From 91c7c0310e6f112900cadd755db912ad4f897fdb Mon Sep 17 00:00:00 2001 From: James Magahern Date: Thu, 12 Nov 2026 15:53:33 -0800 Subject: [PATCH] refactor: remove retired agent provider integration --- docker-compose.example.yml | 3 - docs/api/rest.md | 25 +++--- docs/api/streaming-chat.md | 10 +-- ios/AGENTS.md | 1 - .../Sybil/Sources/Sybil/SybilModels.swift | 17 ++-- .../Sources/Sybil/SybilSettingsStore.swift | 10 +-- .../Sybil/Sources/Sybil/SybilViewModel.swift | 7 +- .../Tests/SybilTests/ProviderTests.swift | 39 +++++++++ .../SybilTests/SybilInlineMentionTests.swift | 5 +- server/README.md | 9 ++- server/prisma/schema.prisma | 16 ++-- server/scripts/ensure-prisma-client.mjs | 5 +- server/src/env.ts | 10 --- server/src/llm/model-catalog.ts | 4 +- server/src/llm/multiplexer.ts | 13 +-- server/src/llm/provider-adapters.ts | 36 +-------- server/src/llm/provider-ids.ts | 38 ++------- server/src/llm/providers.ts | 12 --- server/src/llm/streaming.ts | 7 +- server/src/llm/types.ts | 2 +- server/src/message-generation.ts | 4 +- server/src/routes.ts | 18 ++--- server/tests/agent-inline.test.ts | 9 ++- server/tests/chat-tools-streaming.test.ts | 4 +- server/tests/provider-adapters.test.ts | 9 +-- server/tests/provider-ids.test.ts | 30 ++++--- server/tests/provider-retirement.test.ts | 80 +++++++++++++++++++ tui/README.md | 2 +- tui/src/config.ts | 2 +- tui/src/index.ts | 20 ++--- tui/src/types.ts | 4 +- web/src/App.tsx | 4 +- .../components/settings/model-settings.tsx | 8 +- web/src/hooks/use-lite-workspace.ts | 4 +- web/src/lib/api.ts | 5 +- web/src/lib/chat-model-selection.ts | 3 +- web/src/lib/message-generation.ts | 1 - web/src/lib/workspace-domain.ts | 13 +-- web/tests/app-settings.browser.mjs | 10 ++- web/tests/chat-model-selection.test.mjs | 6 ++ web/tests/message-generation.test.mjs | 2 +- web/tests/workspace-domain.test.mjs | 9 ++- 42 files changed, 271 insertions(+), 245 deletions(-) create mode 100644 ios/Packages/Sybil/Tests/SybilTests/ProviderTests.swift create mode 100644 server/tests/provider-retirement.test.ts diff --git a/docker-compose.example.yml b/docker-compose.example.yml index cc1119b..1bf8474 100644 --- a/docker-compose.example.yml +++ b/docker-compose.example.yml @@ -13,9 +13,6 @@ services: ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-} XAI_API_KEY: ${XAI_API_KEY:-} GEMINI_API_KEY: ${GEMINI_API_KEY:-} - HERMES_AGENT_API_BASE_URL: ${HERMES_AGENT_API_BASE_URL:-http://127.0.0.1:8642/v1} - HERMES_AGENT_API_KEY: ${HERMES_AGENT_API_KEY:-} - HERMES_AGENT_MODEL: ${HERMES_AGENT_MODEL:-} EXA_API_KEY: ${EXA_API_KEY:-} BRAVE_SEARCH_API_KEY: ${BRAVE_SEARCH_API_KEY:-} CHAT_WEB_SEARCH_ENGINE: ${CHAT_WEB_SEARCH_ENGINE:-exa} diff --git a/docs/api/rest.md b/docs/api/rest.md index 695cc32..602e7e2 100644 --- a/docs/api/rest.md +++ b/docs/api/rest.md @@ -37,14 +37,13 @@ Chat upload limits: "openai": { "models": ["chat-latest", "gpt-4.1-mini"], "loadedAt": "2026-02-14T00:00:00.000Z", "error": null }, "anthropic": { "models": ["claude-3-5-sonnet-latest"], "loadedAt": null, "error": null }, "xai": { "models": ["grok-3-mini"], "loadedAt": null, "error": null }, - "gemini": { "models": ["gemini-3.5-flash"], "loadedAt": null, "error": null }, - "hermes-agent": { "models": ["hermes-agent"], "loadedAt": null, "error": null } + "gemini": { "models": ["gemini-3.5-flash"], "loadedAt": null, "error": null } } } ``` +- Selectable providers are `openai`, `anthropic`, `xai`, and `gemini`. Unsupported provider IDs are rejected with HTTP 400 by chat creation, chat completion, and Quick Question endpoints. Sybil Agent runs through its dedicated room or an inline `@sybil` mention; it is not a model-catalog provider. - OpenAI model lists are filtered to models that are expected to work with the backend's Responses API implementation, including the exact `chat-latest` alias when returned by OpenAI. Audio, image-generation, embedding, moderation, and other specialized model ids remain excluded. See [OpenAI's Chat Latest documentation](https://developers.openai.com/api/docs/models/chat-latest) for supported capabilities. - Gemini model lists are loaded from Google's native Models API and filtered to Gemini `generateContent` model ids. -- `hermes-agent` is included only when `HERMES_AGENT_API_KEY` is configured. Set it to Hermes `API_SERVER_KEY`, or any non-empty value if that local server does not require auth. `HERMES_AGENT_API_BASE_URL` defaults to `http://127.0.0.1:8642/v1`; set `HERMES_AGENT_MODEL` only when you need an additional fallback/override model id. - The backend loads provider model lists at startup and refreshes them about once every 24 hours. If a later provider refresh fails, the response keeps the last loaded model list for that provider and sets `error` to the latest failure message. ## Chat Tools @@ -148,7 +147,7 @@ History search (`q`) notes: ```json { "title": "optional title", - "provider": "optional openai|anthropic|xai|gemini|hermes-agent", + "provider": "optional openai|anthropic|xai|gemini", "model": "optional model id", "additionalSystemPrompt": "optional stored system prompt", "enabledTools": ["web_search", "fetch_url"], @@ -286,7 +285,7 @@ Notes: { "chatId": "optional-chat-id", "clientRequestId": "optional-client-generated-id", - "provider": "openai|anthropic|xai|gemini|hermes-agent", + "provider": "openai|anthropic|xai|gemini", "model": "string", "messages": [ { @@ -337,7 +336,8 @@ Behavior notes: - If `chatId` is present, server validates chat existence. - `clientRequestId` is an optional stable identifier for retries of a persisted inline Agent completion. - For a persisted ordinary chat, a literal case-insensitive `@sybil` token in the latest user message invokes the existing persistent Sybil Agent instead of the selected provider for that turn. Email addresses, code spans/fences, indented code, and Markdown quote lines do not trigger it. The message and Agent reply remain visible in the chat; both are marked as Agent asides and are excluded by the backend from later selected-provider conversation history. The Agent root request is not projected into the visible Agent transcript. -- The completion response identifies an inline Agent reply with `provider: "hermes-agent"`, `model: "sybil-agent"`, and `message.name: "Sybil Agent"`, `message.agentAside: true`. +- The completion response identifies an inline Agent reply with `provider: "sybil-agent"`, `model: "sybil-agent"`, and `message.name: "Sybil Agent"`, `message.agentAside: true`. +- The response provider identity can therefore differ from the request's selectable provider. Clients must accept `sybil-agent` in completion responses without adding it to provider selectors. - Agent asides are identified by backend-stored `metadata.agentAside`, not client-supplied metadata. The ordinary-chat list/history APIs above support Agent tools reading the complete visible thread, including prior asides and attachment data, with cursor pagination. - Before the Agent is invoked, the backend paginates and supplies the complete safe visible-thread projection as required initial context; the Agent does not have to choose `read_chat_history` for the current thread. User/assistant asides and full supported attachment representations are included, while system/tool rows and unrelated metadata are excluded. Historical content remains untrusted context, not new authority. - The initial context transfer is limited to 30 MiB. A stored text attachment marked truncated, incomplete history, or a transfer/provider context-limit failure returns an explicit error and no answer from partial history; providers may reject a complete thread that exceeds their model context window. @@ -355,10 +355,9 @@ Behavior notes: - For `anthropic`, backend calls Anthropic's Messages API and enables internal tool use with Anthropic `tool_use`/`tool_result` content blocks. - For `xai`, backend calls xAI's OpenAI-compatible Chat Completions API and enables internal tool use with the same internal system instruction. - For `gemini`, backend calls Google's native Gemini `generateContent` API and enables internal tool use with Gemini function calling. -- For `hermes-agent`, backend calls the configured Hermes Agent OpenAI-compatible Chat Completions API without adding Sybil-managed tool definitions; Hermes Agent handles its own tools server-side. - For `openai`, image attachments are sent as Responses `input_image` items and text attachments are sent as `input_text` items. - For `gemini`, image attachments are sent as native Gemini `inlineData` parts and text attachments are sent as text parts. -- For `xai` and `hermes-agent`, image attachments are sent as Chat Completions content parts alongside text. +- For `xai`, image attachments are sent as Chat Completions content parts alongside text. - For `openai`, Responses calls that can enter the server-managed tool loop use `store: true` so reasoning and function-call items can be passed between tool rounds. - For `anthropic`, image attachments are sent as Messages API `image` blocks using base64 source data; text attachments are added as `text` blocks. - Available Sybil-managed tool calls for `openai`, `anthropic`, `xai`, and `gemini`: `web_search` and `fetch_url`. When `CHAT_CODEX_TOOL_ENABLED=true`, `codex_exec` is also available. When `CHAT_SHELL_TOOL_ENABLED=true`, `shell_exec` is also available. @@ -481,6 +480,8 @@ Behavior notes: ## Type Shapes +Saved selections for unsupported provider IDs are returned as `null` for both the provider and its paired model. Chat messages and historical call records are preserved; an unsupported `calls[].provider` is returned as `null`, while the original call request/response snapshots remain unchanged. Clients should choose a supported provider before continuing those chats. + `ChatSummary` ```json { @@ -492,9 +493,9 @@ Behavior notes: "updatedAt": "...", "starred": false, "starredAt": null, - "initiatedProvider": "openai|anthropic|xai|gemini|hermes-agent|null", + "initiatedProvider": "openai|anthropic|xai|gemini|null", "initiatedModel": "string|null", - "lastUsedProvider": "openai|anthropic|xai|gemini|hermes-agent|null", + "lastUsedProvider": "openai|anthropic|xai|gemini|null", "lastUsedModel": "string|null", "additionalSystemPrompt": null, "enabledTools": ["web_search", "fetch_url"] @@ -546,9 +547,9 @@ Behavior notes: "updatedAt": "...", "starred": false, "starredAt": null, - "initiatedProvider": "openai|anthropic|xai|gemini|hermes-agent|null", + "initiatedProvider": "openai|anthropic|xai|gemini|null", "initiatedModel": "string|null", - "lastUsedProvider": "openai|anthropic|xai|gemini|hermes-agent|null", + "lastUsedProvider": "openai|anthropic|xai|gemini|null", "lastUsedModel": "string|null", "additionalSystemPrompt": null, "enabledTools": ["web_search", "fetch_url"], diff --git a/docs/api/streaming-chat.md b/docs/api/streaming-chat.md index c865c08..2f3982d 100644 --- a/docs/api/streaming-chat.md +++ b/docs/api/streaming-chat.md @@ -26,7 +26,7 @@ Web presentation note: `/lite` uses these same chat streams and existing search "chatId": "optional-chat-id", "persist": true, "clientRequestId": "optional-client-generated-id", - "provider": "openai|anthropic|xai|gemini|hermes-agent", + "provider": "openai|anthropic|xai|gemini", "model": "string", "messages": [ { @@ -76,7 +76,8 @@ Notes: - `maxTokens` is optional. For `anthropic`, when omitted the backend requests the selected model's maximum output token limit from Anthropic's Models API and uses that as `max_tokens`; if the model limit cannot be loaded, the fallback is 128000. For other providers, omitted `maxTokens` is not sent as an explicit cap. - Attachments are optional and are persisted under `message.metadata.attachments` on stored user messages when `persist` is `true`. - For a persisted ordinary chat, a literal case-insensitive `@sybil` token in the latest user message invokes the existing persistent Sybil Agent instead of the selected provider. Email addresses, code spans/fences, indented code, and Markdown quote lines do not trigger it. The visible user message and inline Agent reply remain in the ordinary chat and are marked with backend-owned `metadata.agentAside`; the backend excludes both from later selected-provider context without deleting the visible rows. This routing does not apply to the special Agent tab or Quick Questions. -- The `meta` event for an inline Agent reply contains `provider: "hermes-agent"`, `model: "sybil-agent"`, and `agentAside: true`. The selected ordinary provider is not run for that turn. Clients should render the response with the existing Sybil Agent identity and retain aside metadata on the optimistic streaming message until the canonical REST refresh. +- The `meta` event for an inline Agent reply contains `provider: "sybil-agent"`, `model: "sybil-agent"`, and `agentAside: true`. The selected ordinary provider is not run for that turn. Clients should render the response with the existing Sybil Agent identity and retain aside metadata on the optimistic streaming message until the canonical REST refresh. +- `sybil-agent` is a response identity, not an accepted request provider or a model-picker option. Decode completion metadata independently from the selectable provider list. Active-stream attachment and completed-request retries use the same identity. - Before the Agent request starts, the backend loads every page of the safe visible thread and sends it as required initial context, including previous asides and supported attachment contents. This is not an optional `read_chat_history` tool call. Hidden system/tool rows and unrelated metadata are excluded; transcript data is untrusted context. If history/attachment projection is incomplete or exceeds the 30 MiB transfer limit, or the Agent model rejects the complete context, the stream reports an error and emits no partial-context answer. Persisted chat streams with a `chatId` are backend-owned active runs: @@ -105,7 +106,7 @@ This endpoint is intended for clients that restored an active `chatId` from `GET Request body: ```json { - "provider": "openai|anthropic|xai|gemini|hermes-agent", + "provider": "openai|anthropic|xai|gemini", "model": "string", "question": "What is the capital of France?", "enabledTools": ["web_search", "fetch_url"], @@ -218,10 +219,9 @@ Terminal tool-call event: - `xai`: backend uses xAI's OpenAI-compatible Chat Completions API and may execute the same internal tool calls before producing final text. - `gemini`: backend uses Google's native Gemini `streamGenerateContent` API and may execute the same internal tool calls before producing final text. - `fetch_url` sends browser-like navigation headers for outbound URL requests to reduce false 403s from sites that reject generic server clients. It converts HTML to text and extracts selectable PDF text page by page (without OCR), including when the response media type is inaccurate but the PDF signature is present. URL downloads are limited to 10 MiB, PDF extraction to 30 pages per call and an isolated worker terminated after 8 seconds, and accumulated PDF text to `maxCharacters` (default 12,000; maximum 50,000), plus a brief truncation hint. PDF tool results include `pdfStatus`, `pageCount`, and selected `pages`; call with `pages:[...]` to retrieve specific pages. Encrypted, page-free, and text-free PDFs return explicit status and text with `ok:false`. Oversized responses fail with a size-limit error. -- `hermes-agent`: backend uses the configured Hermes Agent OpenAI-compatible Chat Completions API. Sybil does not add its own tool definitions for this provider; Hermes Agent handles its own tools server-side. Custom Hermes stream events are normalized away unless they produce text deltas in this SSE contract. - `openai`: image attachments are sent as Responses `input_image` items; text attachments are sent as `input_text` items. - `gemini`: image attachments are sent as native Gemini `inlineData` parts; text attachments are inlined as text parts. -- `xai` and `hermes-agent`: image attachments are sent as Chat Completions content parts; text attachments are inlined as text parts. +- `xai`: image attachments are sent as Chat Completions content parts; text attachments are inlined as text parts. - `openai`: Responses calls that can enter the server-managed tool loop use `store: true` so reasoning and function-call items can be passed between tool rounds. - `anthropic`: streamed via event stream; emits `delta` from `content_block_delta` with `text_delta`, and emits normalized `tool_call` SSE events when Anthropic `tool_use` blocks are executed. Image attachments are sent as base64 `image` blocks and text attachments are appended as `text` blocks. - `web_search` uses `CHAT_WEB_SEARCH_ENGINE`: `exa` (default), `brave` (requires `BRAVE_SEARCH_API_KEY`), or `searxng` (requires `SEARXNG_BASE_URL`; the instance must allow `format=json`). This only affects chat-mode tool calls, not search-mode endpoints. diff --git a/ios/AGENTS.md b/ios/AGENTS.md index 1c8aa22..ba8c68a 100644 --- a/ios/AGENTS.md +++ b/ios/AGENTS.md @@ -58,4 +58,3 @@ Instructions for work under `/Users/buzzert/src/sybil-2/ios`. - Anthropic: `claude-3-5-sonnet-latest` - xAI: `grok-3-mini` - Gemini: `gemini-3.5-flash` - - Hermes Agent: `hermes-agent` diff --git a/ios/Packages/Sybil/Sources/Sybil/SybilModels.swift b/ios/Packages/Sybil/Sources/Sybil/SybilModels.swift index c40d790..f333098 100644 --- a/ios/Packages/Sybil/Sources/Sybil/SybilModels.swift +++ b/ios/Packages/Sybil/Sources/Sybil/SybilModels.swift @@ -5,7 +5,6 @@ public enum Provider: String, Codable, CaseIterable, Hashable, Sendable { case anthropic case xai case gemini - case hermesAgent = "hermes-agent" public var displayName: String { switch self { @@ -13,7 +12,6 @@ public enum Provider: String, Codable, CaseIterable, Hashable, Sendable { case .anthropic: return "Anthropic" case .xai: return "xAI" case .gemini: return "Gemini" - case .hermesAgent: return "Hermes Agent" } } } @@ -192,9 +190,9 @@ extension ChatSummary { updatedAt = try container.decode(Date.self, forKey: .updatedAt) starred = try container.decodeIfPresent(Bool.self, forKey: .starred) ?? false starredAt = try container.decodeIfPresent(Date.self, forKey: .starredAt) - initiatedProvider = try container.decodeIfPresent(Provider.self, forKey: .initiatedProvider) + initiatedProvider = try container.decodeIfPresent(String.self, forKey: .initiatedProvider).flatMap(Provider.init(rawValue:)) initiatedModel = try container.decodeIfPresent(String.self, forKey: .initiatedModel) - lastUsedProvider = try container.decodeIfPresent(Provider.self, forKey: .lastUsedProvider) + lastUsedProvider = try container.decodeIfPresent(String.self, forKey: .lastUsedProvider).flatMap(Provider.init(rawValue:)) lastUsedModel = try container.decodeIfPresent(String.self, forKey: .lastUsedModel) } } @@ -329,9 +327,9 @@ extension WorkspaceItem { updatedAt = try container.decode(Date.self, forKey: .updatedAt) starred = try container.decodeIfPresent(Bool.self, forKey: .starred) ?? false starredAt = try container.decodeIfPresent(Date.self, forKey: .starredAt) - initiatedProvider = try container.decodeIfPresent(Provider.self, forKey: .initiatedProvider) + initiatedProvider = try container.decodeIfPresent(String.self, forKey: .initiatedProvider).flatMap(Provider.init(rawValue:)) initiatedModel = try container.decodeIfPresent(String.self, forKey: .initiatedModel) - lastUsedProvider = try container.decodeIfPresent(Provider.self, forKey: .lastUsedProvider) + lastUsedProvider = try container.decodeIfPresent(String.self, forKey: .lastUsedProvider).flatMap(Provider.init(rawValue:)) lastUsedModel = try container.decodeIfPresent(String.self, forKey: .lastUsedModel) } } @@ -522,9 +520,9 @@ extension ChatDetail { updatedAt = try container.decode(Date.self, forKey: .updatedAt) starred = try container.decodeIfPresent(Bool.self, forKey: .starred) ?? false starredAt = try container.decodeIfPresent(Date.self, forKey: .starredAt) - initiatedProvider = try container.decodeIfPresent(Provider.self, forKey: .initiatedProvider) + initiatedProvider = try container.decodeIfPresent(String.self, forKey: .initiatedProvider).flatMap(Provider.init(rawValue:)) initiatedModel = try container.decodeIfPresent(String.self, forKey: .initiatedModel) - lastUsedProvider = try container.decodeIfPresent(Provider.self, forKey: .lastUsedProvider) + lastUsedProvider = try container.decodeIfPresent(String.self, forKey: .lastUsedProvider).flatMap(Provider.init(rawValue:)) lastUsedModel = try container.decodeIfPresent(String.self, forKey: .lastUsedModel) messages = try container.decode([Message].self, forKey: .messages) } @@ -625,7 +623,8 @@ public struct CompletionRequestMessage: Codable, Sendable { public struct CompletionStreamMeta: Codable, Sendable { public var chatId: String? public var callId: String? - public var provider: Provider + // Responses may identify Sybil Agent, which is not a selectable LLM provider. + public var provider: String public var model: String public var agentAside: Bool? = nil } diff --git a/ios/Packages/Sybil/Sources/Sybil/SybilSettingsStore.swift b/ios/Packages/Sybil/Sources/Sybil/SybilSettingsStore.swift index e4e6d8a..50c2dcf 100644 --- a/ios/Packages/Sybil/Sources/Sybil/SybilSettingsStore.swift +++ b/ios/Packages/Sybil/Sources/Sybil/SybilSettingsStore.swift @@ -12,13 +12,11 @@ final class SybilSettingsStore { static let preferredAnthropicModel = "sybil.ios.preferredAnthropicModel" static let preferredXAIModel = "sybil.ios.preferredXAIModel" static let preferredGeminiModel = "sybil.ios.preferredGeminiModel" - static let preferredHermesAgentModel = "sybil.ios.preferredHermesAgentModel" static let quickQuestionPreferredProvider = "sybil.ios.quickQuestionPreferredProvider" static let quickQuestionPreferredOpenAIModel = "sybil.ios.quickQuestionPreferredOpenAIModel" static let quickQuestionPreferredAnthropicModel = "sybil.ios.quickQuestionPreferredAnthropicModel" static let quickQuestionPreferredXAIModel = "sybil.ios.quickQuestionPreferredXAIModel" static let quickQuestionPreferredGeminiModel = "sybil.ios.quickQuestionPreferredGeminiModel" - static let quickQuestionPreferredHermesAgentModel = "sybil.ios.quickQuestionPreferredHermesAgentModel" } private let defaults: UserDefaults @@ -46,8 +44,7 @@ final class SybilSettingsStore { .openai: defaults.string(forKey: Keys.preferredOpenAIModel) ?? "gpt-4.1-mini", .anthropic: defaults.string(forKey: Keys.preferredAnthropicModel) ?? "claude-3-5-sonnet-latest", .xai: defaults.string(forKey: Keys.preferredXAIModel) ?? "grok-3-mini", - .gemini: defaults.string(forKey: Keys.preferredGeminiModel) ?? "gemini-3.5-flash", - .hermesAgent: defaults.string(forKey: Keys.preferredHermesAgentModel) ?? "hermes-agent" + .gemini: defaults.string(forKey: Keys.preferredGeminiModel) ?? "gemini-3.5-flash" ] self.preferredModelByProvider = preferredModels @@ -57,8 +54,7 @@ final class SybilSettingsStore { .openai: defaults.string(forKey: Keys.quickQuestionPreferredOpenAIModel) ?? "chat-latest", .anthropic: defaults.string(forKey: Keys.quickQuestionPreferredAnthropicModel) ?? preferredModels[.anthropic] ?? "claude-3-5-sonnet-latest", .xai: defaults.string(forKey: Keys.quickQuestionPreferredXAIModel) ?? preferredModels[.xai] ?? "grok-3-mini", - .gemini: defaults.string(forKey: Keys.quickQuestionPreferredGeminiModel) ?? preferredModels[.gemini] ?? "gemini-3.5-flash", - .hermesAgent: defaults.string(forKey: Keys.quickQuestionPreferredHermesAgentModel) ?? preferredModels[.hermesAgent] ?? "hermes-agent" + .gemini: defaults.string(forKey: Keys.quickQuestionPreferredGeminiModel) ?? preferredModels[.gemini] ?? "gemini-3.5-flash" ] } @@ -77,14 +73,12 @@ final class SybilSettingsStore { defaults.set(preferredModelByProvider[.anthropic], forKey: Keys.preferredAnthropicModel) defaults.set(preferredModelByProvider[.xai], forKey: Keys.preferredXAIModel) defaults.set(preferredModelByProvider[.gemini], forKey: Keys.preferredGeminiModel) - defaults.set(preferredModelByProvider[.hermesAgent], forKey: Keys.preferredHermesAgentModel) defaults.set(quickQuestionPreferredProvider.rawValue, forKey: Keys.quickQuestionPreferredProvider) defaults.set(quickQuestionPreferredModelByProvider[.openai], forKey: Keys.quickQuestionPreferredOpenAIModel) defaults.set(quickQuestionPreferredModelByProvider[.anthropic], forKey: Keys.quickQuestionPreferredAnthropicModel) defaults.set(quickQuestionPreferredModelByProvider[.xai], forKey: Keys.quickQuestionPreferredXAIModel) defaults.set(quickQuestionPreferredModelByProvider[.gemini], forKey: Keys.quickQuestionPreferredGeminiModel) - defaults.set(quickQuestionPreferredModelByProvider[.hermesAgent], forKey: Keys.quickQuestionPreferredHermesAgentModel) } var trimmedTokenOrNil: String? { diff --git a/ios/Packages/Sybil/Sources/Sybil/SybilViewModel.swift b/ios/Packages/Sybil/Sources/Sybil/SybilViewModel.swift index 4173aa6..7f4e3fc 100644 --- a/ios/Packages/Sybil/Sources/Sybil/SybilViewModel.swift +++ b/ios/Packages/Sybil/Sources/Sybil/SybilViewModel.swift @@ -254,8 +254,7 @@ final class SybilViewModel { .openai: ["gpt-4.1-mini", "chat-latest"], .anthropic: ["claude-3-5-sonnet-latest"], .xai: ["grok-3-mini"], - .gemini: ["gemini-3.5-flash", "gemini-flash-latest"], - .hermesAgent: ["hermes-agent"] + .gemini: ["gemini-3.5-flash", "gemini-flash-latest"] ] init( @@ -283,9 +282,7 @@ final class SybilViewModel { } var providerOptions: [Provider] { - Provider.allCases.filter { candidate in - candidate != .hermesAgent || modelCatalog[candidate] != nil - } + Provider.allCases } var quickQuestionProviderModelOptions: [String] { diff --git a/ios/Packages/Sybil/Tests/SybilTests/ProviderTests.swift b/ios/Packages/Sybil/Tests/SybilTests/ProviderTests.swift new file mode 100644 index 0000000..1f313d4 --- /dev/null +++ b/ios/Packages/Sybil/Tests/SybilTests/ProviderTests.swift @@ -0,0 +1,39 @@ +import Foundation +import Testing +@testable import Sybil + +@Suite +struct ProviderTests { + @Test func selectableProvidersAndCatalogIgnoreRetiredIntegrations() throws { + #expect(Provider.allCases.map(\.rawValue) == ["openai", "anthropic", "xai", "gemini"]) + let data = Data(#"{"providers":{"openai":{"models":["test-model"],"loadedAt":null,"error":null},"retired-provider":{"models":["old-model"],"loadedAt":null,"error":null}}}"#.utf8) + let catalog = try JSONDecoder().decode(ModelCatalogResponse.self, from: data) + #expect(catalog.providers.count == 1) + #expect(catalog.providers[.openai]?.models == ["test-model"]) + } + + @Test func historicalChatWithUnsupportedProviderStillDecodes() throws { + let data = Data(#"{"id":"old-chat","createdAt":0,"updatedAt":0,"initiatedProvider":"retired-provider","initiatedModel":"old-model","lastUsedProvider":"retired-provider","lastUsedModel":"old-model"}"#.utf8) + let chat = try JSONDecoder().decode(ChatSummary.self, from: data) + #expect(chat.initiatedProvider == nil) + #expect(chat.lastUsedProvider == nil) + #expect(chat.id == "old-chat") + } + + @MainActor @Test func retiredSavedPreferencesUseSupportedDefaults() throws { + let suite = "ProviderTests.\(UUID().uuidString)" + let defaults = try #require(UserDefaults(suiteName: suite)) + defer { defaults.removePersistentDomain(forName: suite) } + defaults.set("retired-provider", forKey: "sybil.ios.preferredProvider") + defaults.set("retired-provider", forKey: "sybil.ios.quickQuestionPreferredProvider") + defaults.set("kept-custom-model", forKey: "sybil.ios.preferredOpenAIModel") + let settings = SybilSettingsStore(defaults: defaults) + #expect(settings.preferredProvider == .openai) + #expect(settings.quickQuestionPreferredProvider == .openai) + #expect(settings.preferredModelByProvider[.openai] == "kept-custom-model") + #expect(settings.preferredModelByProvider.count == 4) + settings.persist() + #expect(defaults.string(forKey: "sybil.ios.preferredProvider") == "openai") + #expect(defaults.string(forKey: "sybil.ios.quickQuestionPreferredProvider") == "openai") + } +} diff --git a/ios/Packages/Sybil/Tests/SybilTests/SybilInlineMentionTests.swift b/ios/Packages/Sybil/Tests/SybilTests/SybilInlineMentionTests.swift index 7eaebb7..8b28388 100644 --- a/ios/Packages/Sybil/Tests/SybilTests/SybilInlineMentionTests.swift +++ b/ios/Packages/Sybil/Tests/SybilTests/SybilInlineMentionTests.swift @@ -32,11 +32,14 @@ struct SybilInlineMentionTests { @Test func streamMetaAcceptsOptionalAgentAsideFlag() throws { let legacyData = Data(#"{"chatId":"chat-1","provider":"openai","model":"test-model"}"#.utf8) let legacy = try JSONDecoder().decode(CompletionStreamMeta.self, from: legacyData) + #expect(legacy.provider == "openai") #expect(legacy.agentAside == nil) - let asideData = Data(#"{"chatId":"chat-1","provider":"openai","model":"test-model","agentAside":true}"#.utf8) + let asideData = Data(#"{"chatId":"chat-1","provider":"sybil-agent","model":"sybil-agent","agentAside":true}"#.utf8) let aside = try JSONDecoder().decode(CompletionStreamMeta.self, from: asideData) #expect(aside.agentAside == true) + #expect(aside.provider == "sybil-agent") + #expect(Provider(rawValue: aside.provider) == nil) } @Test func asidePresentationUsesAssistantMetadata() { diff --git a/server/README.md b/server/README.md index 511bee9..ecf61af 100644 --- a/server/README.md +++ b/server/README.md @@ -1,7 +1,7 @@ # Sybil Server Backend API for: -- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Gemini / Hermes Agent) +- LLM multiplexer (OpenAI Responses / Anthropic / xAI Chat Completions-compatible Grok / Gemini) - Personal chat database (chats/messages + LLM call log) ## Stack @@ -18,6 +18,10 @@ npm run dev Migrations are applied automatically on server startup (`prisma migrate deploy`). +Historical provider IDs are stored as strings so retiring an integration does not make saved chats or call logs unreadable. The API validates new requests against the supported provider list and returns `null` for unsupported saved provider selections. These columns remain SQLite `TEXT`; no data rewrite is required. + +Inline Sybil Agent completions identify their response provider as `sybil-agent`. Release native clients that accept this response identity before deploying the server change; older clients that decode completion metadata with the selectable-provider enum cannot decode it. See the [streaming contract](../docs/api/streaming-chat.md). + Open docs: `http://localhost:8787/docs` API contract docs for clients: @@ -44,9 +48,6 @@ If `ADMIN_TOKEN` is not set, the server runs in open mode (dev). - `ANTHROPIC_API_KEY` - `XAI_API_KEY` - `GEMINI_API_KEY` -- `HERMES_AGENT_API_BASE_URL` (`http://127.0.0.1:8642/v1` by default; include the `/v1` suffix) -- `HERMES_AGENT_API_KEY` (enables the Hermes Agent provider; set to Hermes `API_SERVER_KEY`, or any non-empty value if that local server does not require auth) -- `HERMES_AGENT_MODEL` (optional fallback/override model id; defaults client-side to `hermes-agent`) - `EXA_API_KEY` - `BRAVE_SEARCH_API_KEY` (required when `CHAT_WEB_SEARCH_ENGINE=brave`) - `CHAT_WEB_SEARCH_ENGINE` (`exa` by default; `brave` and `searxng` are also supported for chat tool calls only) diff --git a/server/prisma/schema.prisma b/server/prisma/schema.prisma index 1e32ec8..0bbe0db 100644 --- a/server/prisma/schema.prisma +++ b/server/prisma/schema.prisma @@ -9,14 +9,6 @@ datasource db { url = env("DATABASE_URL") } -enum Provider { - openai - anthropic - xai - gemini - hermes_agent @map("hermes-agent") -} - enum MessageRole { system user @@ -54,9 +46,11 @@ model Chat { title String? titleGenerationPending Boolean @default(false) - initiatedProvider Provider? + // Historical provider IDs remain readable after an integration is retired. + // Accepted request IDs are validated by the API, not a storage enum. + initiatedProvider String? initiatedModel String? - lastUsedProvider Provider? + lastUsedProvider String? lastUsedModel String? additionalSystemPrompt String? @@ -103,7 +97,7 @@ model LlmCall { chat Chat @relation(fields: [chatId], references: [id], onDelete: Cascade) chatId String - provider Provider + provider String model String // request/response snapshots for debugging + replay diff --git a/server/scripts/ensure-prisma-client.mjs b/server/scripts/ensure-prisma-client.mjs index c79634b..e6ca7f6 100644 --- a/server/scripts/ensure-prisma-client.mjs +++ b/server/scripts/ensure-prisma-client.mjs @@ -9,6 +9,8 @@ const clientDir = join(rootDir, "node_modules", ".prisma", "client"); const clientIndex = join(clientDir, "index.js"); const prismaJs = join(rootDir, "node_modules", "prisma", "build", "index.js"); const genericEngine = join(clientDir, "libquery_engine.node"); +const schemaFile = join(rootDir, "prisma", "schema.prisma"); +const generatedSchemaFile = join(clientDir, "schema.prisma"); function parseExpectedEngineFiles() { if (!existsSync(clientIndex)) return []; @@ -39,7 +41,8 @@ function runPrismaGenerate() { let expectedFiles = parseExpectedEngineFiles(); let missingFiles = missingEngineFiles(expectedFiles); -if (!expectedFiles.length || missingFiles.length) { +const schemaChanged = !existsSync(generatedSchemaFile) || readFileSync(schemaFile, "utf8") !== readFileSync(generatedSchemaFile, "utf8"); +if (schemaChanged || !expectedFiles.length || missingFiles.length) { runPrismaGenerate(); expectedFiles = parseExpectedEngineFiles(); missingFiles = missingEngineFiles(expectedFiles); diff --git a/server/src/env.ts b/server/src/env.ts index b72899c..98849ed 100644 --- a/server/src/env.ts +++ b/server/src/env.ts @@ -11,13 +11,6 @@ const OptionalUrlSchema = z.preprocess( z.string().trim().url().optional() ); -const DEFAULT_HERMES_AGENT_API_BASE_URL = "http://127.0.0.1:8642/v1"; - -const HermesAgentApiBaseUrlSchema = z.preprocess( - (value) => (typeof value === "string" && value.trim() === "" ? undefined : value), - z.string().trim().url().default(DEFAULT_HERMES_AGENT_API_BASE_URL) -); - const ChatWebSearchEngineSchema = z.preprocess( (value) => { if (typeof value !== "string") return value; @@ -67,9 +60,6 @@ const EnvSchema = z.object({ ANTHROPIC_API_KEY: z.string().optional(), XAI_API_KEY: z.string().optional(), GEMINI_API_KEY: z.string().optional(), - HERMES_AGENT_API_BASE_URL: HermesAgentApiBaseUrlSchema, - HERMES_AGENT_API_KEY: OptionalTrimmedStringSchema, - HERMES_AGENT_MODEL: OptionalTrimmedStringSchema, SYBIL_AGENT_BASE_URL: z.string().url().default("http://sybil-agent:8788"), SYBIL_AGENT_API_KEY: OptionalTrimmedStringSchema, // Off until a deliberate server opt-in plus per-installation user consent. diff --git a/server/src/llm/model-catalog.ts b/server/src/llm/model-catalog.ts index 79e1d1f..545a6e6 100644 --- a/server/src/llm/model-catalog.ts +++ b/server/src/llm/model-catalog.ts @@ -1,7 +1,6 @@ import type { FastifyBaseLogger } from "fastify"; import { fetchProviderCatalogModels, - getProviderCatalogFallbackModels, listModelCatalogProviders, } from "./provider-adapters.js"; import type { Provider } from "./types.js"; @@ -49,9 +48,8 @@ async function refreshProviderModels(provider: Provider, logger?: FastifyBaseLog } catch (err: any) { const message = err?.message ?? String(err); const previous = modelCatalog[provider]; - const fallbackModels = getProviderCatalogFallbackModels(provider); modelCatalog[provider] = { - models: previous?.models.length ? previous.models : fallbackModels, + models: previous?.models ?? [], loadedAt: previous?.loadedAt ?? null, error: message, }; diff --git a/server/src/llm/multiplexer.ts b/server/src/llm/multiplexer.ts index 0b1cf5a..a56126a 100644 --- a/server/src/llm/multiplexer.ts +++ b/server/src/llm/multiplexer.ts @@ -2,12 +2,7 @@ import { performance } from "node:perf_hooks"; import { prisma } from "../db.js"; import { buildToolLogMessageData } from "./chat-tools.js"; import { getProviderChatAdapter } from "./provider-adapters.js"; -import { toPrismaProvider } from "./provider-ids.js"; -import type { MultiplexRequest, MultiplexResponse, Provider } from "./types.js"; - -function asProviderEnum(p: Provider) { - return toPrismaProvider(p); -} +import type { MultiplexRequest, MultiplexResponse } from "./types.js"; export async function runMultiplex(req: MultiplexRequest): Promise { const t0 = performance.now(); @@ -17,7 +12,7 @@ export async function runMultiplex(req: MultiplexRequest): Promise boolean; fetchModels(client: any): Promise; - fallbackModels?: () => string[]; sortModels?: (models: string[]) => string[]; }; @@ -48,7 +45,7 @@ type ProviderBackendSpec = { plainProtocol: ChatProtocol; toolProtocol?: ChatProtocol; managedTools?: boolean; - modelCatalog?: ModelCatalogSpec; + modelCatalog: ModelCatalogSpec; }; const chatCompletionsProtocol: ChatProtocol = { @@ -226,23 +223,6 @@ const backendSpecs: Record = { sortModels: preferGeminiModels, }, }, - "hermes-agent": { - createClient: hermesAgentClient, - plainProtocol: chatCompletionsProtocol, - managedTools: false, - modelCatalog: { - enabled: isHermesAgentConfigured, - async fetchModels(client) { - const page = await client.models.list(); - const models = modelIdsFromListResponse(page); - if (env.HERMES_AGENT_MODEL) models.push(env.HERMES_AGENT_MODEL); - return models; - }, - fallbackModels() { - return env.HERMES_AGENT_MODEL ? [env.HERMES_AGENT_MODEL] : []; - }, - }, - }, }; const providerChatAdapters: Record = Object.fromEntries( @@ -264,21 +244,11 @@ export function describeProviderChatBackend(provider: Provider, enabledTools?: s } export function listModelCatalogProviders(): Provider[] { - return (Object.entries(backendSpecs) as [Provider, ProviderBackendSpec][]) - .filter(([, spec]) => { - const catalog = spec.modelCatalog; - return catalog !== undefined && catalog.enabled?.() !== false; - }) - .map(([provider]) => provider); + return Object.keys(backendSpecs) as Provider[]; } export async function fetchProviderCatalogModels(provider: Provider) { const spec = backendSpecs[provider].modelCatalog; - if (!spec) return []; const models = uniqSorted(await spec.fetchModels(backendSpecs[provider].createClient())); return spec.sortModels ? spec.sortModels(models) : models; } - -export function getProviderCatalogFallbackModels(provider: Provider) { - return uniqSorted(backendSpecs[provider].modelCatalog?.fallbackModels?.() ?? []); -} diff --git a/server/src/llm/provider-ids.ts b/server/src/llm/provider-ids.ts index 8d141f8..68144d2 100644 --- a/server/src/llm/provider-ids.ts +++ b/server/src/llm/provider-ids.ts @@ -1,43 +1,21 @@ -import type { Provider } from "./types.js"; +import { PROVIDERS, type Provider } from "./types.js"; -type PrismaProvider = Exclude | "hermes_agent"; - -const apiToPrismaProvider = { - openai: "openai", - anthropic: "anthropic", - xai: "xai", - gemini: "gemini", - "hermes-agent": "hermes_agent", -} as const satisfies Record; - -const prismaToApiProvider = { - openai: "openai", - anthropic: "anthropic", - xai: "xai", - gemini: "gemini", - hermes_agent: "hermes-agent", - "hermes-agent": "hermes-agent", -} as const satisfies Record; - -export function toPrismaProvider(provider: Provider): PrismaProvider { - return apiToPrismaProvider[provider]; -} - -export function fromPrismaProvider(provider: unknown): Provider | null { - if (provider === null || provider === undefined) return null; - return prismaToApiProvider[provider as keyof typeof prismaToApiProvider] ?? null; +export function parseProvider(provider: unknown): Provider | null { + return typeof provider === "string" && PROVIDERS.includes(provider as Provider) ? provider as Provider : null; } export function serializeProviderFields>(value: T): T { const next: Record = { ...value }; if ("initiatedProvider" in next) { - next.initiatedProvider = fromPrismaProvider(next.initiatedProvider); + next.initiatedProvider = parseProvider(next.initiatedProvider); + if (!next.initiatedProvider && "initiatedModel" in next) next.initiatedModel = null; } if ("lastUsedProvider" in next) { - next.lastUsedProvider = fromPrismaProvider(next.lastUsedProvider); + next.lastUsedProvider = parseProvider(next.lastUsedProvider); + if (!next.lastUsedProvider && "lastUsedModel" in next) next.lastUsedModel = null; } if ("provider" in next) { - next.provider = fromPrismaProvider(next.provider); + next.provider = parseProvider(next.provider); } if (Array.isArray(next.calls)) { next.calls = next.calls.map((call: Record) => serializeProviderFields(call)); diff --git a/server/src/llm/providers.ts b/server/src/llm/providers.ts index f5e1be7..da0eae2 100644 --- a/server/src/llm/providers.ts +++ b/server/src/llm/providers.ts @@ -21,18 +21,6 @@ export function geminiClient() { }; } -export function isHermesAgentConfigured() { - return Boolean(env.HERMES_AGENT_API_KEY); -} - -export function hermesAgentClient() { - if (!env.HERMES_AGENT_API_KEY) throw new Error("HERMES_AGENT_API_KEY not set"); - return new OpenAI({ - apiKey: env.HERMES_AGENT_API_KEY, - baseURL: env.HERMES_AGENT_API_BASE_URL, - }); -} - export function anthropicClient() { if (!env.ANTHROPIC_API_KEY) throw new Error("ANTHROPIC_API_KEY not set"); return new Anthropic({ apiKey: env.ANTHROPIC_API_KEY }); diff --git a/server/src/llm/streaming.ts b/server/src/llm/streaming.ts index 299be7d..fc99cc4 100644 --- a/server/src/llm/streaming.ts +++ b/server/src/llm/streaming.ts @@ -5,7 +5,6 @@ import { type ToolExecutionEvent, } from "./chat-tools.js"; import { getProviderChatAdapter } from "./provider-adapters.js"; -import { toPrismaProvider } from "./provider-ids.js"; import type { MultiplexRequest, Provider } from "./types.js"; type StreamUsage = { @@ -36,7 +35,7 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator ? await prisma.llmCall.create({ data: { chatId, - provider: toPrismaProvider(req.provider) as any, + provider: req.provider, model: req.model, request: req as any, }, @@ -49,14 +48,14 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator prisma.chat.update({ where: { id: chatId }, data: { - lastUsedProvider: toPrismaProvider(req.provider) as any, + lastUsedProvider: req.provider, lastUsedModel: req.model, }, }), prisma.chat.updateMany({ where: { id: chatId, initiatedProvider: null }, data: { - initiatedProvider: toPrismaProvider(req.provider) as any, + initiatedProvider: req.provider, initiatedModel: req.model, }, }), diff --git a/server/src/llm/types.ts b/server/src/llm/types.ts index 5fa85a5..3daa080 100644 --- a/server/src/llm/types.ts +++ b/server/src/llm/types.ts @@ -1,4 +1,4 @@ -export const PROVIDERS = ["openai", "anthropic", "xai", "gemini", "hermes-agent"] as const; +export const PROVIDERS = ["openai", "anthropic", "xai", "gemini"] as const; export type Provider = (typeof PROVIDERS)[number]; diff --git a/server/src/message-generation.ts b/server/src/message-generation.ts index dbc29e9..69f8d59 100644 --- a/server/src/message-generation.ts +++ b/server/src/message-generation.ts @@ -1,4 +1,4 @@ -import { fromPrismaProvider } from "./llm/provider-ids.js"; +import { parseProvider } from "./llm/provider-ids.js"; function record(value: unknown): Record { return value && typeof value === "object" && !Array.isArray(value) ? value as Record : {}; @@ -18,7 +18,7 @@ export function withMessageGenerations normalizeEnabledChatTools(value)); @@ -335,7 +335,7 @@ function executeActiveAgentAsideStream(chatId: string, body: z.infer | null)?.agentAside === true); return { chatId: body.chatId, - provider: completedAgentAside ? "hermes-agent" : body.provider, + provider: completedAgentAside ? "sybil-agent" : body.provider, model: completedAgentAside ? "sybil-agent" : body.model, message: { role: "assistant", @@ -1778,7 +1778,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin await storeAgentAsideReply(body.chatId, content, body.clientRequestId); return { chatId: body.chatId, - provider: "hermes-agent", + provider: "sybil-agent", model: "sybil-agent", message: { role: "assistant", content, name: "Sybil Agent", agentAside: true }, }; diff --git a/server/tests/agent-inline.test.ts b/server/tests/agent-inline.test.ts index 01ff9f0..6588f38 100644 --- a/server/tests/agent-inline.test.ts +++ b/server/tests/agent-inline.test.ts @@ -58,7 +58,7 @@ test("mention invokes only the inline Agent, stores both sides, and replays by r }; const first = await app.inject({ method: "POST", url: "/v1/chat-completions", headers: auth, payload: body }); assert.equal(first.statusCode, 200, first.body); - assert.equal(first.json().provider, "hermes-agent"); + assert.equal(first.json().provider, "sybil-agent"); assert.equal(first.json().message.name, "Sybil Agent"); assert.equal(first.json().message.agentAside, true); assert.equal(first.json().message.content, "Synthetic Sybil reply"); @@ -66,7 +66,7 @@ test("mention invokes only the inline Agent, stores both sides, and replays by r const retry = await app.inject({ method: "POST", url: "/v1/chat-completions", headers: auth, payload: body }); assert.equal(retry.statusCode, 200, retry.body); - assert.equal(retry.json().provider, "hermes-agent"); + assert.equal(retry.json().provider, "sybil-agent"); assert.equal(retry.json().message.name, "Sybil Agent"); assert.equal(retry.json().message.agentAside, true); assert.equal(retry.json().message.content, "Synthetic Sybil reply"); @@ -224,9 +224,12 @@ test("streamed mention is idempotent and identifies the inline Agent", async () const retry = streamingApp.inject({ method: "POST", url: "/v1/chat-completions/stream", headers: auth, payload }); finish("Synthetic streamed reply"); const [firstResponse, retryResponse] = await Promise.all([first, retry]); - for (const response of [firstResponse, retryResponse]) { + const completedReplay = await streamingApp.inject({ method: "POST", url: "/v1/chat-completions/stream", headers: auth, payload }); + for (const response of [firstResponse, retryResponse, completedReplay]) { assert.equal(response.statusCode, 200, response.body); assert.match(response.body, /"agentAside":true/); + assert.match(response.body, /"provider":"sybil-agent"/); + assert.match(response.body, /"model":"sybil-agent"/); assert.match(response.body, /Synthetic streamed reply/); } assert.equal(calls, 1); diff --git a/server/tests/chat-tools-streaming.test.ts b/server/tests/chat-tools-streaming.test.ts index cf85ffb..7460d3d 100644 --- a/server/tests/chat-tools-streaming.test.ts +++ b/server/tests/chat-tools-streaming.test.ts @@ -125,13 +125,13 @@ test("plain Chat Completions stream does not send Sybil-managed tools", async () const events = await collectEvents( streamWithChatCompletionsApi({ client: client as any, - model: "hermes-agent", + model: "grok-test", messages: [{ role: "user", content: "Say hi" }], enabledTools: [], }) ); - assert.equal(requestBody.model, "hermes-agent"); + assert.equal(requestBody.model, "grok-test"); assert.equal(requestBody.stream, true); assert.equal("tools" in requestBody, false); assert.deepEqual( diff --git a/server/tests/provider-adapters.test.ts b/server/tests/provider-adapters.test.ts index 94accfd..56d3327 100644 --- a/server/tests/provider-adapters.test.ts +++ b/server/tests/provider-adapters.test.ts @@ -1,7 +1,7 @@ import assert from "node:assert/strict"; import test from "node:test"; import { env } from "../src/env.js"; -import { describeProviderChatBackend, fetchProviderCatalogModels } from "../src/llm/provider-adapters.js"; +import { describeProviderChatBackend, fetchProviderCatalogModels, listModelCatalogProviders } from "../src/llm/provider-adapters.js"; for (const { name, listedModels, expectedModels } of [ { @@ -47,6 +47,7 @@ for (const { name, listedModels, expectedModels } of [ } test("provider backend registry selects chat protocol and managed-tool mode", () => { + assert.deepEqual(listModelCatalogProviders(), ["openai", "anthropic", "xai", "gemini"]); assert.deepEqual(describeProviderChatBackend("openai", []), { provider: "openai", protocol: "chat-completions", @@ -77,10 +78,4 @@ test("provider backend registry selects chat protocol and managed-tool mode", () managedTools: true, enabledTools: ["web_search"], }); - assert.deepEqual(describeProviderChatBackend("hermes-agent", ["web_search"]), { - provider: "hermes-agent", - protocol: "chat-completions", - managedTools: false, - enabledTools: [], - }); }); diff --git a/server/tests/provider-ids.test.ts b/server/tests/provider-ids.test.ts index 307587e..02ee797 100644 --- a/server/tests/provider-ids.test.ts +++ b/server/tests/provider-ids.test.ts @@ -1,14 +1,26 @@ import assert from "node:assert/strict"; import test from "node:test"; -import { fromPrismaProvider, serializeProviderFields, toPrismaProvider } from "../src/llm/provider-ids.js"; +import { parseProvider, serializeProviderFields } from "../src/llm/provider-ids.js"; +import { PROVIDERS } from "../src/llm/types.js"; -test("Hermes Agent provider id maps between API and Prisma enum forms", () => { - assert.equal(toPrismaProvider("hermes-agent"), "hermes_agent"); - assert.equal(fromPrismaProvider("hermes_agent"), "hermes-agent"); - assert.equal(toPrismaProvider("gemini"), "gemini"); - assert.equal(fromPrismaProvider("gemini"), "gemini"); - assert.deepEqual(serializeProviderFields({ initiatedProvider: "hermes_agent", lastUsedProvider: "gemini" }), { - initiatedProvider: "hermes-agent", - lastUsedProvider: "gemini", +test("only supported provider IDs can become active selections", () => { + for (const provider of PROVIDERS) assert.equal(parseProvider(provider), provider); + for (const provider of [null, undefined, "retired-provider", "sybil-agent", "toString", {}]) { + assert.equal(parseProvider(provider), null); + } +}); + +test("retired saved selections are cleared without changing historical call records", () => { + const record = { + initiatedProvider: "retired-provider", initiatedModel: "old-model", + lastUsedProvider: "gemini", lastUsedModel: "current-model", + calls: [{ provider: "retired-provider", model: "old-model", request: { provider: "retired-provider" } }], + }; + assert.deepEqual(serializeProviderFields(record), { + initiatedProvider: null, initiatedModel: null, + lastUsedProvider: "gemini", lastUsedModel: "current-model", + calls: [{ provider: null, model: "old-model", request: { provider: "retired-provider" } }], }); + assert.equal(record.initiatedProvider, "retired-provider"); + assert.equal(record.calls[0]!.provider, "retired-provider"); }); diff --git a/server/tests/provider-retirement.test.ts b/server/tests/provider-retirement.test.ts new file mode 100644 index 0000000..d99724d --- /dev/null +++ b/server/tests/provider-retirement.test.ts @@ -0,0 +1,80 @@ +import assert from "node:assert/strict"; +import { execFileSync } from "node:child_process"; +import { mkdtempSync, rmSync } from "node:fs"; +import { tmpdir } from "node:os"; +import { dirname, join, resolve } from "node:path"; +import test from "node:test"; +import { fileURLToPath } from "node:url"; +import Fastify from "fastify"; +import sensible from "@fastify/sensible"; +import { PROVIDERS } from "../src/llm/types.js"; + +const serverRoot = resolve(dirname(fileURLToPath(import.meta.url)), ".."); +const databaseDir = mkdtempSync(join(tmpdir(), "sybil-provider-retirement-")); +process.env.DATABASE_URL = `file:${join(databaseDir, "test.db")}`; +process.env.ADMIN_TOKEN = "provider-retirement-test-token"; +execFileSync(process.execPath, [join(serverRoot, "node_modules/prisma/build/index.js"), "migrate", "deploy"], { + cwd: serverRoot, env: { ...process.env, PRISMA_HIDE_UPDATE_MESSAGE: "1" }, stdio: "pipe", +}); +const [{ registerRoutes }, { prisma }] = await Promise.all([import("../src/routes.js"), import("../src/db.js")]); +const app = Fastify({ logger: false }); +await app.register(sensible); +await registerRoutes(app, { agentInlineInvoker: async () => { throw new Error("Unsupported requests must not invoke the Agent"); } }); +await app.ready(); +const auth = { authorization: "Bearer provider-retirement-test-token" }; +test.after(async () => { await app.close(); await prisma.$disconnect(); rmSync(databaseDir, { recursive: true, force: true }); }); + +test("catalog and request validation expose only the remaining LLM providers", async () => { + const catalog = await app.inject({ method: "GET", url: "/v1/models", headers: auth }); + assert.equal(catalog.statusCode, 200); + assert.deepEqual(Object.keys(catalog.json().providers), [...PROVIDERS]); + const before = await prisma.chat.count(); + for (const provider of ["retired-provider", "sybil-agent"]) { + for (const url of ["/v1/chats", "/v1/chat-completions", "/v1/chat-completions/stream", "/v1/quick-questions/stream"]) { + const response = await app.inject({ method: "POST", url, headers: auth, payload: { + provider, model: "test-model", messages: [{ role: "user", content: "@sybil test" }], question: "test", + } }); + assert.equal(response.statusCode, 400, `${url}: ${response.body}`); + } + } + assert.equal(await prisma.chat.count(), before); + assert.equal(await prisma.llmCall.count(), 0); + for (const provider of PROVIDERS) { + const response = await app.inject({ method: "POST", url: "/v1/chats", headers: auth, payload: { provider, model: "test-model" } }); + assert.equal(response.statusCode, 200, response.body); + assert.equal(response.json().chat.lastUsedProvider, provider); + } +}); + +test("existing text provider IDs remain readable and forkable without relabeling history", async () => { + const chat = await prisma.chat.create({ data: { + title: "Archived provider conversation", + initiatedProvider: "retired-provider", initiatedModel: "archived-model", + lastUsedProvider: "retired-provider", lastUsedModel: "archived-model", + messages: { create: { role: "assistant", content: "Original saved answer", metadata: { clientRequestId: "old-request" } } }, + calls: { create: { provider: "retired-provider", model: "archived-model", request: { provider: "retired-provider", clientRequestId: "old-request" }, latencyMs: 1 } }, + }, include: { messages: true, calls: true } }); + const detail = await app.inject({ method: "GET", url: `/v1/chats/${chat.id}`, headers: auth }); + assert.equal(detail.statusCode, 200, detail.body); + const saved = detail.json().chat; + for (const key of ["initiatedProvider", "initiatedModel", "lastUsedProvider", "lastUsedModel"]) assert.equal(saved[key], null); + assert.equal(saved.messages[0].content, "Original saved answer"); + assert.equal(saved.messages[0].metadata.generation, undefined); + assert.equal(saved.calls[0].provider, null); + assert.equal(saved.calls[0].request.provider, "retired-provider"); + for (const url of ["/v1/chats", "/v1/workspace-items", "/v1/chats?limit=50"]) { + const response = await app.inject({ method: "GET", url, headers: auth }); + assert.equal(response.statusCode, 200, `${url}: ${response.body}`); + const rows = response.json().chats ?? response.json().items; + assert.equal(rows.find((row: any) => row.id === chat.id).lastUsedProvider, null); + } + const fork = await app.inject({ method: "POST", url: `/v1/chats/${chat.id}/fork`, headers: auth, payload: {} }); + assert.equal(fork.statusCode, 200, fork.body); + const forkDetail = await app.inject({ method: "GET", url: `/v1/chats/${fork.json().chat.id}`, headers: auth }); + assert.equal(forkDetail.statusCode, 200, forkDetail.body); + assert.equal(forkDetail.json().chat.lastUsedProvider, null); + assert.equal(forkDetail.json().chat.messages[0].content, "Original saved answer"); + const stored = await prisma.chat.findUniqueOrThrow({ where: { id: chat.id }, include: { calls: true } }); + assert.equal(stored.lastUsedProvider, "retired-provider"); + assert.equal(stored.calls[0]!.provider, "retired-provider"); +}); diff --git a/tui/README.md b/tui/README.md index d4d8bb2..f10d4fc 100644 --- a/tui/README.md +++ b/tui/README.md @@ -23,7 +23,7 @@ Configuration is environment-only (no in-app settings). - `SYBIL_TUI_API_BASE_URL`: API base URL. Default: `http://127.0.0.1:8787` - `SYBIL_TUI_ADMIN_TOKEN`: optional bearer token for token-mode servers -- `SYBIL_TUI_DEFAULT_PROVIDER`: `openai` | `anthropic` | `xai` | `hermes-agent` (default: `openai`) +- `SYBIL_TUI_DEFAULT_PROVIDER`: `openai` | `anthropic` | `xai` | `gemini` (default: `openai`) - `SYBIL_TUI_DEFAULT_MODEL`: optional default model name - `SYBIL_TUI_SEARCH_NUM_RESULTS`: results per search run (default: `10`) diff --git a/tui/src/config.ts b/tui/src/config.ts index f21afda..7e3d34d 100644 --- a/tui/src/config.ts +++ b/tui/src/config.ts @@ -1,6 +1,6 @@ import type { Provider } from "./types.js"; -const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini", "hermes-agent"]; +const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"]; function normalizeBaseUrl(value: string) { const trimmed = value.trim(); diff --git a/tui/src/index.ts b/tui/src/index.ts index 9f45637..e46beda 100644 --- a/tui/src/index.ts +++ b/tui/src/index.ts @@ -42,14 +42,12 @@ type ToolLogMetadata = { resultPreview?: string | null; }; -const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"]; -const PROVIDERS: Provider[] = [...BASE_PROVIDERS, "hermes-agent"]; +const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"]; const PROVIDER_FALLBACK_MODELS: Record = { openai: ["gpt-4.1-mini"], anthropic: ["claude-3-5-sonnet-latest"], xai: ["grok-3-mini"], gemini: ["gemini-3.5-flash", "gemini-flash-latest"], - "hermes-agent": ["hermes-agent"], }; const EMPTY_MODEL_CATALOG: ModelCatalogResponse["providers"] = { @@ -82,7 +80,6 @@ function getProviderLabel(provider: Provider | null | undefined) { if (provider === "anthropic") return "Anthropic"; if (provider === "xai") return "xAI"; if (provider === "gemini") return "Gemini"; - if (provider === "hermes-agent") return "Hermes Agent"; return ""; } @@ -227,10 +224,6 @@ function getModelOptions(catalog: ModelCatalogResponse["providers"], provider: P return PROVIDER_FALLBACK_MODELS[provider]; } -function getVisibleProviders(catalog: ModelCatalogResponse["providers"]) { - return PROVIDERS.filter((provider) => provider !== "hermes-agent" || catalog[provider] !== undefined); -} - function pickProviderModel(options: string[], preferred: string | null, fallback: string | null = null) { if (fallback && options.includes(fallback)) return fallback; if (preferred && options.includes(preferred)) return preferred; @@ -276,7 +269,6 @@ async function main() { anthropic: null, xai: null, gemini: null, - "hermes-agent": null, }; let model: string = config.defaultModel ?? pickProviderModel(getModelOptions(modelCatalog, provider), null); let errorMessage: string | null = null; @@ -509,7 +501,7 @@ async function main() { if (draftKind || selectedItem?.kind !== "chat") return; const detailSelection = - selectedChat?.id === selectedItem.id && selectedChat.lastUsedProvider && selectedChat.lastUsedModel?.trim() + selectedChat?.id === selectedItem.id && selectedChat.lastUsedProvider && PROVIDERS.includes(selectedChat.lastUsedProvider) && selectedChat.lastUsedModel?.trim() ? { provider: selectedChat.lastUsedProvider, model: selectedChat.lastUsedModel.trim(), @@ -518,7 +510,7 @@ async function main() { const summary = getSelectedChatSummary(); const summarySelection = - summary?.lastUsedProvider && summary.lastUsedModel?.trim() + summary?.lastUsedProvider && PROVIDERS.includes(summary.lastUsedProvider) && summary.lastUsedModel?.trim() ? { provider: summary.lastUsedProvider, model: summary.lastUsedModel.trim(), @@ -1473,10 +1465,8 @@ async function main() { } function cycleProvider() { - const visibleProviders = getVisibleProviders(modelCatalog); - const cycleProviders = visibleProviders.length ? visibleProviders : BASE_PROVIDERS; - const currentIndex = Math.max(0, cycleProviders.indexOf(provider)); - const nextProvider: Provider = cycleProviders[(currentIndex + 1) % cycleProviders.length] ?? "openai"; + const currentIndex = Math.max(0, PROVIDERS.indexOf(provider)); + const nextProvider: Provider = PROVIDERS[(currentIndex + 1) % PROVIDERS.length] ?? "openai"; provider = nextProvider; syncModelForProvider(); updateUI(); diff --git a/tui/src/types.ts b/tui/src/types.ts index b979919..23ace95 100644 --- a/tui/src/types.ts +++ b/tui/src/types.ts @@ -1,4 +1,4 @@ -export type Provider = "openai" | "anthropic" | "xai" | "gemini" | "hermes-agent"; +export type Provider = "openai" | "anthropic" | "xai" | "gemini"; export type ProviderModelInfo = { models: string[]; @@ -140,7 +140,7 @@ export type CompletionRequestMessage = { }; export type CompletionStreamHandlers = { - onMeta?: (payload: { chatId: string; callId: string; provider: Provider; model: string }) => void; + onMeta?: (payload: { chatId: string | null; callId: string | null; provider: Provider | "sybil-agent"; model: string; agentAside?: boolean }) => void; onToolCall?: (payload: ToolCallEvent) => void; onDelta?: (payload: { text: string }) => void; onDone?: (payload: { text: string; usage?: { inputTokens?: number; outputTokens?: number; totalTokens?: number } }) => void; diff --git a/web/src/App.tsx b/web/src/App.tsx index 9129545..0e97d09 100644 --- a/web/src/App.tsx +++ b/web/src/App.tsx @@ -2,7 +2,7 @@ import { readSidebarSelectionFromUrl, buildWorkspaceUrl, PROVIDER_FALLBACK_MODELS, EMPTY_MODEL_CATALOG, createClientRequestId, isRecoverableStreamDisconnect, hasNewPersistedUserMessage, - getModelOptions, getVisibleProviders, loadStoredModelPreferences, saveModelPreferences, + getModelOptions, PROVIDERS, loadStoredModelPreferences, saveModelPreferences, loadStoredQuickQuestionModelSelection, saveQuickQuestionModelSelection, pickProviderModel, buildCompletionMessages, type ProviderModelPreferences, } from "@/lib/workspace-domain"; @@ -1147,7 +1147,7 @@ export default function App() { () => getModelOptions(modelCatalog, chatSettingsProviderDraft), [chatSettingsProviderDraft, modelCatalog] ); - const providerOptions = useMemo(() => getVisibleProviders(modelCatalog), [modelCatalog]); + const providerOptions = PROVIDERS; useEffect(() => { if (model.trim()) return; diff --git a/web/src/components/settings/model-settings.tsx b/web/src/components/settings/model-settings.tsx index 446ac6a..fb76c2a 100644 --- a/web/src/components/settings/model-settings.tsx +++ b/web/src/components/settings/model-settings.tsx @@ -3,7 +3,7 @@ import { ModelCombobox } from "@/components/chat/model-combobox"; import { Button } from "@/components/ui/button"; import type { ModelCatalogResponse, Provider } from "@/lib/api"; import { getProviderLabel } from "@/lib/message-generation"; -import { getModelOptions, getVisibleProviders, pickProviderModel, type ProviderModelPreferences } from "@/lib/workspace-domain"; +import { getModelOptions, PROVIDERS, pickProviderModel, type ProviderModelPreferences } from "@/lib/workspace-domain"; export type ModelSettingsProps = { modelCatalog: ModelCatalogResponse["providers"]; @@ -19,9 +19,7 @@ export type ModelSettingsProps = { }; export function ModelSettings(props: ModelSettingsProps) { - const providers = getVisibleProviders(props.modelCatalog); - // Retain a previously selected optional provider even while its catalog is unavailable. - const quickProviders = providers.includes(props.quickProvider) ? providers : [...providers, props.quickProvider]; + const providers = PROVIDERS; return

@@ -49,7 +47,7 @@ export function ModelSettings(props: ModelSettingsProps) {
diff --git a/web/src/hooks/use-lite-workspace.ts b/web/src/hooks/use-lite-workspace.ts index 732e82e..9ba9cc5 100644 --- a/web/src/hooks/use-lite-workspace.ts +++ b/web/src/hooks/use-lite-workspace.ts @@ -9,7 +9,7 @@ import { shouldRequestChatTitle } from "@/lib/chat-forking"; import type { SidebarSelection } from "@/lib/sidebar-selection"; import { buildCompletionMessages, buildWorkspaceUrl, createClientRequestId, EMPTY_MODEL_CATALOG, - getModelOptions, getVisibleProviders, hasNewPersistedUserMessage, isRecoverableStreamDisconnect, + getModelOptions, PROVIDERS, hasNewPersistedUserMessage, isRecoverableStreamDisconnect, loadStoredModelPreferences, pickProviderModel, readSidebarSelectionFromUrl, saveModelPreferences, } from "@/lib/workspace-domain"; @@ -293,7 +293,7 @@ export function useLiteWorkspace(isAuthenticated: boolean, onAuthFailure: (messa : selection?.kind === "search" ? activeRuns.searches.includes(selection.id) : false; return { selection, draftKind, items, chat, search, provider, model, - providerOptions: getVisibleProviders(catalog), modelOptions: getModelOptions(catalog, provider), + providerOptions: PROVIDERS, modelOptions: getModelOptions(catalog, provider), isLoading, isBusy: isSending || selectedRun, isSending, error, activeRuns, selectItem, newChat: () => startDraft("chat"), newSearch: () => startDraft("search"), setProvider, setModel, send, refresh, diff --git a/web/src/lib/api.ts b/web/src/lib/api.ts index d2c7555..739bc6b 100644 --- a/web/src/lib/api.ts +++ b/web/src/lib/api.ts @@ -156,7 +156,8 @@ export type CompletionRequestMessage = { attachments?: ChatAttachment[]; }; -export type Provider = "openai" | "anthropic" | "xai" | "gemini" | "hermes-agent"; +export type Provider = "openai" | "anthropic" | "xai" | "gemini"; +export type CompletionProvider = Provider | "sybil-agent"; export type ProviderModelInfo = { models: string[]; @@ -187,7 +188,7 @@ type CompletionResponse = { }; type CompletionStreamHandlers = { - onMeta?: (payload: { chatId: string | null; callId: string | null; provider: Provider; model: string; agentAside?: boolean }) => void; + onMeta?: (payload: { chatId: string | null; callId: string | null; provider: CompletionProvider; model: string; agentAside?: boolean }) => void; onToolCall?: (payload: ToolCallEvent) => void; onDelta?: (payload: { text: string }) => void; onDone?: (payload: { text: string; usage?: { inputTokens?: number; outputTokens?: number; totalTokens?: number } }) => void; diff --git a/web/src/lib/chat-model-selection.ts b/web/src/lib/chat-model-selection.ts index f1b6814..fcf2ea1 100644 --- a/web/src/lib/chat-model-selection.ts +++ b/web/src/lib/chat-model-selection.ts @@ -1,4 +1,5 @@ import type { Provider } from "./api"; +import { PROVIDERS } from "./workspace-domain.ts"; type PersistedChatModel = { lastUsedProvider: Provider | null; @@ -11,7 +12,7 @@ export type ChatModelSelection = { }; export function getChatModelSelection(chat: PersistedChatModel | null): ChatModelSelection | null { - if (!chat?.lastUsedProvider || !chat.lastUsedModel?.trim()) return null; + if (!chat?.lastUsedProvider || !PROVIDERS.includes(chat.lastUsedProvider) || !chat.lastUsedModel?.trim()) return null; return { provider: chat.lastUsedProvider, model: chat.lastUsedModel.trim(), diff --git a/web/src/lib/message-generation.ts b/web/src/lib/message-generation.ts index e6b1f49..52cffc0 100644 --- a/web/src/lib/message-generation.ts +++ b/web/src/lib/message-generation.ts @@ -5,7 +5,6 @@ export function getProviderLabel(provider: unknown) { if (provider === "anthropic") return "Anthropic"; if (provider === "xai") return "xAI"; if (provider === "gemini") return "Gemini"; - if (provider === "hermes-agent") return "Hermes Agent"; return ""; } diff --git a/web/src/lib/workspace-domain.ts b/web/src/lib/workspace-domain.ts index 5aa7a3e..0a2e223 100644 --- a/web/src/lib/workspace-domain.ts +++ b/web/src/lib/workspace-domain.ts @@ -36,7 +36,6 @@ export const PROVIDER_FALLBACK_MODELS: Record = { anthropic: ["claude-3-5-sonnet-latest"], xai: ["grok-3-mini"], gemini: ["gemini-3.5-flash", "gemini-flash-latest"], - "hermes-agent": ["hermes-agent"], }; export const EMPTY_MODEL_CATALOG: ModelCatalogResponse["providers"] = { @@ -46,8 +45,7 @@ export const EMPTY_MODEL_CATALOG: ModelCatalogResponse["providers"] = { gemini: { models: [], loadedAt: null, error: null }, }; -export const BASE_PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"]; -export const ALL_PROVIDERS: Provider[] = [...BASE_PROVIDERS, "hermes-agent"]; +export const PROVIDERS: Provider[] = ["openai", "anthropic", "xai", "gemini"]; export const MODEL_PREFERENCES_STORAGE_KEY = "sybil:modelPreferencesByProvider"; export const QUICK_QUESTION_MODEL_SELECTION_STORAGE_KEY = "sybil:quickQuestionModelSelection"; @@ -60,7 +58,6 @@ export const EMPTY_MODEL_PREFERENCES: ProviderModelPreferences = { anthropic: null, xai: null, gemini: null, - "hermes-agent": null, }; export function createClientRequestId() { @@ -97,10 +94,6 @@ export function getModelOptions(catalog: ModelCatalogResponse["providers"], prov return PROVIDER_FALLBACK_MODELS[provider]; } -export function getVisibleProviders(catalog: ModelCatalogResponse["providers"]) { - return ALL_PROVIDERS.filter((provider) => provider !== "hermes-agent" || catalog[provider] !== undefined); -} - export function loadStoredModelPreferences() { if (typeof window === "undefined") return EMPTY_MODEL_PREFERENCES; try { @@ -113,7 +106,7 @@ export function loadStoredModelPreferences() { } export function normalizeStoredProvider(value: unknown): Provider { - return value === "anthropic" || value === "xai" || value === "gemini" || value === "openai" || value === "hermes-agent" + return value === "anthropic" || value === "xai" || value === "gemini" || value === "openai" ? value : "openai"; } @@ -126,8 +119,6 @@ export function normalizeStoredModelPreferences(value: unknown): ProviderModelPr anthropic: typeof parsed.anthropic === "string" && parsed.anthropic.trim() ? parsed.anthropic.trim() : null, xai: typeof parsed.xai === "string" && parsed.xai.trim() ? parsed.xai.trim() : null, gemini: typeof parsed.gemini === "string" && parsed.gemini.trim() ? parsed.gemini.trim() : null, - "hermes-agent": - typeof parsed["hermes-agent"] === "string" && parsed["hermes-agent"].trim() ? parsed["hermes-agent"].trim() : null, }; } diff --git a/web/tests/app-settings.browser.mjs b/web/tests/app-settings.browser.mjs index 4b5d7ba..fd7268d 100644 --- a/web/tests/app-settings.browser.mjs +++ b/web/tests/app-settings.browser.mjs @@ -28,8 +28,8 @@ async function fixture(viewport, mode = "token", options = {}) { localStorage.setItem("sybil:ui-mode", "full"); if (options.seedModels && !localStorage.getItem("model-fixture-seeded")) { localStorage.setItem("model-fixture-seeded", "true"); - localStorage.setItem("sybil:modelPreferencesByProvider", JSON.stringify({ openai: "remembered-initial", anthropic: "legacy-custom" })); - localStorage.setItem("sybil:quickQuestionModelSelection", JSON.stringify({ provider: "xai", modelPreferences: { xai: "legacy-quick", openai: "quick-original" } })); + localStorage.setItem("sybil:modelPreferencesByProvider", JSON.stringify({ openai: "remembered-initial", anthropic: "legacy-custom", "retired-provider": "old-model" })); + localStorage.setItem("sybil:quickQuestionModelSelection", JSON.stringify({ provider: "xai", modelPreferences: { xai: "legacy-quick", openai: "quick-original", "retired-provider": "old-model" } })); } window.__denyPreferenceWrites = !!options.denyWrites; const setItem = Storage.prototype.setItem; @@ -51,7 +51,7 @@ async function fixture(viewport, mode = "token", options = {}) { else if (path.endsWith("/workspace-items")) value = { items: [{ ...chat, type: "chat" }, { ...search, type: "search" }] }; else if (path.endsWith(`/chats/${chat.id}`)) value = { chat }; else if (path.endsWith(`/searches/${search.id}`)) value = { search }; - else if (path.endsWith("/models")) value = { providers: { openai: { models: ["fixture-model", "listed-next-model"], loadedAt: date, error: null } } }; + else if (path.endsWith("/models")) value = { providers: { openai: { models: ["fixture-model", "listed-next-model"], loadedAt: date, error: null }, "retired-provider": { models: ["old-model"], loadedAt: date, error: null } } }; else if (path.endsWith("/chat-tools") || path.endsWith("/agent/tools")) value = { tools: [] }; else if (path.endsWith("/active-runs")) value = { chats: [], searches: [] }; else if (path.endsWith("/agent/messages")) value = { conversationId: "1", messages: [], cursor: "0", beforeCursor: null, hasMore: false }; @@ -212,6 +212,8 @@ try { assert.equal(await settings.getByRole("combobox", { name: "Anthropic chat model", exact: true }).inputValue(), "legacy-custom"); const quickProvider = settings.getByRole("combobox", { name: "Quick Questions provider", exact: true }); const quickModel = settings.getByRole("combobox", { name: "Quick Questions model", exact: true }); + assert.deepEqual(await quickProvider.locator("option").evaluateAll(options => options.map(option => option.value)), ["openai", "anthropic", "xai", "gemini"]); + assert.equal(await settings.getByRole("combobox").count(), 6, "only four chat models and the two Quick Questions controls"); assert.equal(await quickProvider.inputValue(), "xai"); assert.equal(await quickModel.inputValue(), "legacy-quick"); // Reuse the catalog, accept custom values, commit with Tab, and cancel only the picker with Escape. @@ -248,8 +250,10 @@ try { const stored = await page.evaluate(() => ({ chats: JSON.parse(localStorage.getItem("sybil:modelPreferencesByProvider")), quick: JSON.parse(localStorage.getItem("sybil:quickQuestionModelSelection")) })); assert.equal(stored.chats.openai, "custom-chat-model"); assert.equal(stored.chats.anthropic, "legacy-custom"); + assert.deepEqual(Object.keys(stored.chats), ["openai", "anthropic", "xai", "gemini"]); assert.equal(stored.quick.provider, "openai"); assert.equal(stored.quick.modelPreferences.xai, "legacy-quick"); + assert.deepEqual(Object.keys(stored.quick.modelPreferences), ["openai", "anthropic", "xai", "gemini"]); assert.equal(await settings.locator(".app-settings-content").evaluate(el => el.scrollWidth > el.clientWidth), false); await settings.getByRole("heading", { name: "Models", exact: true }).scrollIntoViewIfNeeded(); if (artifactDir) await page.screenshot({ path: `${artifactDir}/models-${viewport.width}.png` }); diff --git a/web/tests/chat-model-selection.test.mjs b/web/tests/chat-model-selection.test.mjs index 75698c2..d575f33 100644 --- a/web/tests/chat-model-selection.test.mjs +++ b/web/tests/chat-model-selection.test.mjs @@ -18,6 +18,12 @@ test("chat model selections are normalized from persisted metadata", () => { ); }); +test("unsupported historical providers never restore an active model selection", () => { + for (const provider of ["retired-provider", "sybil-agent", null]) { + assert.equal(getChatModelSelection({ lastUsedProvider: provider, lastUsedModel: "archived-model" }), null); + } +}); + test("unrelated chat updates do not change the model synchronization key", () => { const beforeSettingsSave = getChatModelSelection({ lastUsedProvider: "openai", diff --git a/web/tests/message-generation.test.mjs b/web/tests/message-generation.test.mjs index 5afb3d2..b3614aa 100644 --- a/web/tests/message-generation.test.mjs +++ b/web/tests/message-generation.test.mjs @@ -3,7 +3,7 @@ import test from "node:test"; import { getMessageGenerationLabel } from "../src/lib/message-generation.ts"; test("reply labels use the recorded provider and model", () => { - for (const [provider, label] of [["openai", "OpenAI"], ["anthropic", "Anthropic"], ["xai", "xAI"], ["gemini", "Gemini"], ["hermes-agent", "Hermes Agent"]]) { + for (const [provider, label] of [["openai", "OpenAI"], ["anthropic", "Anthropic"], ["xai", "xAI"], ["gemini", "Gemini"]]) { assert.equal(getMessageGenerationLabel({ role: "assistant", metadata: { generation: { provider, model: "original-model" } } }), `${label} ยท original-model`); } }); diff --git a/web/tests/workspace-domain.test.mjs b/web/tests/workspace-domain.test.mjs index f1163ed..3e342ca 100644 --- a/web/tests/workspace-domain.test.mjs +++ b/web/tests/workspace-domain.test.mjs @@ -1,7 +1,7 @@ import assert from "node:assert/strict"; import test from "node:test"; import { - buildCompletionMessages, buildWorkspaceUrl, getModelOptions, getVisibleProviders, + buildCompletionMessages, buildWorkspaceUrl, getModelOptions, PROVIDERS, normalizeStoredProvider, hasNewPersistedUserMessage, loadStoredModelPreferences, normalizeStoredModelPreferences, pickProviderModel, readSidebarSelectionFromUrl, saveModelPreferences, loadStoredQuickQuestionModelSelection, saveQuickQuestionModelSelection, @@ -38,12 +38,13 @@ test("reconciliation recognizes only a new matching persisted user turn", () => }); test("model policy preserves custom selections and uses advertised provider models", () => { - const catalog = { openai: { models: ["server-model"] }, "hermes-agent": { models: ["hermes"] } }; + const catalog = { openai: { models: ["server-model"] } }; assert.deepEqual(getModelOptions(catalog, "openai"), ["server-model"]); assert.equal(pickProviderModel(["server-model"], " custom-model "), "custom-model"); assert.equal(pickProviderModel(["server-model"], null), "server-model"); - assert.ok(getVisibleProviders(catalog).includes("hermes-agent")); - assert.ok(!getVisibleProviders({}).includes("hermes-agent")); + assert.deepEqual(PROVIDERS, ["openai", "anthropic", "xai", "gemini"]); + assert.equal(normalizeStoredProvider("retired-provider"), "openai"); + assert.deepEqual(Object.keys(normalizeStoredModelPreferences({ "retired-provider": "old-model" })), PROVIDERS); assert.equal(normalizeStoredModelPreferences({ openai: " x ", xai: 123 }).openai, "x"); assert.equal(normalizeStoredModelPreferences({ xai: 123 }).xai, null); });