920920592e* polish: update provider dropdown and rename cloud
* fix: tighten custom provider fallback handling
* fix: external provider fallback typing
* studio: wire the chat Search button to OpenAI's built-in web_search tool
When the active model is an OpenAI external provider and the user
clicks the existing Search pill in the composer, the chat-completion
request now carries the unified enable_tools shorthand:
enable_tools: true
enabled_tools: ["web_search"]
The backend's stream_chat_completion threads enabled_tools through
to _stream_openai_responses, which translates it into the Responses
API tool schema:
body["tools"] = [{"type": "web_search"}]
per the OpenAI Responses tool spec
(https://developers.openai.com/api/docs/guides/tools). OpenAI then
runs the search server-side before the model replies; the search-
informed answer streams back through the existing
response.output_text.delta path. web_search_call lifecycle events
are silently ignored for now — sources / status indicators are
follow-up scope.
Frontend:
- provider-capabilities.ts: new providerSupportsBuiltinWebSearch()
helper. Returns true only for `openai` today; Anthropic
(web_search_20250305), Gemini grounded-search, and OpenRouter
variants can be added later with matching backend translation.
- chat-page.tsx: both model-switch paths (the onChange handler and
the inferenceParams.checkpoint useEffect) set supportsTools to
match the new helper, and force toolsEnabled=false on every
external switch so the Search toggle is opt-in by default.
- chat-adapter.ts: external branch adds enable_tools +
enabled_tools=["web_search"] to the request body when the
toggle is on AND the active provider supports built-in
web-search. Local-model branch is unchanged — it continues to
route the same shorthand through our local tool runtime.
Backend:
- routes/inference.py: forwards payload.enabled_tools to
stream_chat_completion at the proxy site (line 1599).
- external_provider.py: stream_chat_completion gains an
enabled_tools parameter; _stream_openai_responses appends
{"type": "web_search"} to body["tools"] when the list contains
"web_search". Other tools (file_search, code_interpreter,
image_generation, computer_use_preview) are easy follow-ups in
the same block.
Reuses the existing pydantic ChatCompletionRequest.enabled_tools
field, so no schema migrations.
* studio/backend: surface OpenAI server-side web_search in the chat UI
When the user has the chat Search button toggled on and OpenAI's
/v1/responses invokes the built-in web_search tool, _stream_openai_responses
now translates the tool's lifecycle events and citation annotations
into the same _toolEvent shape that local-tool calls use. The result:
the chat UI shows a web_search tool-call card mid-stream, then lists
the cited sources at the end of the message — identical to how local
web_search renders.
SSE event translation:
- response.output_item.added with item.type=web_search_call ->
emit _toolEvent tool_start. Carries item.action.query as args
when OpenAI ships it on the added event.
- response.output_item.done with item.type=web_search_call ->
backfill the query if it only arrives on the done variant. The
existing reasoning branch on the same event is preserved as an
if/elif under a shared isinstance guard.
- response.output_text.annotation.added with type=url_citation ->
collect into the most-recent web_search_call.citations list.
- response.output_text.delta with inline annotations[] (older
API variant) -> same collection path, so both wire shapes work.
- response.completed -> emit _toolEvent tool_end per call with
citations formatted as
Title: <title>\nURL: <url>\nSnippet: <snippet>
blocks joined by `\n---\n`. The frontend's
parseSourcesFromResult already lifts this format into source
content parts at end-of-stream.
- response.incomplete -> close out web_search cards with whatever
citations had landed, so a truncated response does not leave a
perpetually "running" tool card in the UI.
Both reasoning and web_search work simultaneously on the same turn —
the body sends `reasoning: {effort, summary}` and `tools: [{type:
"web_search"}]` independently, and the SSE handler tracks them
through separate channels.
Diagnostic: finally-block logger now reports per stream
web_search_requested - whether the client asked for it
web_search_invocations - how many calls OpenAI actually made
citations - total URLs cited
queries - the search queries the model issued
reasoning_emitted - whether <think> content was streamed
so reports of "I clicked Search and nothing happened" can be triaged
from the backend log without browser devtools.
* studio/backend: fix empty query + per-card '(no sources cited)' on OpenAI web_search
Two display bugs on the OpenAI Responses web_search → chat-UI bridge:
1. Tool cards showed "Searching for ''" — query missing.
OpenAI's response.output_item.added for web_search_call does not
reliably populate action.query across API versions; the canonical
place is output_item.done. The previous code emitted tool_start
at added with empty args and tried to backfill at done, but the
frontend's _toolEvent: tool_start is a one-shot push (no update
mechanism), so the args stayed empty.
Fix: defer both tool_start *and* a placeholder tool_end emission
to output_item.done, where action.query is guaranteed populated.
added now just initialises tracking. Frontend then renders one
card per call with the right "Searching for: <query>" label.
2. Every card showed "(no sources cited)".
The previous code tried to attribute url_citation annotations
to individual web_search_call invocations, but OpenAI's
annotations carry no link back to a specific search call —
they're just URLs the model cited from the aggregated search
pool. With N invocations and M annotations, the previous logic
bucketed all M into the last call and stamped "(no sources
cited)" on the rest.
Fix: collect citations into a single shared all_url_citations
list, dedup by URL. At response.completed (and
response.incomplete) overwrite the *last* web_search_call's
tool_end result with the aggregated Title:/URL:/Snippet:
blocks. The frontend's parseSourcesFromResult already flatMaps
every web_search result, so one non-empty result is enough to
surface the full source-pill set at the message tail. Other
tool cards get an empty result string (no '(no sources)' text).
Diagnostic log unchanged in shape; total_citations now reads
len(all_url_citations) directly.
* studio/chat: split Code and Search pill gates so external models cannot enable Code
The previous wire-up set supportsTools=true for OpenAI external
models to light up the Search pill, but supportsTools also gates the
Code pill, so Code became clickable for OpenAI even though external
providers have no local code execution.
Separate the two gates so each pill reflects what's actually
available:
- chat-runtime-store: new `supportsBuiltinWebSearch: boolean` flag.
Distinct from supportsTools — that one still means "runtime has a
local tool sandbox" (Code, python, our DuckDuckGo web_search).
This one means "the active external provider exposes a server-side
web_search tool we can opt into" (OpenAI's /v1/responses today).
- chat-page model-switch (both code paths): for external models,
supportsTools is now forced to false (no local Code path) and
supportsBuiltinWebSearch follows providerSupportsBuiltinWebSearch.
Local-model paths are unaffected — they only set supportsTools.
- shared-composer: Search pill gates on
`searchDisabled = !modelLoaded || !(supportsTools ||
supportsBuiltinWebSearch)`. Code pill gates on
`codeDisabled = !modelLoaded || !supportsTools` — strictly the
local runtime, so external models keep Code greyed out.
A `toolsDisabled = codeDisabled` alias is left in place for any
later-touched call site that may still reference the old name.
No backend changes — chat-adapter already calls
providerSupportsBuiltinWebSearch directly, independent of the store
flags, so the request shape and the backend translation are
unchanged.
* studio/chat: default external reasoning effort to medium, not the carry-over
When switching to an external model with reasoning support, the effort
dropdown was inheriting whatever value the user had set on a prior
model — frequently "xhigh" left over from a previous Opus/gpt-5
session. That meant every fresh OpenAI/Anthropic selection started at
Extra High, burning tokens unintentionally.
Both model-switch sites in chat-page (the useEffect on
inferenceParams.checkpoint and the onChange callback) now pick
"medium" whenever the new model's level list contains it, instead of
the clamped carry-over. The clamp still fires as a fallback for the
narrow case where a model doesn't expose medium (e.g. gpt-5.3-chat-
latest which only has medium anyway — no change there). Users can
still pick another level explicitly via the Think dropdown.
* studio/chat: also light the Search pill in the welcome-screen composer
There are two composers in the chat feature. shared-composer.tsx
renders inside an active thread, and assistant-ui/thread.tsx has its
own WebSearchToggle / CodeToolsToggle that ship the welcome-screen
"Send a message…" composer (visible before the first user message).
The previous fix split supportsTools and supportsBuiltinWebSearch in
shared-composer but never touched the welcome-screen toggles in
thread.tsx — they both still gated on supportsTools alone, so the
Search pill stayed greyed on the welcome screen even for OpenAI
external models that legitimately support web_search server-side.
Mirror the shared-composer rule in WebSearchToggle:
disabled = !modelLoaded || !(supportsTools || supportsBuiltinWebSearch)
CodeToolsToggle is left as-is — its current
`disabled = !(modelLoaded && supportsTools)` is correct: external
models have no local code-execution sandbox, so Code stays greyed
when supportsTools=false (which is what chat-page now writes for
external selections).
* studio/backend: wire Anthropic server-side web_search end-to-end
Mirrors the OpenAI web_search integration for Anthropic's
web_search_20250305 tool. When the user toggles Search on with an
Anthropic model selected, the request now carries the documented
tool entry:
tools: [{type: "web_search_20250305", name: "web_search",
max_uses: 5}]
on /v1/messages, and the SSE translation surfaces tool cards +
source pills in the chat UI exactly the same way as OpenAI.
stream_chat_completion now forwards enabled_tools into the
Anthropic branch (was only doing this for the OpenAI Responses
branch). _stream_anthropic gains an enabled_tools parameter and
the web_search request-body block plus three additional event
handlers:
- content_block_start with type=server_tool_use, name=web_search:
start tracking a new call. id becomes the tool_call_id.
- content_block_delta with type=input_json_delta inside a
server_tool_use block: buffer the partial_json so we can read
out the search query when the block closes.
- content_block_start with type=web_search_tool_result: capture
the per-call result list (urls + titles) that Anthropic ships
inline.
- content_block_stop: closes whichever block we're inside —
* server_tool_use -> emit _toolEvent: tool_start with the
parsed query as args.
* web_search_tool_result -> emit _toolEvent: tool_end with
Title:/URL: blocks the frontend's parseSourcesFromResult
lifts into source pills.
* thinking block -> existing </think> close.
Unlike OpenAI we get per-call results directly, so no aggregated-
last-call fallback is needed — each tool card carries its own
citations.
Diagnostic log on stream completion now reports
web_search_requested / invocations / total_results / queries,
matching the OpenAI shape.
Frontend providerSupportsBuiltinWebSearch returns true for
'anthropic' as well, so the Search pill lights up on Claude
models the same way it does on OpenAI. The existing chat-adapter
external branch already sends enabled_tools=['web_search'] based
on this helper — no adapter changes needed.
* studio: wire OpenRouter built-in web search via :online model suffix
OpenRouter exposes a universal "add web search to any model" shortcut:
append `:online` to the model id and the gateway runs the search
server-side, streaming citations back as annotations on text deltas.
Documented at https://openrouter.ai/docs/features/web-search
Hook the existing Search toggle into that path:
Backend (external_provider.py, default OAI-compat branch):
- When provider_type == 'openrouter' and enabled_tools contains
'web_search', rewrite body['model']:
openai/gpt-4o -> openai/gpt-4o:online
anthropic/claude-sonnet-4-5:free -> anthropic/claude-sonnet-4-5:online
Any existing `:variant` (`:free`, `:nitro`, etc.) is replaced —
OpenRouter variants are mutually exclusive.
- `openrouter/free` is skipped: it's a meta-router and `:online` is
not a valid suffix on it (the gateway 400s).
- A one-line INFO log fires whenever the rewrite happens so the
diagnostic backend log shows exactly which model id the request
was promoted to.
Frontend (provider-capabilities.ts):
- providerSupportsBuiltinWebSearch now returns true for 'openrouter'
alongside 'openai' and 'anthropic'. The Search pill lights up and
the existing chat-adapter external branch already forwards
enabled_tools=['web_search'] based on this helper — no adapter
changes needed.
No new SSE event handling: OpenRouter does not emit a separate
web_search_call event the way OpenAI/Anthropic do. Citations come
back as text annotations via the existing reasoning_details path
the adapter already parses, so source data flows through without
extra translation. A per-call tool-card UX ("Searching for: …")
would require synthesizing one client-side; deferred to a follow-up
if the bare-citation flow feels too minimal.
* studio: wire Mistral built-in web search connector
Same shape as OpenAI's web_search tool, lives on
/v1/chat/completions instead of /v1/responses. When the chat
Search pill is toggled on with a Mistral model selected, the
backend now appends
{"type": "web_search"}
to body["tools"] before the request goes out. Idempotent —
won't double-append if a future call site adds it first. Models
in the registry allowlist that don't support the connector
(codestral, devstral, ministral, mistral-tiny) will surface a
400 from upstream; the existing default-path error log captures
it. Mistral's docs:
https://docs.mistral.ai/capabilities/agents/connectors/websearch
Frontend providerSupportsBuiltinWebSearch returns true for
'mistral' now, alongside openai / anthropic / openrouter. The
Search pill lights up for Mistral models and the existing
adapter branch already sends enabled_tools=['web_search'] off
this helper — no adapter changes.
No SSE translation yet — Mistral streams citations inline as
text annotations or `references` in the final assistant content,
not as a separate web_search_call event. Citations flow through
to the message body as text; a per-call tool-card UX with
"Searching for: …" indicators is a follow-up if needed.
* studio/backend: fix OpenRouter web_search to use plugins shape + synthesize tool card
Two changes against the actual OpenRouter docs at
https://openrouter.ai/docs/guides/features/plugins/web-search:
Request shape:
The previous commit appended :online to the model id, which works on
concrete model ids but rejects on meta-routers like openrouter/free —
and that's exactly the model the user was testing with, so neither
the request rewrite nor the diagnostic log fired. Switch to the
universal plugins shape:
body["plugins"] = [{"id": "web"}]
Per the docs this is "exactly equivalent" to :online but works on
every model id including openrouter/free and openrouter/auto. No
model suffix manipulation, idempotent if added twice.
Tool-card synthesis:
OpenRouter doesn't emit a structured web_search_call event the way
OpenAI/Anthropic do — citations come back only as `annotations` of
type=url_citation on delta/message objects. To match the chat-UI
tool-card UX the user expects ("Searching for: …" indicator,
source pills at message tail), synthesize the events client-side
in the default OAI-compat stream loop:
- On stream open (after the 200 status check): yield a synthetic
_toolEvent: tool_start with tool_name=web_search, fixed id
"openrouter_web_search". The chat-UI then renders the running
tool card before any text streams.
- During the SSE loop: scan every chunk's choices[].delta and
choices[].message for `annotations: [{type: "url_citation",
url_citation: {url, title, content}}]` entries. Dedup by URL
into a citations list. Handles both the nested-url_citation
shape OpenRouter documents and the flat-on-annotation shape
some upstreams ship.
- On [DONE] (or stream-close without [DONE]): emit synthetic
tool_end carrying the citations as
Title: …\nURL: …\nSnippet: …\n---\n…
blocks the existing parseSourcesFromResult lifts into source
pills at message tail.
Diagnostic log on completion now also reports
web_search_requested + citation count alongside the existing
chosen-model / event-count telemetry.
* studio: drop Mistral built-in web_search — connector lives on Agents API only
Mistral's web_search is exclusively on /v1/agents + /v1/conversations;
sending it on /v1/chat/completions returns
"WebSearchTool connector is not supported". Wiring it would require a
dedicated Agents streaming path. Remove from the frontend capability map
and revert the chat-completions tool injection.
* studio: wire Kimi $web_search builtin via two-call round-trip
Kimi's $web_search lives on /v1/chat/completions but requires a client
round-trip per https://platform.kimi.ai/docs/guide/use-web-search:
the first call returns tool_calls with function.arguments populated;
the caller echoes those arguments back as a role=tool message; the
second call streams the final answer with search results incorporated.
The docs also mandate thinking=disabled while the builtin is active.
Backend: new _stream_kimi_web_search helper dispatched from
stream_chat_completion when provider_type=='kimi' and 'web_search' in
enabled_tools. Buffers tool_calls across deltas, falls back to a plain
stream if the model declines to search, and synthesizes tool_start
(with parsed query) / tool_end (with any url_citation annotations) so
the chat UI's web-search card behaves the same as other providers.
Frontend: kimi added to providerSupportsBuiltinWebSearch so the Search
pill lights up in the composer.
* studio/chat: mutual exclusion of Think + Search on Kimi composer
Kimi's $web_search builtin requires thinking=disabled per
https://platform.kimi.ai/docs/guide/use-web-search, so the two states
cannot coexist. Make the pills mutually exclusive in both composers
(shared and welcome-screen): clicking Search turns Think off; clicking
Think back on turns Search off. Default Think to on when a Kimi model
is selected — k2.6/k2.5 ship with thinking enabled out of the box.
* studio/chat: fix wrong provider var name in onChange branch
selectedProvider, not provider — TS2304 in tsc -b.
* studio/backend: add diagnostics to Kimi $web_search round-trip
Log the actual function.arguments from the first call (so we can see
the model's search query) and the second call's usage.prompt_tokens +
any annotation type names that came through. prompt_tokens spiking
above the input message length is direct proof the server injected
search results into context. annotation_types lets us learn the shape
Kimi uses for citations if/when they emit any.
* studio: per-provider defaults — Anthropic xhigh + Search on, OpenAI high + Search on, Opus 4.7 gains max
Anthropic: Think effort defaults to the highest level the model
supports (xhigh on 4.6/4.7, high on 4.5) and Search starts on, since
the web_search_20250305 tool returns structured citations end-to-end.
OpenAI: Think effort defaults to 'high' (the gpt-5.x reasoning sweet
spot for /v1/responses + web_search) and Search starts on.
Opus 4.7: 'max' added as an effort level above 'xhigh' in both
backend (_ANTHROPIC_THINKING_SPECS) and frontend (ANTHROPIC_REASONING_MODELS).
Kimi diagnostics: emit tool_end immediately after tool_start so the
web-search card transitions to 'complete' before the second-call
answer streams, log first-call args + second-call usage/prompt_tokens
+ any annotation type names, request stream_options.include_usage so
the second call exposes usage in SSE.
* studio/backend: harden Kimi fallback path with HTTPError handler + manual aiter_lines loop
Addresses PR review feedback (#5443): the no-search fallback streaming
path was using `async for response.aiter_lines()` and had no
`httpx.HTTPError` guard around the POST. Switch to the manual
__anext__ loop pattern used elsewhere in this module (avoids the
Python 3.13 + httpcore 1.0.x GeneratorExit propagation issue) and wrap
the whole request in a try/except so network failures surface as a
proper SSE error frame instead of a raw traceback.
* feat: prompt caching frontend for openai/anthropic
* studio/chat: route vLLM provider to /v1/chat/completions, not /v1/responses
vLLM's /v1/responses rebuilds messages through the loaded model's chat
template, which 400s on strict-alternation templates like Gemma 3
("Conversation roles must alternate user/assistant/..."). Stop collapsing
vllm -> openai in the frontend so the backend sees the real provider type
and falls through to the standard chat-completions path. Register vllm as
a hidden entry in PROVIDER_REGISTRY so supports_vision and provider-create
validation work without surfacing it in the cloud-provider dropdown.
* studio/chat: wire prompt caching for OpenAI and Anthropic external providers
Backend half of the prompt_caching toggle that already exists in the chat
settings panel. Scoped to OpenAI cloud (/v1/responses) and Anthropic
(/v1/messages); every other provider plumbs the flag as a no-op.
- Anthropic: attach cache_control={type:ephemeral} to the system block so
the static prefix is reused across turns. Without the marker Anthropic
caches nothing, so this is the only way to make the toggle do real work
on /v1/messages.
- OpenAI: opt into prompt_cache_retention="24h" — same price as the
default in_memory policy per the OpenAI docs, but the cache survives
~24 hours of idle instead of ~5-10 minutes. The model picker is
registry-scoped to gpt-5.x / o3 / gpt-4.5, all of which accept the
parameter (gpt-5.5+ already defaults to "24h" so it's a no-op there).
- Treats `enable_prompt_caching=None` as enabled to match the frontend
default for both providers; pass `false` explicitly to opt out.
* studio/chat: log cache token counts on OpenAI and Anthropic stream completion
Surface cache usage in the existing "stream complete" info logs so
prompt-caching behavior can be verified by tailing the studio backend
log instead of opening the provider dashboard.
- Anthropic: latch usage from message_start (input + cache_creation +
cache_read counts) and message_delta (output_tokens), then include in
the per-request summary. cache_read_input_tokens > 0 confirms the
cache_control marker on the system block is doing its job.
- OpenAI Responses: latch usage from response.completed and
response.incomplete, extract usage.input_tokens_details.cached_tokens
(the /v1/responses field name, not prompt_tokens_details). A non-zero
value on turn N proves prompt_cache_retention="24h" let the prefix
hit the cache instead of being recomputed.
* studio/backend: strip temperature/top_p for Claude 4.7 family
Anthropic Opus 4.7 removed temperature, top_p, and top_k as a launch
breaking change ("Sampling parameters removed" in the 4.7 release notes
at https://platform.claude.com/docs/en/about-claude/models/whats-new-claude-4-7).
Setting any of them to a non-default value returns 400
"<param> is deprecated for this model". The existing guard only handled
top_k; temperature was still being sent unconditionally and is now
breaking opus-4-7 requests.
Rename _ANTHROPIC_TOP_K_DEPRECATED to _ANTHROPIC_4_7_SAMPLING_REMOVED to
reflect the broader scope, omit temperature from the base body on 4.7,
and skip the thinking-mode temperature=1 override on 4.7 (still applied
on 4.5/4.6 where it's required). Existing thinking_translation tests
target 4.5/4.6 / mock the wire so they're unaffected.
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* studio/chat: anchor Anthropic prompt cache on the latest message too
A system-only cache_control marker is a no-op when the system prompt is
empty or shorter than Anthropic's ~1024-token cache floor — caching
silently does nothing (both cache_creation and cache_read return 0).
Add a second cache_control breakpoint on the final block of the latest
conversation message so the entire prefix (system + prior turns + new
user turn) becomes eligible for caching. On turn N+1, Anthropic
rehydrates everything up through turn N's marker instead of recomputing
it. Up to 4 breakpoints are allowed per request; we use at most 2
(system + tail). Tail rebuild avoids mutating the caller's content list
so an image-bearing turn still slots cleanly into the cached prefix.
* studio/chat: gate vLLM reasoning toggle on provider config
Add a "This server runs a reasoning model" checkbox on the vLLM
provider config. When off (default), the chat Think pill stays
hidden and no enable_thinking ever reaches vLLM. When on, the
pill renders, per-turn state flows through the existing
enable_thinking plumbing, and the backend proxy lifts it onto
chat_template_kwargs.enable_thinking so vLLM's Jinja template
honours it.
* chore: clean vLLM reasoning-toggle comments
* studio/chat: gate prompt_cache_retention to actual OpenAI cloud requests
Addresses Codex P1 review on _stream_openai_responses. The frontend
only sends enable_prompt_caching for the openai/anthropic UI provider
types, so ollama/llama.cpp/"custom" requests reach this helper with
the flag as None. The previous `is not False` check treated None as
enabled and injected prompt_cache_retention="24h" into every request
including those bound for non-OpenAI servers, which would 400 on
servers that implement /v1/responses but not the retention parameter.
Match the public OpenAI host (api.openai.com) on the client base_url
before adding the field so it only lands on actual OpenAI cloud
requests. Studio's openai picker is already registry-scoped to
gpt-5.x / o3 / gpt-4.5, all of which accept the parameter.
---------
Co-authored-by: Roland Tannous <rolandtannous@gravityq.ai>
Co-authored-by: Roland Tannous <115670425+rolandtannous@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
14 lines
8.6 KiB
XML
14 lines
8.6 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="294 159 1405.09 1857.06">
|
|
<g clip-path="url(#clip0_1758_1066)">
|
|
<path d="M599.877 159.522C582.544 162.322 561.744 171.388 547.077 182.588C502.677 216.322 468.277 287.922 453.744 377.122C448.277 410.855 444.544 457.655 444.544 493.388C444.544 535.522 449.477 589.388 456.544 626.589C458.144 634.855 458.944 642.188 458.277 642.722C457.744 643.255 451.211 648.588 443.877 654.455C418.811 674.455 390.144 705.255 370.411 733.388C332.544 787.122 308.011 848.188 297.744 914.322C293.744 940.455 292.677 993.255 295.877 1019.39C302.944 1079.66 321.077 1130.59 352.144 1177.26L362.277 1192.32L359.344 1197.26C338.544 1232.19 320.811 1282.72 312.544 1331.26C306.011 1369.66 305.211 1379.92 305.211 1431.39C305.211 1483.26 305.877 1493.52 312.011 1529.39C319.344 1572.32 334.277 1617.79 350.944 1648.06C356.411 1657.92 369.744 1678.46 371.344 1679.52C371.877 1679.79 370.277 1684.72 367.744 1690.46C348.544 1732.46 332.144 1788.32 325.344 1835.39C320.544 1867.66 319.877 1878.06 319.877 1912.06C319.877 1955.39 322.277 1976.46 331.344 2010.99L332.677 2016.06H389.744H446.944L443.211 2008.99C420.144 1966.32 418.011 1887.12 437.877 1808.06C446.944 1771.52 457.211 1744.72 476.411 1707.79L487.877 1685.39V1671.66C487.877 1658.86 487.611 1657.39 483.477 1648.99C480.277 1642.59 476.011 1637.12 468.411 1629.66C455.477 1617.12 446.144 1603.92 438.677 1587.66C405.877 1516.46 399.477 1410.72 422.544 1320.59C432.144 1282.99 448.011 1249.52 464.677 1231.26C476.011 1218.72 481.877 1204.72 481.877 1190.19C481.877 1175.12 476.544 1162.72 464.544 1149.79C430.144 1112.99 408.944 1068.19 401.344 1016.06C390.544 941.788 410.144 860.855 454.677 796.722C498.277 733.788 559.477 693.388 627.877 682.589C643.211 680.055 671.877 680.455 687.877 683.388C705.344 686.455 716.277 685.522 727.477 680.188C741.344 673.655 748.277 665.522 756.411 646.855C763.611 630.188 769.211 621.122 784.277 602.322C802.411 579.788 819.877 564.455 847.877 545.922C879.877 524.988 916.277 509.788 952.544 502.455C965.744 499.788 971.877 499.388 996.544 499.388C1021.21 499.388 1027.34 499.788 1040.54 502.455C1093.74 513.255 1146.54 540.722 1188.68 579.655C1197.74 588.055 1219.48 614.988 1226.41 626.188C1229.08 630.588 1233.74 639.922 1236.68 646.855C1244.81 665.522 1251.74 673.655 1265.61 680.188C1276.41 685.388 1287.74 686.455 1304.54 683.655C1331.08 679.122 1351.48 679.522 1377.48 684.855C1466.01 702.722 1543.08 775.655 1577.21 873.388C1606.94 959.122 1598.54 1048.86 1554.28 1117.39C1546.81 1128.99 1539.34 1138.32 1528.54 1149.79C1505.21 1174.72 1505.21 1205.66 1528.41 1231.26C1566.54 1272.99 1590.41 1375.66 1583.21 1466.19C1578.41 1525.92 1563.08 1579.39 1542.01 1609.66C1538.28 1614.99 1530.54 1624.06 1524.68 1629.66C1517.08 1637.12 1512.81 1642.59 1509.61 1648.99C1505.48 1657.39 1505.21 1658.86 1505.21 1671.66V1685.39L1516.68 1707.79C1535.88 1744.72 1546.14 1771.52 1555.21 1808.06C1574.81 1886.06 1573.08 1963.66 1550.68 2007.79C1548.81 2011.52 1547.21 2014.99 1547.21 2015.39C1547.21 2015.79 1572.68 2016.06 1603.88 2016.06H1660.41L1661.88 2010.32C1662.68 2007.26 1664.01 2002.59 1664.68 1999.92C1666.14 1994.06 1669.08 1976.72 1671.48 1960.06C1673.74 1943.26 1673.74 1881.39 1671.48 1862.72C1662.94 1794.99 1648.68 1741.26 1625.34 1690.46C1622.81 1684.72 1621.21 1679.79 1621.74 1679.52C1622.41 1679.12 1626.14 1673.79 1630.14 1667.79C1659.21 1623.79 1677.08 1568.46 1686.14 1495.39C1688.54 1475.26 1688.54 1388.72 1686.14 1369.39C1679.74 1319.52 1672.01 1285.66 1659.21 1251.39C1653.88 1237.12 1639.74 1206.99 1633.74 1197.26L1630.81 1192.32L1640.94 1177.26C1672.01 1130.59 1690.14 1079.66 1697.21 1019.39C1700.41 993.255 1699.34 940.455 1695.34 914.322C1684.94 848.055 1660.54 787.255 1622.68 733.388C1602.94 705.255 1574.28 674.455 1549.21 654.455C1541.88 648.588 1535.34 643.255 1534.81 642.722C1534.14 642.188 1534.94 634.855 1536.54 626.589C1552.68 542.455 1552.14 437.522 1535.21 355.522C1520.54 284.055 1493.88 227.255 1459.48 194.455C1432.01 168.322 1404.01 157.122 1370.41 159.255C1293.34 163.788 1231.21 252.455 1206.68 392.188C1202.68 414.722 1199.21 441.122 1199.21 448.322C1199.21 451.122 1198.68 453.388 1198.01 453.388C1197.34 453.388 1192.14 450.722 1186.54 447.388C1127.08 412.188 1060.94 393.388 996.544 393.388C932.144 393.388 866.011 412.188 806.544 447.388C800.944 450.722 795.744 453.388 795.077 453.388C794.411 453.388 793.877 451.122 793.877 448.322C793.877 440.855 790.277 413.655 786.411 392.188C764.144 266.722 713.077 183.655 645.211 162.722C635.877 159.922 609.344 158.055 599.877 159.522ZM622.544 268.055C641.744 283.255 663.077 326.722 675.344 375.388C677.611 384.188 680.011 394.322 680.677 398.055C681.211 401.655 682.677 409.788 683.877 416.055C689.077 444.322 691.477 474.855 691.744 512.055L691.877 548.722L682.677 562.322L673.477 576.055H652.011C626.944 576.055 602.011 579.255 578.144 585.655C569.611 587.788 561.344 589.922 559.744 590.322C557.211 590.855 556.811 590.055 555.344 579.122C547.477 519.788 547.877 454.055 556.544 399.388C566.144 338.455 588.544 283.255 610.411 266.988C615.611 263.122 616.544 263.255 622.544 268.055ZM1382.81 267.122C1396.01 276.855 1410.54 302.722 1421.34 335.788C1443.08 401.922 1449.21 492.722 1437.74 579.122C1436.28 590.055 1435.88 590.855 1433.34 590.322C1431.74 589.922 1423.48 587.788 1414.94 585.655C1391.08 579.255 1366.14 576.055 1341.08 576.055H1319.61L1310.41 562.322L1301.21 548.722L1301.34 512.055C1301.61 460.322 1306.41 419.922 1317.88 374.988C1330.01 326.722 1351.48 283.255 1370.54 268.055C1376.54 263.255 1377.48 263.122 1382.81 267.122Z" fill="black"/>
|
|
<path d="M975.877 938.189C946.944 940.989 939.077 942.055 925.21 944.855C902.677 949.522 872.544 959.922 851.61 970.189C778.81 1005.79 728.677 1065.12 713.344 1133.79C710.277 1147.39 709.877 1151.92 709.877 1174.86C709.877 1197.52 710.277 1202.46 713.21 1215.39C733.61 1305.12 816.277 1371.39 923.21 1383.52C946.41 1386.06 1046.68 1386.06 1069.88 1383.52C1155.74 1373.79 1229.61 1327.26 1262.81 1261.92C1271.61 1244.46 1275.88 1233.12 1279.88 1215.39C1282.81 1202.46 1283.21 1197.52 1283.21 1174.86C1283.21 1151.92 1282.81 1147.39 1279.74 1133.79C1257.48 1034.06 1160.68 955.522 1042.01 940.589C1026.54 938.722 986.01 937.122 975.877 938.189ZM1025.74 1010.72C1065.34 1014.99 1105.21 1029.12 1137.21 1050.46C1154.41 1061.92 1178.68 1085.92 1189.08 1101.66C1201.88 1121.12 1209.21 1140.99 1212.54 1165.12C1214.01 1176.19 1213.21 1184.59 1209.21 1202.46C1202.94 1229.12 1183.48 1256.99 1157.21 1276.46C1144.94 1285.39 1119.48 1298.32 1103.88 1303.39C1074.28 1312.86 1054.94 1314.59 985.877 1314.06C940.81 1313.66 932.81 1313.26 919.877 1310.86C875.744 1302.59 840.81 1284.99 815.477 1258.19C794.944 1236.59 785.61 1216.86 780.544 1184.99C778.277 1170.19 782.544 1145.66 791.21 1124.99C801.744 1099.79 828.944 1068.46 855.877 1050.46C887.077 1029.66 928.144 1014.86 965.877 1010.86C980.41 1009.26 1011.21 1009.26 1025.74 1010.72Z" fill="black"/>
|
|
<path d="M945.61 1108.06C935.477 1113.52 928.41 1127.39 930.543 1137.66C932.943 1148.72 942.677 1159.92 957.877 1169.12C966.01 1174.06 966.543 1174.72 966.943 1179.66C967.21 1182.59 966.143 1190.99 964.677 1198.46C963.077 1205.79 961.877 1213.52 961.877 1215.66C962.01 1221.39 967.343 1230.72 972.943 1235.26C977.877 1239.26 978.81 1239.39 992.677 1239.79C1005.34 1240.19 1008.01 1239.92 1013.08 1237.52C1026.14 1231.12 1029.48 1219.39 1024.68 1196.86C1020.68 1178.06 1021.48 1175.12 1031.48 1169.39C1042.01 1163.26 1053.21 1152.46 1056.54 1145.12C1062.94 1131.12 1057.08 1115.26 1042.94 1107.92C1039.48 1106.19 1035.21 1105.39 1028.94 1105.39C1019.21 1105.39 1012.94 1107.66 1001.48 1114.99L994.943 1119.12L990.81 1116.59C973.877 1106.59 970.81 1105.39 960.543 1105.52C953.21 1105.52 949.21 1106.19 945.61 1108.06Z" fill="black"/>
|
|
<path d="M621.878 953.255C598.278 960.722 580.678 978.055 571.611 1002.72C567.211 1014.46 565.078 1032.99 566.945 1042.99C571.345 1066.86 590.945 1088.59 613.211 1094.59C641.211 1101.92 662.145 1097.12 680.678 1078.72C691.478 1068.19 697.345 1058.99 703.211 1044.06C707.478 1033.52 707.745 1031.66 707.745 1016.72L707.878 1000.72L702.278 989.255C693.345 971.122 677.211 957.655 658.545 952.722C648.011 950.055 631.078 950.189 621.878 953.255Z" fill="black"/>
|
|
<path d="M1334.01 952.855C1315.74 957.789 1299.48 971.389 1290.81 989.255L1285.21 1000.72L1285.34 1016.72C1285.34 1031.66 1285.61 1033.52 1289.88 1044.06C1295.74 1058.99 1301.61 1068.19 1312.41 1078.72C1330.94 1097.12 1351.88 1101.92 1379.88 1094.59C1396.01 1090.32 1412.14 1076.72 1419.88 1060.86C1426.54 1047.39 1428.14 1037.66 1426.01 1022.32C1421.08 987.255 1400.54 961.789 1370.01 952.855C1361.08 950.189 1343.74 950.189 1334.01 952.855Z" fill="black"/>
|
|
</g>
|
|
<defs>
|
|
<clipPath id="clip0_1758_1066">
|
|
<rect width="5849.33" height="2016" fill="transparent"/>
|
|
</clipPath>
|
|
</defs>
|
|
</svg>
|
