counter-case where a
structured `/v1/models/...:generateContent` path still normalizes.
- claude.rs: three new `test_extract_auth_gemini_cli_*` tests covering
refresh-only JSON, empty-string access_token JSON, and the valid-JSON
pass-through.
All 839 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex review P2 findings on #1918.
* fix(proxy/gemini): treat empty-string functionCall id as missing in streaming path
Follow-up to the earlier P1 fix: some Gemini relays serialize an absent
functionCall id as `"id": ""` instead of omitting the field. The
non-streaming `extract_tool_call_meta` already filters these via
`.filter(|s| !s.is_empty())`, but the streaming counterpart
`extract_tool_calls` passed the empty string straight through
`function_call.get("id").and_then(|v| v.as_str())` into
`GeminiToolCallMeta::new`, producing a `Some("")` id.
Downstream, `merge_tool_call_snapshots` would then match two parallel
no-id calls against each other on their shared empty-string id,
collapsing them into a single snapshot (silent data loss for the first
call) and emitting an Anthropic `tool_use.id: ""` that breaks tool_result
correlation on the Claude Code client.
Fix:
- `extract_tool_calls`: apply the same `filter(|s| !s.is_empty())` guard
used in the non-streaming path so empty strings become `None` before
reaching the shadow meta.
- `merge_tool_call_snapshots`: defensively collapse any incoming
`Some("")` to `None` up front — keeps the "missing vs present" invariant
local to the merge step for future callers that might build
`GeminiToolCallMeta` by hand.
Tests (2 new, both in streaming_gemini):
- `parallel_empty_string_id_calls_are_treated_as_missing_and_preserved`
covers two parallel calls with explicit `"id": ""` — asserts both
surface, no empty tool_use id leaks, and each gets a unique
`gemini_synth_` id.
- `single_empty_string_id_tool_call_gets_synthesized_id` covers the
non-parallel degraded-relay case.
All 841 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex follow-up P1 on #1918.
* fix(proxy/gemini): gate generic REST path suffixes behind Google host whitelist
`should_normalize_gemini_full_url` previously treated any full URL whose
path ends with `/v1`, `/v1/models`, `/models`, `/v1/openai`, or `/openai`
as a structured Gemini endpoint and rewrote it to
`/v1beta/models/{model}:generateContent`. These are ubiquitous REST
conventions — opaque relays such as `https://relay.example/custom/v1`
legitimately use them for fixed endpoints — so the rewrite silently
routed traffic to the wrong upstream path.
Split the predicate into two layers:
- **Unconditional**: `matches_structured_gemini_models_path` (i.e. a
`/models/...:generateContent` method call anywhere in the path), the
Google-specific `/v1beta*` family, and the deep OpenAI-compat paths
(`/v1beta/openai/chat/completions`, `/openai/chat/completions`, and
their `responses` siblings). These remain host-agnostic because the
path grammar itself is Gemini-specific.
- **Google-host gated**: `/v1`, `/v1/models`, `/models`, `/v1/openai`,
`/openai`. Only normalized when the host is one of
`generativelanguage.googleapis.com`, `aiplatform.googleapis.com`, or a
real `*-aiplatform.googleapis.com` Vertex regional endpoint. The match
is exact/suffix (not `contains`), so lookalike hosts like
`aiplatform.example.com` are correctly treated as opaque relays.
Tests (8 new in `gemini_url::tests`):
- Four opaque-relay cases: `/custom/v1`, `/custom/models`,
`/custom/v1/models`, `/custom/openai` — all preserved as-is.
- Three Google-host counter-cases: `/v1`, `/models`, and
`us-central1-aiplatform.googleapis.com/v1` still normalize.
- One lookalike safety case: `aiplatform.example.com/v1` is NOT
treated as Google.
All 849 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex review P2 on #1918.
* fix(proxy/gemini): align shadow id with client-visible id in non-streaming path
When Gemini returns a `functionCall` without an id (common in 2.x
parallel calls), `gemini_to_anthropic_with_shadow_and_hints` previously
generated TWO independent synthesized UUIDs:
1. Line 186-197 — synthesized id `A` used for the Anthropic-visible
`content[tool_use].id` returned to the client.
2. Line 850-881 — `extract_tool_call_meta` independently synthesized
id `B ≠ A`, which populated `shadow_turn.tool_calls[i].id`.
`shadow_content` (line 225-228, cloned from `rectified_parts`) retained
the original missing/empty id. Result: the client sees id `A`, the
shadow store holds id `B`.
On the next turn, `convert_messages_to_contents` builds
`tool_name_by_id` from `build_tool_name_map_from_shadow_turns`, which
uses `tool_calls[i].id` — so the map contains `B → name` but not
`A → name`. When the client sends back `tool_result(tool_use_id=A)`,
resolution fails with:
Unable to resolve Gemini functionResponse.name for tool_use_id `A`
This affects both truncated histories (client sends only the
tool_result) and full histories (shadow-replay branch at line 342-354
skips `convert_message_content_to_parts`, so the assistant tool_use
block never registers id `A` itself).
Fix: make `rectified_parts` the single source of truth. After
`rectify_tool_call_parts`, run a pre-pass that writes
`synthesize_tool_call_id()` back into any `functionCall` that lacks a
non-empty id. All three readers — the content builder (186-197), the
shadow_content clone (225-228), and `extract_tool_call_meta` — then
observe the same id. `shadow_parts()` already strips synthesized ids on
replay (line 616-628), so the internal identifier never leaks to
Gemini upstream.
This mirrors the streaming path, which already has single-source-of-
truth semantics via `tool_call_snapshots` in `streaming_gemini.rs` —
no change needed there.
Tests (5 new in `transform_gemini::tests`):
- `non_stream_shadow_id_matches_client_visible_id`: asserts
`response.content[0].id == shadow.tool_calls[0].id ==
shadow.assistant_content.parts[0].functionCall.id`.
- `non_stream_missing_id_scenario_a_truncated_history_resolves`: turn 2
sends only `[tool_result(id=A)]`; resolution must succeed.
- `non_stream_missing_id_scenario_b_full_history_replay_resolves`: turn 2
sends `[assistant(tool_use=A), tool_result(A)]`; shadow-replay branch
strips the synth id from outgoing `functionCall` while still
resolving the subsequent `tool_result`.
- `non_stream_preserves_original_gemini_id_when_present`: regression —
genuine Gemini ids flow through unchanged.
- `non_stream_synthesized_id_not_leaked_to_gemini_via_shadow_replay`:
defensive — shadow-replay path must strip synth ids from both
`functionCall.id` and `functionResponse.id`.
All 854 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex follow-up P1 on #1918.
* refactor(proxy/gemini): share build_anthropic_usage between stream and non-stream paths
`streaming_gemini::anthropic_usage_from_gemini` and
`transform_gemini::build_anthropic_usage` were byte-for-byte identical
(32 lines each) — both converting Gemini `usageMetadata` into the
Anthropic `usage` shape including `cache_read_input_tokens` mapping.
Promote the non-streaming version to `pub(crate)` and reuse it from the
streaming SSE converter. Removes ~30 lines of duplication and guarantees
the two paths cannot drift apart.
No behavioral change; all 854 lib tests pass; cargo fmt + clippy -D
warnings clean.
* fix(proxy/gemini): gate /v1beta behind Google host + normalize models/ model id prefix
Two related P2 corrections to the Gemini Native URL surface, both
folding into the existing Google-host-whitelist architecture.
## P2a — `/v1beta` suffix should not unconditionally trigger rewrite
`should_normalize_gemini_full_url` placed `/v1beta` and `/v1beta/models`
in the unconditional layer on the reasoning that `/v1beta` is
Google-specific. In practice an opaque relay fronting a non-Gemini
service at `https://relay.example/custom/v1beta` would still be
silently rewritten to `/v1beta/models/{model}:generateContent`,
breaking the deployment.
Move `/v1beta`, `/v1beta/models`, and `/v1beta/openai` into the
Google-host gated layer alongside `/v1`, `/models`, and friends. The
unconditional layer now only accepts paths whose grammar is
intrinsically Gemini — `/models/...:generateContent` method calls and
the deep OpenAI-compat endpoints like `/openai/chat/completions` and
`/openai/responses`. Pasted AI-Studio URLs such as
`https://generativelanguage.googleapis.com/v1beta` still normalize
because the host matches the whitelist.
## P2b — `model: "models/gemini-2.5-pro"` produced doubled path prefix
Gemini SDKs (and the official `list_models` response) commonly surface
model ids in resource-name form `models/gemini-2.5-pro`. Raw
interpolation into `format!("/v1beta/models/{model}:...")` produced
`/v1beta/models/models/gemini-2.5-pro:streamGenerateContent` which
upstream rejects — yielding false-negative health checks for otherwise
valid provider configs.
Introduce `normalize_gemini_model_id(&str) -> &str` in `gemini_url`
as the single source of truth: strips an optional leading `/` then an
optional `models/` prefix, leaving bare ids untouched. Apply in the
three call sites that build a Gemini method URL:
- `services/stream_check.rs::resolve_claude_stream_url` (unified path)
- `services/stream_check.rs::check_gemini_stream` (Gemini-only path)
- `proxy/forwarder.rs::rewrite_claude_transform_endpoint` (production)
Tests (9 new):
- `gemini_url`: 3 regressions for opaque vs Google-host `/v1beta*`
handling + 5 unit tests pinning `normalize_gemini_model_id` behavior
(strip prefix, leave bare id, preserve nested slashes past the one
stripped prefix, tolerate leading slash, pass through empty input).
- `stream_check`: one end-to-end regression confirming
`models/gemini-2.5-pro` collapses to the expected single-prefix URL.
- `forwarder`: one end-to-end regression on the production rewrite
path.
All 864 lib tests pass; cargo fmt + clippy -D warnings clean.
Addresses Codex P2 feedback on #1918.
* fix(proxy/gemini): trim API key before provider-type detection and OAuth parsing
Leading whitespace on a copied oauth_creds.json (e.g. trailing newline
when the user copies the file content as-is) would slip past the
`starts_with("ya29.") || starts_with('{')` prefix check in
`ClaudeAdapter::provider_type`, causing the provider to be misclassified
as raw-API-key Gemini and fall back to `x-goog-api-key` with the raw
JSON as the key — which upstream rejects with 401.
The frontend's `handleApiKeyChange` already trims on keystrokes but
deep-link imports, the JSON editor, and live-config backfill all bypass
that path. Trim at every backend extraction point so the coverage is
uniform:
- `ClaudeAdapter::extract_key` (5 env / fallback branches) gets
`.map(str::trim)` before `.filter(|s| !s.is_empty())` so that
whitespace-only values are also treated as missing.
- `GeminiAdapter::extract_key_raw` gets the same chain (including
the `.filter` it was missing before).
- `GeminiAdapter::parse_oauth_credentials` gets a defensive
`let key = key.trim();` at the entry as a belt-and-suspenders guard.
Adds two regression tests covering JSON and bare `ya29.` keys with
leading newline/space.
* fix(proxy/gemini): gate generic REST suffix stripping behind Google host in non-full-URL mode
`build_gemini_native_url` unconditionally stripped `/v1`, `/v1beta`,
`/models`, and `/openai` suffixes from the base path regardless of
host. This worked for Google's own endpoints but silently rewrote
third-party relay URLs like `https://relay.example/custom/v1` to
`.../custom/v1beta/models/...`, breaking any relay that mounts its
Gemini-compatible namespace under a versioned prefix.
The result was also asymmetric with the previously-fixed full-URL
branch: toggling the "full URL" switch changed the outbound URL for
the same base_url, which is exactly the kind of invisible behavior
that makes debugging proxy deployments painful.
Align `normalize_gemini_base_path` with
`should_normalize_gemini_full_url`'s layered model:
- Unconditional: `/models/...:method` structured paths and deep
OpenAI-compat endpoints (`/openai/chat/completions`,
`/openai/responses` and their versioned variants) — these are
unambiguous Gemini-specific grammar on any host.
- Google-host gated: generic `/v1`, `/v1beta`, `/models`, `/openai`
suffixes only get stripped on `generativelanguage.googleapis.com`,
`aiplatform.googleapis.com`, or `*-aiplatform.googleapis.com`.
Other hosts preserve the prefix verbatim so relays keep their
intended routing.
Adds seven regression tests for the non-full-URL flow: opaque relay
preservation (v1 / v1beta / models / openai suffix variants), Google
host normalization (counter-case), and boundary cases (structured
method path and deep OpenAI-compat endpoint stripped regardless of
host).
Test count: 864 -> 873.
* Revert "fix(proxy/gemini): gate generic REST suffix stripping behind Google host in non-full-URL mode"
This reverts commit d19ff09cb7.
* test(proxy/gemini): pin non-full-URL versioned relay base stripping
Adds two regression tests that lock in the intentional asymmetry
between full-URL and non-full-URL modes:
- Full-URL mode: opaque base path (e.g. `https://relay.example/custom/v1beta`)
is preserved verbatim. Already covered by
`preserves_opaque_full_url_with_bare_v1beta_suffix`.
- Non-full-URL mode: base path MUST strip `/v1`, `/v1beta`, etc. so the
standard `/v1beta/models/{model}:method` endpoint can be appended
without producing a doubled `/v1beta/v1beta/models/...` path.
The non-full-URL contract is "base URL + cc-switch appends the
canonical Gemini endpoint". A user who needs a relay's custom
namespace (e.g. `/v1/models/...`) must use full-URL mode and paste
the complete method path. This commit adds regression coverage so a
future attempt to mirror full-URL's host-whitelist gating into
`normalize_gemini_base_path` will fail the test suite immediately.
* chore(lint): address clippy 1.95 findings in existing modules
CI upgraded to Rust 1.95 and flagged ten pre-existing warnings that
older toolchains did not enforce. None relate to the Gemini proxy
integration PR itself but they block CI on the feature branch, so
clean them up here as a separate commit for easy review:
collapsible_match:
- proxy/providers/gemini_schema.rs: `"items" if value.is_object()`
match guard instead of nested if.
- proxy/providers/transform_responses.rs: fold
`map_responses_stop_reason`'s `"completed"` / `"incomplete"` arms
into match guards, relying on the existing `_ => "end_turn"` fall-
through for non-matching guard conditions (semantics preserved).
- services/session_usage_codex.rs: fold
`"session_meta" if state.session_id.is_none()` guard, relying on
the existing `_ => {}` fall-through.
unnecessary_sort_by:
- services/provider/endpoints.rs: `sort_by_key(|ep| Reverse(ep.added_at))`.
- services/skill.rs (backup list): same Reverse idiom on `created_at`.
- services/skill.rs (skill listings x2): `sort_by_key(|s| s.name.to_lowercase())`.
useless_conversion:
- services/skill.rs: drop the explicit `.into_iter()` on `zip`'s argument.
while_let_loop:
- services/webdav_auto_sync.rs: `while let Some(wait_for) = ...`
instead of `loop { let Some(...) = ... else { break }; ... }`.
All changes are mechanical and preserve behavior. `cargo test --lib`
remains green (868 passed).
* fix(proxy/gemini): reconcile synthesized tool-call ids with later real ids + preserve thoughtSignature
Three related findings on `streaming_gemini.rs` for Gemini's cumulative
`streamGenerateContent` stream, all centered on `merge_tool_call_snapshots`:
1. (P1) Match upgraded tool-call IDs by position.
When Gemini delivers a `functionCall` without an id on chunk 1
(cc-switch synthesizes `gemini_synth_*`) and then upgrades it to a
real id on chunk 2, the `Some(incoming_id)` branch only matched by
id and missed the existing synthesized snapshot. A second entry
would be pushed, yielding duplicate `tool_use` content blocks at
stream end — one with the synthesized id, one with the real id —
which could trigger duplicate tool execution and break tool_result
correlation. Add a positional fallback: when no id match exists but
the same-position slot holds a synthesized id, merge into it.
`or(preserved_id)` already lets the real id win the merge.
2. (P2) Preserve prior thoughtSignature when merging snapshots.
`tool_call_snapshots[index] = tool_call` overwrote the slot
entirely, dropping any `thoughtSignature` captured on an earlier
chunk if the current cumulative snapshot omitted it. Since
`build_shadow_assistant_parts` writes `thoughtSignature` into the
shadow turn from `tool_call.thought_signature`, a dropped signature
would cause later replay requests to Gemini to be rejected with
invalid-signature errors. Preserve the existing signature when the
incoming chunk does not carry one.
3. (P2) Document the part-order streaming trade-off.
All `tool_use` content blocks are emitted after the final text
`content_block_stop`, so interleaved [text, functionCall, text,
functionCall] parts arrive at the Anthropic client as [text(concat),
tool_use, tool_use] — different from the non-streaming transformer,
which preserves part order. This is intentional given the cumulative
snapshot model and the consumers we target (claude-code-like clients
don't depend on strict interleaving for tool execution correctness).
Add a block comment at the flush site describing the trade-off and
what a strict-order fix would entail, so this isn't rediscovered as
a bug later.
Regression tests:
- upgraded_real_id_merges_into_existing_synthesized_snapshot
- thought_signature_preserved_when_later_chunk_omits_it
Test count: 868 -> 870. clippy 1.95 clean. fmt clean.
* fix(proxy/gemini): prefer exact tool-call id over normalized-name fallback
The shadow-turn matcher used a three-branch `||` chain (id / full name /
normalized name). When two tools share a suffix (e.g. `server_a:search`
and `server_b:search`), the normalized-name clause could short-circuit
on an earlier turn whose id is actually wrong for the incoming tool_use,
mis-routing replay state (functionCall id / thoughtSignature) for later
tool_result resolution.
Split matching into two layers: when the incoming message carries any
tool_use ids, run id-based lookup first and return on the earliest hit.
Only fall back to full-name / normalized-name matching when the incoming
ids are absent or none of them resolve.
Add two regressions:
- shadow_replay_prefers_exact_id_match_over_normalized_name_collision
Two shadow turns with colliding normalized names and two assistant
messages whose ids cross the positional order; asserts each message
replays the id-correct shadow turn (including thoughtSignature).
- shadow_replay_falls_back_to_name_when_ids_absent
Shadow turn with no id and incoming tool_use with an empty id;
asserts the name fallback still populates the replayed part.
---------
Co-authored-by: Jason <farion1231@gmail.com>
Jason
涂瑜
Coconut-Fish
santugege
Jesus Díaz Rivas
lif
nmsn
tison
xpfo
Li Yang
Suda202
hotelbe
YaoguoHH
Dex Miller