refactor(provider): use LiteLLM as unified LLM requester backend (#2150)

* refactor(provider): use LiteLLM as unified LLM requester backend

  - Replace 23+ individual requester implementations with unified litellmchat.py
  - Add litellm_provider field to 27 YAML manifests for provider routing
  - Delete redundant requester subclasses
  - Add unit tests for LiteLLMRequester (29 tests)
  - Fix num_retries parameter name (was max_retries)
  - Fix exception handling order for subclass exceptions

  LiteLLM provides unified API for 100+ providers, eliminating need for
  provider-specific requesters.

* fix: ruff format provider.py

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* refactor(provider): simplify LiteLLM requester usage handling

  - Remove unused Anthropic-specific tool schema generation
  - Share completion argument construction between normal and streaming calls
  - Use LiteLLM/OpenAI native usage fields for monitoring
  - Collect stream token usage from LiteLLM stream_options
  - Update LiteLLM requester tests for unified usage fields

* restore: restore deleted provider requester files

Restore individual provider requester implementations that were
removed in de61b5d3. These files coexist with the unified
litellmchat.py backend.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat: update requesters and improve provider selection UI

- Added `litellm_provider` field to various requesters' YAML configurations.
- Removed obsolete Python requester files for OpenRouter, PPIO, QHAIGC, ShengSuanYun, SiliconFlow, Space, TokenPony, VolcArk, and Xai.
- Introduced new requesters for Tencent and Together AI with corresponding YAML configurations and SVG icons.
- Enhanced the ProviderForm component to include a searchable dropdown for selecting providers, improving user experience.
- Updated localization files to include search provider text for both English and Chinese.

* fix(provider): align litellm rebase with master

* fix(provider): capture streaming token usage; add token observability

The LiteLLM streaming requester only captured usage when a chunk had an
empty `choices` list. Many OpenAI-compatible gateways (e.g. new-api) and
providers send the final usage payload in a chunk that still carries an
empty-delta choice, so streamed calls always recorded 0 tokens in the
monitoring logs/dashboard (non-streaming worked).

- Capture stream usage whenever a chunk carries it, regardless of choices
- Add robust _normalize_usage (dict/obj shapes, derive missing total_tokens)
- Register litellm in bootutils/deps.py (was in pyproject only)
- Add MonitoringService.get_token_statistics + /monitoring/token-statistics
  endpoint: summary, per-model breakdown, token timeseries, and a
  zero-token-success data-quality signal
- Add TokenMonitoring dashboard tab (summary tiles, stacked token chart,
  per-model table) + i18n (en/zh)
- Regression tests for stream usage capture and usage normalization

Verified end-to-end against a real OpenAI-compatible endpoint with
gpt-5.5 and claude-opus-4-8: tokens now recorded non-zero for both
streaming and non-streaming paths.

* refactor(provider): simplify litellm capabilities

* style: simplify wrapped expressions

* feat(models): persist context metadata

* fix(provider): handle dict embeddings and openai-compatible rerank in LiteLLMRequester

- invoke_embedding: support both object- and dict-shaped response.data
  entries (OpenAI-compatible gateways like new-api return dicts)
- invoke_rerank: litellm.arerank rejects the 'openai' provider, so for
  openai-compatible (or unspecified) providers call the standard
  Jina/Cohere-style POST /v1/rerank endpoint directly over HTTP
- accept both 'relevance_score' and 'score' fields in rerank results
- add unit tests for the openai-compatible HTTP rerank path

* feat(provider): enforce requester support_type when adding models

- frontend: AddModelPopover only shows model-type tabs (llm/embedding/
  rerank) that the provider's requester declares in its manifest
  support_type; ModelsDialog fetches requester manifests and maps
  requester -> support_type, passed down through ProviderCard
- backend: add _validate_provider_supports guard in create_llm_model /
  create_embedding_model / create_rerank_model so a model cannot be
  attached to a provider whose requester does not support that type,
  even if the frontend restriction is bypassed (manifests without
  support_type are allowed for backward compatibility)
- manifests: correct support_type for providers that do not offer all
  three model types:
  - llm only: anthropic, deepseek, groq, moonshot, openrouter, xai
  - llm + text-embedding: openai, gemini, mistral
  - add rerank to new-api (verified working via /v1/rerank)
  - set llm + text-embedding + rerank for aggregator/unknown gateways

* feat(provider): add searchable alias to requester manifests

- add a free-text 'alias' field to every requester manifest spec,
  containing the vendor's English/Chinese names, pinyin, common
  nicknames and flagship model-series names (e.g. moonshot -> kimi,
  月之暗面; zhipu -> glm, 智谱清言)
- frontend: ProviderForm requester search now also matches against
  alias (substring/contains), so searching 'kimi' surfaces Moonshot,
  '硅基' surfaces SiliconFlow, etc.
- also fix support_type: openrouter (relay) supports embedding+rerank;
  LangBot Space gains rerank (coming soon)

* fix(provider): make support_type guard defensive against incomplete model_mgr

- _validate_provider_supports now uses getattr to gracefully skip when
  model_mgr / provider_dict / manifest lookup is unavailable, instead of
  raising AttributeError (fixes unit tests that mock ap.model_mgr as a
  bare SimpleNamespace)
- add TestValidateProviderSupports covering: allow supported type,
  reject unsupported type, allow when support_type missing, allow when
  provider unknown, degrade safely when model_mgr is incomplete

* fix(persistence): guard 0004 migration against missing llm_models table

The 0004_add_llm_model_context_length migration called
inspector.get_columns('llm_models') unconditionally, raising
NoSuchTableError when the table does not exist (e.g. migrating a
fresh/empty DB, as exercised by the integration tests where
create_all() registers no tables because the ORM models are not
imported). Every other migration guards with a table-existence check
first; add the same guard here for both upgrade and downgrade.

Also restore the test head assertion to 0004 (it had been lowered to
0003 to mask this failure).

* Merge branch 'master' into feat/litellm

Resolve conflicts:
- uv.lock: regenerated via 'uv lock' to reconcile litellm/fastuuid
  (ours) with openai bump (master).
- Alembic migrations: master added 0004_add_mcp_readme while this
  branch added 0004_add_llm_model_context_length, both as children of
  0003 (would create multiple heads). Re-chain the litellm migration as
  0005_add_llm_model_context_length with down_revision=0004_add_mcp_readme
  for a single linear head. Update test head assertion accordingly.

* fix(persistence): shorten migration revision id to fit varchar(32)

PostgreSQL stores alembic_version.version_num as varchar(32).
'0005_add_llm_model_context_length' (33 chars) overflowed it, raising
StringDataRightTruncationError in the PG migration tests. Rename the
revision (and file) to '0005_add_llm_context_length' (27 chars) and
update the head assertions in both SQLite and PostgreSQL migration
tests.

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: fdc310 <2213070223@qq.com>
Co-authored-by: RockChinQ <rockchinq@gmail.com>

web/src/app/home/components/models-dialog/ModelsDialog.tsx

@@ -64,6 +64,17 @@ function convertExtraArgsToObject(
   return obj;
 }
 
+function parseContextLength(
+  value: number | null | undefined,
+  invalidMessage: string,
+): number | null {
+  if (value === undefined || value === null) return null;
+  if (!Number.isInteger(value) || value <= 0) {
+    throw new Error(invalidMessage);
+  }
+  return value;
+}
+
 export default function ModelsDialog({
   open,
   onOpenChange,
@@ -91,6 +102,12 @@ export default function ModelsDialog({
     null,
   );
 
+  // Map of requester name -> support_type[] (from requester manifests),
+  // used to restrict which model-type tabs are shown when adding models.
+  const [requesterSupportTypes, setRequesterSupportTypes] = useState<
+    Record<string, string[]>
+  >({});
+
   // Popover states
   const [addModelPopoverOpen, setAddModelPopoverOpen] = useState<string | null>(
     null,
@@ -122,6 +139,7 @@ export default function ModelsDialog({
     if (open) {
       loadUserInfo();
       loadProviders();
+      loadRequesterSupportTypes();
     }
   }, [open]);
 
@@ -161,6 +179,19 @@ export default function ModelsDialog({
     }
   }
 
+  async function loadRequesterSupportTypes() {
+    try {
+      const resp = await httpClient.getProviderRequesters();
+      const map: Record<string, string[]> = {};
+      for (const r of resp.requesters) {
+        map[r.name] = r.spec?.support_type ?? [];
+      }
+      setRequesterSupportTypes(map);
+    } catch (err) {
+      console.error('Failed to load requester support types', err);
+    }
+  }
+
   async function loadProviderModels(providerUuid: string, silent = false) {
     if (loadingProviders.has(providerUuid)) return;
 
@@ -254,6 +285,7 @@ export default function ModelsDialog({
     name: string,
     abilities: string[],
     extraArgs: ExtraArg[],
+    contextLength?: number | null,
   ) {
     if (!name.trim()) {
       toast.error(t('models.modelNameRequired'));
@@ -268,6 +300,10 @@ export default function ModelsDialog({
           name,
           provider_uuid: providerUuid,
           abilities,
+          context_length: parseContextLength(
+            contextLength,
+            t('models.contextLengthInvalid'),
+          ),
           extra_args: extraArgsObj,
         } as never);
       } else if (modelType === 'embedding') {
@@ -325,6 +361,7 @@ export default function ModelsDialog({
             name: item.model.name,
             provider_uuid: providerUuid,
             abilities: item.abilities,
+            context_length: item.model.context_length ?? null,
             extra_args: {},
           } as never);
         } else if (effectiveType === 'embedding') {
@@ -361,6 +398,7 @@ export default function ModelsDialog({
     name: string,
     abilities: string[],
     extraArgs: ExtraArg[],
+    contextLength?: number | null,
   ) {
     if (!name.trim()) {
       toast.error(t('models.modelNameRequired'));
@@ -375,6 +413,10 @@ export default function ModelsDialog({
           name,
           provider_uuid: providerUuid,
           abilities,
+          context_length: parseContextLength(
+            contextLength,
+            t('models.contextLengthInvalid'),
+          ),
           extra_args: extraArgsObj,
         } as never);
       } else if (modelType === 'embedding') {
@@ -495,6 +537,7 @@ export default function ModelsDialog({
         key={provider.uuid}
         provider={provider}
         isLangBotModels={isLangBotModels}
+        supportTypes={requesterSupportTypes[provider.requester]}
         isExpanded={expandedProviders.has(provider.uuid)}
         isLoading={loadingProviders.has(provider.uuid)}
         models={providerModels[provider.uuid]}
@@ -509,8 +552,15 @@ export default function ModelsDialog({
         onSpaceLogin={handleSpaceLogin}
         onOpenAddModel={() => setAddModelPopoverOpen(provider.uuid)}
         onCloseAddModel={() => setAddModelPopoverOpen(null)}
-        onAddModel={(modelType, name, abilities, extraArgs) =>
-          handleAddModel(provider.uuid, modelType, name, abilities, extraArgs)
+        onAddModel={(modelType, name, abilities, extraArgs, contextLength) =>
+          handleAddModel(
+            provider.uuid,
+            modelType,
+            name,
+            abilities,
+            extraArgs,
+            contextLength,
+          )
         }
         onScanModels={(modelType) => handleScanModels(provider.uuid, modelType)}
         onAddScannedModels={(modelType, models) =>
@@ -518,7 +568,14 @@ export default function ModelsDialog({
         }
         onOpenEditModel={(modelId) => setEditModelPopoverOpen(modelId)}
         onCloseEditModel={() => setEditModelPopoverOpen(null)}
-        onUpdateModel={(modelId, modelType, name, abilities, extraArgs) =>
+        onUpdateModel={(
+          modelId,
+          modelType,
+          name,
+          abilities,
+          extraArgs,
+          contextLength,
+        ) =>
           handleUpdateModel(
             provider.uuid,
             modelId,
@@ -526,6 +583,7 @@ export default function ModelsDialog({
             name,
             abilities,
             extraArgs,
+            contextLength,
           )
         }
         onOpenDeleteConfirm={(modelId) => setDeleteConfirmOpen(modelId)}