445 Commits

Author	SHA1	Message	Date
TUGOhost	92f4278039	feat: add auto model resolution and model creation timestamp tracking ... - Add 'created' field to model registry for tracking model creation time - Implement GetFirstAvailableModel() to find the first available model by newest creation timestamp - Add ResolveAutoModel() utility function to resolve "auto" model name to actual available model - Update request handler to resolve "auto" model before processing requests - Ensures automatic model selection when "auto" is specified as model name This enables dynamic model selection based on availability and creation time, improving the user experience when no specific model is requested.	2025-11-11 20:30:09 +08:00
Luis Pater	8ae8a5c296	Fixed: #233 ... feat(management): add auth ID normalization and file-based ID resolution Introduce `authIDForPath` to standardize ID generation from file paths, improving consistency in authentication handling. Update `registerAuthFromFile` and `disableAuth` to utilize normalized IDs, incorporating relative path resolution and file name extraction where applicable.	2025-11-11 19:23:31 +08:00
Luis Pater	dc804e96fb	fix(management): improve error handling and normalize YAML comment indentation ... Enhance error management for file operations and clean up temporary files. Add `NormalizeCommentIndentation` function to ensure YAML comments maintain consistent formatting.	2025-11-11 08:37:57 +08:00
Luis Pater	ab76cb3662	feat(management): add Vertex service account import and WebSocket auth management ... Introduce an endpoint for importing Vertex service account JSON keys and storing them as authentication records. Add handlers for managing WebSocket authentication configuration.	2025-11-10 20:48:31 +08:00
Luis Pater	2965bdadc1	fix(translator): remove debug print statement from OpenAI Gemini request processing	2025-11-10 18:37:05 +08:00
Luis Pater	40f7061b04	feat(watcher): debounce config reloads to prevent redundant operations ... Introduce `scheduleConfigReload` with debounce functionality for config reloads, ensuring efficient handling of frequent changes. Added `stopConfigReloadTimer` for stopping timers during watcher shutdown.	2025-11-10 12:57:40 +08:00
Luis Pater	8c947cafbe	Merge branch 'vertex' into dev	2025-11-10 12:24:07 +08:00
Luis Pater	717eadf128	feat(vertex): add support for Vertex AI Gemini authentication and execution ... Introduce Vertex AI Gemini integration with support for service account-based authentication, credential storage, and import functionality. Added new executor for Vertex AI requests, including execution and streaming paths, and integrated it into the core manager. Enhanced CLI with `--vertex-import` flag for importing service account keys.	2025-11-10 12:23:51 +08:00
Luis Pater	9e105738fd	fix(server): add PATCH method to CORS allowed methods	2025-11-10 12:12:05 +08:00
Luis Pater	5d806fcefc	fix(translator): support system instructions with parts and inline data in OpenAI Gemini requests ... Handle both `systemInstruction` and `system_instruction` keys, processing text and inline data parts (e.g., images) for system messages in Gemini.	2025-11-10 10:31:32 +08:00
hkfires	43095de162	fix(management): exclude disabled runtime-only auths from file entries	2025-11-10 08:32:42 +08:00
Luis Pater	ef7e8206d3	fix(executor): ensure usage reporting for upstream responses lacking usage data ... Add `ensurePublished` to guarantee request counting even when usage fields (e.g., tokens) are absent in OpenAI-compatible executor responses, particularly for streaming paths.	2025-11-09 17:24:47 +08:00
hkfires	51d2766d5c	fix(management): sanitize keys and normalize headers	2025-11-09 12:13:02 +08:00
hkfires	a00ba77604	refactor(config): rename SyncGeminiKeys; use Sanitize* methods	2025-11-09 08:29:47 +08:00
hkfires	cfb9cb8951	feat(config): support HTTP headers across providers	2025-11-08 20:52:05 +08:00
Luis Pater	1afbc4dd96	fix(translator): separate tool calls from content in OpenAI Claude requests	2025-11-08 17:57:46 +08:00
Luis Pater	d745f07044	fix(registry): replace Gemini model list with updated stable and preview versions	2025-11-08 15:51:57 +08:00
Luis Pater	695eaa5450	docs(instructions): add Codex operational and review guidelines ... Added detailed operational instructions for Codex agents based on GPT-5, covering shell usage, editing constraints, sandboxing policies, and approval mechanisms. Also included comprehensive review process guidelines for flagging and communicating issues effectively.	2025-11-08 15:19:51 +08:00
Luis Pater	67ad26c35a	fix(executor): remove default reasoning effort for gpt-5-codex-mini	2025-11-08 11:56:32 +08:00
Luis Pater	30d448e73c	fix(executor): update model name from codex-mini-latest to gpt-5-codex-mini	2025-11-08 11:17:40 +08:00
jeffnash	ec354f7a1a	add default medium reasoning case for gpt-5-codex-mini ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-11-07 17:12:10 -08:00
jeffnash	240e782606	add default medium reasoning case for gpt-5-codex-mini ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-11-07 17:11:40 -08:00
Jeff Nash	fcb0293c0d	feat(registry): add GPT-5 Codex Mini model variants ... Adds three new Codex Mini model variants (mini, mini-medium, mini-high) that map to codex-mini-latest. Codex Mini supports medium and high reasoning effort levels only (no low/minimal). Base model defaults to medium reasoning effort.	2025-11-07 17:07:39 -08:00
Luis Pater	682c4598ee	fix(translator): handle gjson strings in OpenAI response formatting	2025-11-08 00:41:56 +08:00
Luis Pater	a7d105bd69	Fixed: #223 ... fix(registry): add `MiniMax-M2` model to registry definitions	2025-11-08 00:10:51 +08:00
Luis Pater	b9eef45305	Merge pull request #222 from router-for-me/api ... Return auth info from memory	2025-11-07 22:41:12 +08:00
Luis Pater	c8f20a66a8	fix(executor): add logging and prompt cache key handling for OpenAI responses	2025-11-07 22:40:45 +08:00
hkfires	1f6a384c9a	fix(api): omit auth file entries lacking path unless runtime-only	2025-11-07 19:15:54 +08:00
hkfires	c9fc033cf5	feat(management): support in-memory auth listing with disk fallback	2025-11-07 19:04:54 +08:00
hkfires	d60040b222	fix(translator): accept camelCase thinking config in OpenAI→Gemini	2025-11-07 16:45:31 +08:00
Luis Pater	3ce1b4159b	fix(executor): remove outdated Gemini model previews from CLI fallback order	2025-11-07 10:30:22 +08:00
Luis Pater	7516ac4ce7	fix(registry): add gemini-3-pro-preview-11-2025 model to Gemini CLI model definitions	2025-11-06 08:47:17 +08:00
Luis Pater	2a73d8c4a3	fix(translator): simplify tool response handling and adjust JSON schema updates in Gemini modules	2025-11-05 22:48:50 +08:00
Luis Pater	10be026ace	fix(translator): remove strict field from Gemini Claude tool initialization	2025-11-05 18:14:58 +08:00
Luis Pater	e18e288fda	fix(registry): Remove gemini-2.5-flash-image Gemini models from gemini cli and add gemini-2.5-flash-image preview to AIStudio ... These models were likely for internal preview or testing and are no longer relevant for public use.	2025-11-04 03:02:16 +08:00
Luis Pater	38cfbac8f0	fix(executor): adjust Anthropic-Beta header handling for consistent API requests	2025-11-03 20:49:01 +08:00
Luis Pater	5be4d22b9b	fix(executor): ensure consistent header application in Claude API requests	2025-11-03 17:57:20 +08:00
Luis Pater	64774a5786	fix(executor): remove safetySettings from payload in token counting request	2025-11-03 17:31:43 +08:00
Luis Pater	89b0d53a09	fix(executor): remove safetySettings from payload for Gemini requests	2025-11-01 16:53:48 +08:00
Luis Pater	fd2b23592e	Fixed: #193 ... fix(translator): consolidate temperature and top_p conditionals in OpenAI Claude request Fixed: #169 fix(translator): adjust instruction strings in Codex Claude and OpenAI responses	2025-11-01 15:37:51 +08:00
hkfires	2021ae3891	fix(config): skip persisting empty API key and compat entries	2025-10-31 15:56:47 +08:00
hkfires	5c65938113	fix(config): stabilize YAML sequence merges by reordering items	2025-10-31 15:21:58 +08:00
hkfires	16be3f0a12	fix(config): dedupe and normalize Gemini keys and headers	2025-10-31 13:20:10 +08:00
hkfires	7c1c4ee60b	feat(gemini): add Gemini API key endpoints	2025-10-31 11:09:28 +08:00
Luis Pater	96c7271448	Merge pull request #191 from router-for-me/gemini ... Add safety settings for gemini models	2025-10-31 09:24:37 +08:00
Luis Pater	07da781336	feat(registry): add client model support check for executor filtering ... - Introduced `ClientSupportsModel` function to `ModelRegistry` for verifying client support for specific models. - Integrated model support validation into executor candidate filtering logic. - Updated CLIProxy registry interface to include the new support check method.	2025-10-31 09:15:14 +08:00
hkfires	a53c84d0d1	feat(gemini): apply default safety settings across request translators	2025-10-31 08:22:16 +08:00
hkfires	a517290726	refactor(executor): summarize API error bodies of html in debug logs	2025-10-31 06:58:38 +08:00
Luis Pater	af3fbd134d	fix(translator): remove strict key from function declaration to prevent errors during schema transformation	2025-10-30 13:14:26 +08:00
hkfires	1bbbd16df6	chore(logging): clarify 429 rate-limit retries in Gemini executor	2025-10-29 19:19:18 +08:00