* Change API button warning from credit to charge
Updated the warning message for the test API button to indicate a charge instead of a credit. (you are using tokens to send the message, the provider is not giving you tokens because you sent a test)
* fix: clarify test message usage charges
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Allow npm releases to be retried from an existing release tag through the trusted publishing workflow, and scope the `allow-directory` workaround to the publish command.
undici (Node's fetch) transparently decompresses gzip, deflate, and br,
but not zstd. When a browser's full Accept-Encoding header is forwarded
as-is to the target origin, a Cloudflare-fronted server may respond
with zstd, and corsProxyMiddleware pipes those still-compressed bytes
straight through — the client receives garbage instead of the expected
body (e.g. "SyntaxError: Unexpected token" when parsing JSON).
Cap the outgoing Accept-Encoding to the encodings undici can actually
decode, so the target always responds with something we can forward
correctly.
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
* Fix: Avoid cpSync crash when renaming characters
Add a no-op filter to fs.cpSync during character renaming.
This avoids Node.js's native copyDir fast path, which can terminate
the process on Windows with affected Node.js versions instead of
throwing a catchable filesystem error.
Refs: https://github.com/nodejs/node/issues/63970
* docs: explain character rename copy workaround
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
* fix: return a degraded preview instead of {} when a chat's last line is unparseable
getChatInfo resolved an empty object when the last line of a chat .jsonl
failed to parse or lacked known fields (truncated write, external edit).
All three consumers (chat list, search, recents) drop entries without a
file_name, so an otherwise intact chat silently disappeared from the UI
while still occupying its name for uniqueness checks (#5940).
Resolve the already-built chatData instead: file_id, file_name, file_size
and mtime-based last_mes are known good from stat(), chat_items comes from
the line count, and mes falls back to the existing placeholder. Matcher
results from the intact lines are preserved for search.
Fixes#5940
* fix: exclude unreadable chat line from message count
Keep degraded previews aligned with the messages that can actually be loaded by excluding both the metadata line and broken trailing line.
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
This change adds a chat-specific "x-session-affinity" HTTP header to requests to Fireworks that use the full prompt. Quiet requests like summarization requests that don't use the same prompt prefix are excluded.
This improves prompt caching by
1. Adding a stable "x-session-affinity" header, which Fireworks AI recommends to route requests to the same replica
2. Separating different chats into different sessions
3. Separating main LLM calls from quiet calls which have a completely different prompt prefix
See https://docs.fireworks.ai/guides/prompt-caching.
This uses an HMAC with the cookie secret instead of simply hashing the chat title to avoid leaking chat titles. Session affinity headers may not fall under zero-data retention in Fireworks or could be cached by proxies on the way. Chat titles are tiny, so the HMAC computation is instant.
Providers can return an HTTP 200 response whose body carries an error
object without a message field, or the error as a plain string. The
error message fell back to response.statusText, which is 'OK' for any
200 response, producing the opaque 'Error: OK'. Error messages now fall
back to the error's code or type field, then the string form, and only
use statusText for non-2xx responses where it carries meaning. Applies
to the non-streaming request path and both streaming error toasts.
Fixes#5647
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix: give non-ASCII chat names distinct backup keys and throttles
Backup filenames replace all non-alphanumeric characters with
underscores, so names such as equal-length CJK ones collapsed to the
same key and shared a single backup quota: busy chats evicted the
backups of unrelated quiet ones. The backup key now appends a short
hash of the raw name whenever the name contains non-ASCII characters,
keeping keys distinct and stable while ASCII names keep their exact
current keys and retention.
The backup throttle was also keyed per user only, so rapid saves in
one chat deferred or swallowed the backup of another chat saved in the
same window. It is now keyed per user and chat.
Fixes#5780
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix: replace stray NUL byte in backup throttle key separator
A literal 0x00 byte slipped into the template string separator, which
made Git treat the whole file as binary.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* chore: reunite backupChat docblock with its function
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Branches and checkpoints inherited the parent chat's integrity UUID
through the chat_metadata spread in saveChat and saveGroupBookmarkChat,
so every member of a branch family shared one slug and the integrity
guard could not tell them apart. A save aimed at the wrong file within
the family would pass validation. New branches and checkpoints now get
their own slug at creation. Existing files are unaffected.
Fixes#5942
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Check the never_resize_avatars setting to request or not cropping for group avatars.
* Change max width of thumbnail to 300px so square images are allowed.
* fix(expressions): guard against null/undefined default-expression labels
Classifiers can return a falsy or literal "null"/"undefined" expression
label, and setDefaultEmojiForImage then requested the nonexistent
/img/default-expressions/null.png, producing a 404.
Fall back to DEFAULT_FALLBACK_EXPRESSION (joy) when the label is falsy,
a literal "null"/"undefined", or a custom expression without a default
asset. This is the only place the default-expressions URL is built, so the
guard covers all 404 paths.
Fixes#5863
* fix(expressions): fall back for any label without a default asset
Generalize the guard to a whitelist check against DEFAULT_EXPRESSIONS.
Every entry in that list has a matching default-expressions asset, so
any other label (falsy, literal null/undefined strings, custom
expressions, or unexpected classifier output) falls back to the
default expression instead of requesting a missing image.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
PR #5571 added an extensionsEnabledFeatureGuard middleware that reads
extensions.enabled via getConfigValue. The test environment has no
config.yaml, so getConfig() exits the process and kills the Jest
worker, failing the extensions-discover suite. Set the env var
override so the guard resolves without touching the config file.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix: prevent proxy keys from triggering password manager
Render reverse proxy credentials as visually masked text fields with password-neutral DOM identifiers while preserving existing settings, preset, and request field names. Align the Azure OpenAI key input and add regression coverage.
* fix: preserve masked secret clipboard protection
Closes#4448
The 'ooba' special case in the caption-image route split the correctly
structured message (a single user message with a content array
containing text + image_url) into two separate messages, moving
image_url to a top-level property with an empty content array.
oobabooga's own multimodal image handling (modules/image_utils.py)
only looks for images inside content array items with
type: 'image_url', so this transformation caused the image to be
silently dropped, producing hallucinated or "I can't see an image"
captions - even though the request appeared to contain valid image
data.
Removing the special case lets 'ooba' use the same, already-correct
message structure as every other multimodal-capable API.
Verified against a local oobabooga (llama.cpp/GGUF loader) with a
vision-capable GGUF + mmproj pair: before the fix, captions ignored
the attached image; after the fix, captions accurately describe real
photos.
Co-authored-by: bbastex <bbastex@users.noreply.github.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
* Fireworks AI: Fetch model list from custom URL
Fireworks provides the model list on a custom URL in a custom format, see https://docs.fireworks.ai/api-reference/list-models. The standard /v1/models endpoint no longer works correctly and returns a wrong list of models:
```
Available models: [
'accounts/fireworks/models/deepseek-v4-pro',
'accounts/fireworks/models/flux-1-schnell-fp8',
'accounts/fireworks/models/glm-5p1',
'accounts/fireworks/models/glm-5p2',
'accounts/fireworks/models/gpt-oss-120b',
'accounts/fireworks/models/kimi-k2p5',
'accounts/fireworks/models/kimi-k2p6'
]
```
Many new models like Deepseek V4 Pro, Kimi K2.7 Code are missing.
* Fireworks AI: Add "fast" models
Some models have a "fast" variant. The model list endpoint does not return this information, so for now the available fast versions are listed explicitly.
Fast models have the same parameters (max context etc.) as the regular ones. They are only faster and cost more.
Filter lists only print tags that are assigned to at least one entity, so a
persisted filter on an unassigned tag has no element to toggle. "Clear all
filters" cannot reset it either, since it works by clicking the printed
elements. The result is a character list that stays empty on every app start,
showing only an "N characters hidden" notice with no visible cause.
removeMissingTagFilters() already dropped filters for deleted tags and for
empty open bogus folders (#5225). Generalize that check to any tag without
assigned entities, which covers plain tags as well, and clear the matching
account storage entry so the filter does not come back on the next reload.
Co-authored-by: Martin Tibke <martin@tibke.net>
A manually deleted extension often leaves a folder husk on disk, for
example when Windows fails to remove locked .git files. The discover
endpoint listed any directory, so the husk kept reporting as an
installed extension: /extension-exists and /extension-state returned
true after a fresh load and the manifest fetch produced a 404 in the
console on every load. Discovery now skips folders without a
manifest.json and logs a warning naming the exact path, and the
client drops any discovered name whose manifest could not be loaded
so state queries cannot report ghost extensions.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Browsers filter datalist suggestions to the current input value, so
Generic OpenAI-compatible text completion looked like a single model
while Chat Custom's select showed the full /v1/models list. Add an
Available Models select (select2 + reconnect) matching other textgen
backends, and keep the optional free-text Model ID field.
Co-authored-by: trahloc <trahloc@proton.me>
Co-authored-by: Cursor <cursoragent@cursor.com>
* Update TTS model from Gemini 2.5 to 3.1 in TTS Extension (#5778)
* Update TTS model from Gemini 2.5 to 3.1 in TTS Extension
Added New versions and new Default model
* Add glm-5.2 option to model selection dropdown
* fix: remove GroupId requirement from MiniMax TTS
MiniMax's current API (sk-cp- keys) uses Bearer auth only. GroupId
is a legacy parameter from the pre-2025 API that the current API
tolerates/ignores. Requiring it blocks new users from setting up
MiniMax TTS.
- Backend: drop groupId from required params and URL
- Frontend: remove Group ID input field and all validation checks
Fixes#5909
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Samueras <Samueras@jackoedv.de>
Co-authored-by: chen-jiying <chen-jiying@users.noreply.github.com>
* Update TTS model from Gemini 2.5 to 3.1 in TTS Extension (#5778)
* Update TTS model from Gemini 2.5 to 3.1 in TTS Extension
Added New versions and new Default model
* Add glm-5.2 option to model selection dropdown
* Refactor file reading to use getArrayBufferSlice
* Update util.js
* Update util-pure.test.js
* test: add real-archive regression for BYAF pooled buffer handling
Builds an actual BYAF zip in memory, embeds it at an offset inside a
larger backing buffer to simulate Node's buffer pooling, and proves
through the real parser that the exact ArrayBuffer slice parses
correctly while the raw oversized backing buffer does not.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Samueras <Samueras@jackoedv.de>
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix: skip non-image ComfyUI outputs
* test: cover ComfyUI gif fallback and no-output error paths
Extends the skip-non-image regression with the gifs fallback that
animated workflows rely on and the error path when no output node
carries images or gifs.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: CaoBochun <caobochun@bytedance.com>
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* feature: add Claude Opus 5, Sonnet 5, and Gemini 3.6 Flash / 3.5 Flash-Lite
Enable adaptive thinking and strip rejected sampling/prefill fields so the new models work with Chat Completions and Image Captioning.
* feature: add Gemini 3.7 Flash
Strip rejected sampling/prefill fields and map min thinking to low so the model works with Chat Completions and Image Captioning.
* feat: refresh Claude and Gemini model lists on top of Claude 5 support
Builds on the Claude 5 and Gemini wiring in this branch: removes
retired models from the Claude and Gemini dropdowns and captioning
lists (claude-opus-4-1 verified retired with a live 404; Gemini 2.0
experimental models, 2.5 preview snapshots, and gemini-3-pro-preview
are shut down per Google's model docs), labels deprecated models
without touching option values so saved selections keep working, adds
claude-fable-5 to the captioning list, and moves new-install defaults
to claude-sonnet-5 and gemini-3.7-flash. Claude 5 generation, vision,
web search, and effort mapping verified live against the API; the
trailing-prefill test now uses a plain loop so the tests lint passes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Verifies Sol, Terra, and Luna live against the API: generation,
vision, effort values (none/low/xhigh), the unlisted gpt-5.6 alias,
and the sampler contract (temperature and top_p are rejected even
with reasoning off, so the strict stripping stays). Removes models
OpenAI has shut down from the model dropdowns, labels announced
deprecations without touching option values, orders groups newest
first, and moves the new-install and captioning defaults off
gpt-4-turbo, which shuts down on October 23, 2026.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Don't reload chat from addswipe
* test: add /addswipe regression and harden e2e login helper
Covers both /addswipe modes through the real command pipeline:
swipe data, counters, visible text, and message element identity,
which a full chat reload would break. The login helper now tries
accounts from last to first so password-protected accounts don't
break local e2e runs, and the test waits out fresh-account
onboarding before measuring.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Update TTS model from Gemini 2.5 to 3.1 in TTS Extension (#5778)
* Update TTS model from Gemini 2.5 to 3.1 in TTS Extension
Added New versions and new Default model
* Add glm-5.2 option to model selection dropdown
* Fix crash when a chat file is deleted mid-scan
getChatInfo() stats a chat file without handling ENOENT. If the file
is deleted (e.g. from the UI) while a search or the recent-chats list
is scanning the same directory, the stat throws, and since it's inside
new Promise(async (res) => {...}) with no reject wired up, it becomes
an unhandled rejection that kills the whole server process.
This catches ENOENT and resolves with { match: false } instead, same
as the fallback already used elsewhere in this function/its callers
for corrupted or unmatched entries.
* fix: handle all mid-scan chat deletion races in getChatInfo
The stat guard alone left the function unsound: it lived inside an
async promise executor, so a non-ENOENT error became an unhandled
rejection and the promise never settled. A file deleted between the
stat and the stream opening still crashed via an unhandled stream
error, which readline re-emits, and a file truncated to empty mid-scan
hung the request because the close handler never resolved.
getChatInfo now uses plain async/await up to the streaming part,
resolves a no-match sentinel when the file vanishes at either point,
resolves an empty object on truncation, and properly rejects
everything else. Comes with deterministic regression tests for each
race window.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Samueras <Samueras@jackoedv.de>
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Fix BFL API endpoint and polling URL handling
* fix: send authentication header when polling BFL results
The bfl.ai API requires the x-key header on the polling request as
well; the retired bfl.ml API tolerated unauthenticated polling. Without
the header every poll returns 403 and generation never completes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Applying a CC preset deferred the actual settings update behind an
unawaitable event continuation, so /preset resolved before the preset
was applied. A connection profile switch runs /api, /preset, /api in
sequence, and the preset's stored chat_completion_source would land
after the final /api check, reverting the source to the previous
provider. Requests then silently went to the wrong endpoint.
The preset application chain is now captured in a promise that
selectPreset awaits, so /preset resolves only when the preset is fully
applied and follow-up commands sequence correctly. The UI dropdown
path is unchanged, and callers that do not await selectPreset keep
the exact previous behavior.
Fixes#5926Fixes#5147
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix: reject localhost and .localhost domains in /api/search/visit to prevent SSRF bypass
The hostname check in /api/search/visit only validated IP addresses using
ipRegex, but did not block 'localhost' or subdomains ending in '.localhost'.
This allowed SSRF bypasses to internal services via localhost URLs.
Changes:
- Add explicit rejection of 'localhost' hostname
- Add rejection of any hostname ending in '.localhost' (RFC 6761 reserved)
Closes GHSA-wm7j-m6jm-8797
* fix: enforce SSRF boundary for /api/search/visit at connection time
The URL string checks only guard the literal input. Hostnames resolving
to private addresses, redirects into internal services, and DNS
rebinding all bypassed them. The visit endpoint now routes its outbound
request through a strict PrivateRequestAgent even when the private
request filter is disabled: the resolved IP is validated at connection
time on every hop and the connection is pinned to the validated IP.
When the private request filter is enabled its configured whitelist
keeps applying, and an enabled request proxy keeps owning routing.
Also rejects bracketed IPv6 literals, which kept their brackets and
slipped past the hostname check.
Fixes GHSA-wm7j-m6jm-8797
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
An existing non-empty chat file whose first line could not be parsed as a
JSON object passed the integrity check as if it were a legacy chat, so a
save silently replaced the file and only the replacement got backed up.
The check now fails closed for unparseable, truncated, or non-object
headers, routing the client into the existing overwrite confirmation
dialog. A UTF-8 BOM in front of an otherwise valid header is stripped
before parsing. Empty files, valid legacy headers, and force saves behave
as before.
Fixes#5454
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The ComfyUI polling loop fetches /history every 100ms to check if the
current prompt has completed. This returns the entire history, which
grows unboundedly. After ~170 generations, the JSON response exceeds
Node.js's 512MB string length limit, crashing the server with:
RangeError: Invalid string length
Fix by requesting /history/{id} instead, which returns only the single
prompt entry needed. This is a supported ComfyUI API endpoint that
returns the same data structure.
updatePlugins called fs.statSync on every entry returned by readdirSync
just to test isDirectory(). Pass withFileTypes to readdirSync and filter
on the Dirent type instead. Symlinks are still treated as directories.
The previous date sort read file modification times while comparing
items, which meant stat'ing the same files over and over for one
listing. mtimes are now read once per file before sorting. Files that
disappear during the call (e.g. concurrent deletion) sort to the start
instead of crashing.
* feature: support Claude Opus 4.8 model
* feature: support OpenAI GPT 5.6 models
* fix: replace deprecated Gemini preview model with stable gemini-3.1-flash-lite
* Fix GPT-5.6 Chat Completions effort mapping
- Map Maximum reasoning effort to xhigh because max is Responses-only
- Clarify model-specific OpenAI and adaptive Claude effort guidance
- Cover stable Gemini 3.1 Flash-Lite thinking-level routing
Tests:
- npm run test:unit -- --runInBand
- ESLint on all changed JavaScript files
* Fix: migrate Gemini image models to stable IDs
- Replace shut-down Gemini image preview selectors for Google AI and Vertex AI
- Migrate saved chat and caption model settings to the stable replacements
- Enable image generation for the stable model IDs
- Correct the Gemini 3.1 Flash Image context fallback to 128K
- Add regression coverage for stable Gemini 3 image thinking levels
Tests:
- npm run test:unit -- --runInBand
- ESLint on all changed JavaScript files
---------
Co-authored-by: Wolfsblvt <wolfsblvt@gmail.com>
* Optimize World Info entry sorting to avoid O(n^2) lookups
The comparator in checkWorldInfo called sortedEntries.indexOf() twice per
comparison, making the sort O(n^2 log n). Build an index Map once and use
it for lookups instead. Sort order is unchanged.
* Address review: build index map before sort, use -1 for unknown entries
Move sortedEntriesIndex creation to immediately before the activatedNow
sort so indices match the current sortedEntries array. Use ?? -1 so
externally force-activated (cloned) entries behave like indexOf(-1).
* Skip index map when at most one entry needs sorting
Build sortedEntriesIndex only when activatedNow.size > 1, since the
comparator is not used for zero or one activated entries.
---------
Co-authored-by: ransxd <ransxd@users.noreply.github.com>
* Update TTS model from Gemini 2.5 to 3.1 in TTS Extension
Added New versions and new Default model
* Add glm-5.2 option to model selection dropdown
Co-authored-by: Samueras <Samueras@jackoedv.de>
"for 3rd party API customers: GET /user/information, GET /user/data, GET /user/subscription should now be called from https://image.novelai.net. The old URL will be non-functional in a couple of hours. The old URL is currently non-functional."
from NAI devs, this change has already been implemented from NAI side, no backward compat.
* Split Pollinations into two separate API providers: (Key) and (No Key)
- Replaces the single "Pollinations" source with two distinct entries:
- "Pollinations (Key)": uses gen.pollinations.ai/v1 with Bearer token auth,
supports BYOP OAuth flow with app key pk_Gu8Ta8q6QhS67hSg and manual key entry
- "Pollinations (No Key)": uses text.pollinations.ai/v1, no authentication required
- Renames CHAT_COMPLETION_SOURCES.POLLINATIONS to POLLINATIONS_KEY/POLLINATIONS_NOKEY
throughout the codebase (constants, endpoints, frontend scripts)
- Adds BYOP authorize button and OAuth callback handler for key-based source
- Updates all data-source attributes, secret key mappings, model selectors,
tool-calling, reasoning, slash-commands, caption, and SD extension references
https://claude.ai/code/session_01T57Cm84cv2GiSL4DPCccBj
* Fix POLLINATIONS_NOKEY: exempt from API key check, fix placeholder text
- Add POLLINATIONS_NOKEY to the keyless providers exemption in the
/generate endpoint's API key guard (was hitting the 400 check)
- Remove 'pk_...' from the key input placeholder since pk_ is the
app key used in the BYOP auth link, not the user's secret key
https://claude.ai/code/session_01T57Cm84cv2GiSL4DPCccBj
* Add Pollinations anonymous/authenticated endpoint selector
Implements reviewer feedback to use a single Pollinations provider with
an endpoint dropdown (similar to Z.AI) rather than two separate sources.
- Add POLLINATIONS_ENDPOINT enum (anonymous / authenticated)
- Anonymous uses text.pollinations.ai/v1, no API key required
- Authenticated uses gen.pollinations.ai/v1, requires sk_... key with BYOP OAuth support
- Key input and BYOP button are hidden when anonymous endpoint is selected
- Backend skips key guard for anonymous requests
- Reasoning effort and JSON schema only sent for authenticated mode
- Connection status check passes for anonymous without a saved key
https://claude.ai/code/session_01T57Cm84cv2GiSL4DPCccBj
* Fix broken Pollinations references after resolving merge conflicts
- Replace POLLINATIONS_KEY/NOKEY in CHAT_COMPLETION_SOURCES with POLLINATIONS
- Fix SECRET_KEYS.POLLINATIONS → SECRET_KEYS.POLLINATIONS_KEY in backend
- Update all chat_completion_sources references in openai.js to use unified POLLINATIONS
- Consolidate duplicate model select/change handlers into single pollinations_model
- Keep backward compat in caption-image handler for pollinations_key/nokey multimodal API
- Fix openai.js inline handler to route pollinations to correct endpoint based on endpoint field
https://claude.ai/code/session_01T57Cm84cv2GiSL4DPCccBj
* Complete Pollinations unification: remove all pollinations_key/nokey splits
- Fix committed merge conflict in openai.js (Wolfsblvt review)
- Replace POLLINATIONS_KEY/NOKEY in chat_completion_source dropdown with single POLLINATIONS option
- Replace pollinations_key,pollinations_nokey in all data-source attributes with pollinations
- Merge duplicate /pollinations_key and /pollinations_nokey multimodal routes into single /pollinations
- Update caption extension: single "Pollinations" option using pollinations_endpoint from oai_settings
- Update slash-commands.js model selector to single pollinations entry
- Clean up caption-image handler (openai.js) to use only 'pollinations' api type
- Pass pollinations_endpoint in caption request body (shared.js)
- Add settings migration: pollinations_key → pollinations, pollinations_nokey → pollinations (anonymous)
https://claude.ai/code/session_01T57Cm84cv2GiSL4DPCccBj
* Address Cohee review: named constants, mock key, revert POLLINATIONS_KEY rename, default to authenticated
- Use POLLINATIONS_ENDPOINT named constants throughout (no magic 'anonymous' strings)
- Use mock key pattern (set key to POLLINATIONS_ENDPOINT.ANONYMOUS value) so no guard exception needed
- Revert POLLINATIONS_KEY rename back to POLLINATIONS in secrets.js files
- Default pollinations_endpoint to AUTHENTICATED so saved keys aren't bypassed
- Remove redundant isPollinationsAnon check from getReasoningEffort() (backend handles it)
- Unify tool-calling.js, caption, shared, stable-diffusion to single POLLINATIONS source
https://claude.ai/code/session_01T57Cm84cv2GiSL4DPCccBj
* Fix ESLint padded-blocks error in BYOP OAuth callback
https://claude.ai/code/session_01T57Cm84cv2GiSL4DPCccBj
* fix: regression in caption API validation
* fix: remove unneeded migration
* fix: remove duplicate keyless check in apiSourceConfig
* fix: regression in extractReasoningFromData
* refactor: simplify UI unhide logic
* fix: remove BYOP flow due to security concerns
* fix: use a string instead of a constant reference for placeholder key
* fix: reconnect when switching endpoints
* feat: support pollinations in /api-url command
* fix: remove endpoint check from image generation (it always uses authenticated)
* fix: default to authenticated
* fix: use a named constant in auto-connect logic
* fix: filter by modality in anon models list
* fix: remove bespoke model loading logic for anon endpoint
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat(core): add MessageFormatter pipeline for extension message hooks
Introduces a new MessageFormatter singleton class (public/scripts/message-formatter.js)
that allows extensions to transform message text at well-defined stages of the
messageFormatting() pipeline, before the result reaches the DOM.
The pipeline exposes three hook stages (all before DOMPurify sanitization):
- BEFORE_REGEX -- raw Markdown, before custom regex rules
- AFTER_REGEX -- plain Markdown, after regex, before showdown conversion
- AFTER_MARKDOWN -- rendered HTML, after showdown, before sanitization (default)
There is intentionally no post-sanitize stage to prevent XSS vectors.
Extensions register hooks via getContext().messageFormatter.addHook(fn, { stage, order }).
Stage and order enums (formatting_stage, hook_order) are re-exported on the
singleton instance itself so extensions need no additional imports beyond getContext().
The formatter also exposes a .format() shim over messageFormatting() for
convenience. messageFormatting() itself gains full JSDoc documentation.
* feat(core): add pipeline documentation to MessageFormatter.format()
Adds detailed JSDoc documentation to the MessageFormatter.format() method
describing the complete 11-step message formatting pipeline, from prompt-bias
stripping through DOMPurify sanitization. Clarifies that all extension hooks
(beforeRegex, afterRegex, afterMarkdown) run before sanitization to ensure
their output is always sanitised.
* feat(core): add async detection and non-string return guards to MessageFormatter
Adds runtime and registration-time safety checks to the MessageFormatter hook system:
- Throws TypeError at registration if an async function is passed to addHook()
- Emits console warning and ignores return value if a hook returns non-string at runtime
- Detects Promise returns and includes helpful hint that hook may be async
- Updates JSDoc to clarify synchronous string return requirement and error conditions
* test(frontend): add comprehensive e2e tests for MessageFormatter
Adds full test coverage for the MessageFormatter singleton class including:
- Module exports validation (formatting_stage, hook_order enums)
- Singleton instance constant re-exports
- Registration validation (rejects non-functions, async functions, unknown stages)
- Hook execution pipeline (stage isolation, order sorting, context freezing)
- Error handling (continues on throw, warns on non-string/Promise returns)
- Stage injection
* refactor(core): rename ch_name parameter to characterName in MessageFormatter
Renames the `ch_name` parameter to `characterName` throughout MessageFormatter for improved code clarity and consistency with modern naming conventions. Updates JSDoc typedef and method signatures.
* fix: handle scoped comment macro closing tag tokenization edge case
The lexer greedily tokenizes '//' before '/', causing {{///}} to parse as {{// /}} instead of {{/ //}}. Added special case detection in MacroCstWalker to check if the comment macro's first argument starts with '/' and treat it as a closing block. Removed list/strictArgs flags from comment macro definition and added comprehensive e2e tests for scoped comment blocks.
* refactor: DRY, remove unneccessarily duplicated private extractMacroInfo
* feat: enhance world info sorting with ascending/descending modes and animation
- Add autoFocus property to popup inputs with autofocus attribute and tabIndex
- Add slide animation to setInfoBlock/clearInfoBlock with configurable animate option
- Replace simple input prompt with detailed popup for applying current sorting
- Add ascending/descending order toggle for world info entry sorting
- Add configurable step value between order assignments
- Add real-time warning when starting value is below
* fix: improve world info sorting warning to account for step value
- Update warning calculation to consider step size when detecting order collisions
- Add step input parameter to updateWarning function
- Attach input listener to step field for real-time warning updates
- Display more detailed warning message showing the calculated final order value
Temporarily commented out Filter.Pipe and Filter.EscapedPipe token handling in MacroLexer to fix issue where pipe characters in argument values (e.g., {{setvar::foo::|bar}}) were incorrectly parsed as filter operators. Added regression tests for pipe handling in argument values and skipped existing output modifier tests until filter flag (>) logic is properly implemented.
Resolves: #5618
When a textarea is removed from the DOM before the autocomplete
clone-positioning logic runs, parentElement is null and
MutationObserver.observe throws. This can happen when extensions
abort generation early (via generate_interceptor) and the textarea
is torn down before autocomplete finishes setup.
Add a null check so the observer is only attached when the parent
still exists.
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* fix mislabelled popup for "Replace existing Quick Reply Set"
it currently provides a popup asking for confirmation "Replace existing World Info" when user tries to create a new QR Set with an existing name.
Checked that it does not conflict/reuse anything from the actual world info screen.
* capitalisation
* Add message indicating that the 'Request mode reasoning' checkbox
controls whether reasoning is generated at the source, for Deepseek API.
* Added zai and moonshot to conditions for showing message indicating reasoning is enabled/disabled by 'request model reasoning' toggle..
* Added new message indicating openrouter's behaviour when 'request model reasoning' setting is disabled.
* fix: grammar
* fix: duplication for openrouter
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* update: improve fetching of selected default expression
It includes the fallback values #emoji and #none.
* update: allow expression-list to filter custom expressions
It can allow, filter out, or only include custom expressions in the result.
* update: separate getLastExpression from the slash command to use on macros
* feat: register defaultExpression macro
It will fetch the label of the currently selected global fallback expression.
* feat: register lastExpression macro
It will return the last expression used by the selected character.
* feat: register availableExpressions macro
Returns a list of all expressions provided by the Classifier API.
* update: fix macros labels
* update: normalize return label for defaultExpression macro
* Fix - Typos
* Update - Add compatibility with old macro engine
* Fix - Remove redundant structuredClone
* Update - Consider sprite folders to fetch the last expression used
* Update - Improve last message handling when name is provided
* Fix - Update description of getLastCharacterMessage
* Update - Bring back using active character as fallback for groups
Just weighted that if no name is provided, doing fallback to the active character generating prompt is more useful for groups than grabbing the expression used by another character, after randomly removing that prev commit.
* Fix personal lore stale update on rename (#5628)
* Add test for rename persona lore
Co-authored-by: Copilot <copilot@github.com>
* Fix stale update on personal lore rename
Co-authored-by: Copilot <copilot@github.com>
Given the recent work to fix#5610, this is a continuation to fix a
similiar bug in the persona lore.
* Add newline for linter check
---------
Co-authored-by: Copilot <copilot@github.com>
* feat: update links for other personas
---------
Co-authored-by: Unnatural Developer <40277404+unnaturaldeveloper@users.noreply.github.com>
Co-authored-by: Copilot <copilot@github.com>
* Add test to reproduce chat lore bug
Co-authored-by: Copilot <copilot@github.com>
Given that I wanted to reliably reproduce the bug, I created a playwright Docker container as part of this commit, along with the applicable unit test. The included docker-compose includes an environment variable that is passed for use by the frontend test harness, default to the host that the playwright and the ST instance containers are running on.
* Fix stale chat bound lore name after rename
Co-authored-by: Copilot <copilot@github.com>
Given the function renameWorldInfo and the resulting call to updateWorldInfoLinks, this fix ensures that if the world_info key in the chat_metadata is still set to the old name, it will be updated to the name
Resolves: #5608
* Start to separate test runner from branch
Given the bug fix for #5608 should be separate from the test runner
compose file, this commit removes the file from the branch associated
with the bug fix.
* Fix frontend test setup to check for login page
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Make change to eslint configuration
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Given the updates to the setup of frontend-utils, configure eslint to
recognize browser and jquery specific globals
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat: add allowBaseName option to getUniqueName utility function
* feat: simplify getUniqueName by removing allowBaseName option and changing default startIndex to 0
* fix: remove the cloned directory if it contains no manifest
* fix: apply feature flag guard to user extension data hosting
* fix: disable inactive controls when feature flag is off
* fix: change response status to 404
* feat: add user account version to session cookie
Co-authored-by: Copilot <copilot@github.com>
* feat: include user handle in account version hash calculation
* feat: refactor recovery code generation to use a dedicated function
* fix: don't overwrite current session version if updating another user
Co-authored-by: Copilot <copilot@github.com>
* fix: reset session version instead of nullifying the entire session
* fix: short circuit and clear cookie on request invalidation
Co-authored-by: Copilot <copilot@github.com>
* fix: update account version on recovery
---------
Co-authored-by: Copilot <copilot@github.com>
* Update - Turn expression-set-fallback into expression-fallback
Make the extension a getter and setter instead of a setter only.
* Update - Rewrite the help string and add usage examples
* Fix - Remove the alias
* Feat - Add expression-set-fallback slash command
* Fix ESLint
* Fix - Use proper name convention for slash command method
* Fix - Change misleading expression-set-fallback help string label
* Fix - Use normal description for expression label argument
* Update - Make expression-set-fallback case unsensitive
Also fixed array creation by removing the spread syntax and added warning.
* pass jsonSchema options through sendStreamingRequest in Generate
* translate json_schema to response_format for CUSTOM chat completion source
* pass jsonSchema through generateGroupWrapper params in group chat generation
* feat: enhance asset management with extension categories
Co-authored-by: Copilot <copilot@github.com>
* fix: enhance extension name validation in server endpoints
* feat: display extension author in the extensions list
* fix: unify server error response format
Co-authored-by: Copilot <copilot@github.com>
* feat: add splash on installing third-party for the first time
* fix: add URL format validation, unify validation error messages
Co-authored-by: Copilot <copilot@github.com>
* fix: apply object freeze to EMPTY_AUTHOR value
Co-authored-by: Copilot <copilot@github.com>
* fix: typecheck extensionName in API requests
Co-authored-by: Copilot <copilot@github.com>
* feat: add feature flag guard to extensions endpoints
Co-authored-by: Copilot <copilot@github.com>
* fix: parse URL before checking
Co-authored-by: Copilot <copilot@github.com>
* fix: use case insensitive regex check
* fix: make debug log more useful
Co-authored-by: Copilot <copilot@github.com>
* fix: add pre-validation of URL format and protocol
Co-authored-by: Copilot <copilot@github.com>
* fix: leaner installation success toast
* fix: settings data loss when extensions are disabled
* fix: don't try to auto-focus elements that don't exist
Co-authored-by: Copilot <copilot@github.com>
* fix: set Popup.defaultResult to negative
Co-authored-by: Copilot <copilot@github.com>
* revert: restore undefined default result
---------
Co-authored-by: Copilot <copilot@github.com>
* fix: sanitize character filenames on V2 JSON import and harden getPngName
- Add missing sanitize() call in importFromJson V2 spec branch to match all other import paths
- Sanitize data.name before readFromV2() so the name field sync happens automatically
- Add sanitize() as defense-in-depth inside getPngName() to catch future oversights
- Refactor getPngName() to use getUniqueName() utility for consistent name generation
* fix: sanitize data.name before readFromV2 in importFromPng and importFromCharX
Same bug as importFromJson: readFromV2() overwrites the top-level name
with the unsanitized data.name, undoing any prior sanitize() call.
Fix by sanitizing data.name before readFromV2 so the sync preserves it.
* fix: sanitize top-level name field in JSON and CharX import paths
* fix: incorrect path rejection in isPathUnderParent
* fix: increase maxTries in getPngName
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Improve NanoGPT Model List
* Update token multiplier condition to !== 1 to support showing discounts
* Add Model Sorting
* rework sorting to be more compact
* feat: combine CC model sorting/grouping settings
Co-authored-by: Copilot <copilot@github.com>
* fix: adjust migration logic
Co-authored-by: Copilot <copilot@github.com>
* feat: implement grouping for Chutes
* fix: apply review suggestions
* fix: call reconnect instead of direct status check
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Copilot <copilot@github.com>
* feat: add gemma 4 for AI studio
* fix: update max context return value for gemma-3n-e4b-it model
* refactor: iterate array of [regex, number]
* gemma4: enable tool calling and sysprompt
Co-authored-by: Copilot <copilot@github.com>
---------
Co-authored-by: Copilot <copilot@github.com>
* added macro processing to caption ext
added
`prompt = substituteParamsExtended(prompt);`
to the captionmultimodal function
(so it can use macros and stuff)
* caption ext updated from old substituteparams
* removed comment
This fixes the following bug in Firefox Mobile on Android:
**Steps to reproduce:**
1. Swipe a word into the chat input edit field in Firefox Mobile on Android, for examples "Test".
2. In GBoard (default Android keyboard), tap on a different suggestion, for examples "Rest".
**Expected behavior:** The word "Test" is replaced with "Rest".
**Actual behavior:** The word becomes "TestRest".
I confirmed with bisecting that the commit f897a4ab1a introduced the issue.
This change fixes the issue by disabling the layout hack while editing text.
Disabling the layout hack is limited to Firefox Mobile because
* I could not reproduce the bug in Chrome on Android
* This way, if it causes a new bug, only Firefox Mobile users are affected
* feat: add MiniMax as a chat completion provider
Add MiniMax (https://www.minimax.io) as a first-class chat completion
provider. MiniMax already has TTS integration in SillyTavern; this
extends support to LLM chat completions via their OpenAI-compatible API.
Supported models:
- MiniMax-M2.5 (default) — 204K context
- MiniMax-M2.5-highspeed — same capability, faster inference
Key implementation details:
- Reuses existing SECRET_KEYS.MINIMAX (shared with TTS)
- API endpoint: https://api.minimax.io/v1
- Temperature clamped to (0.0, 1.0] as required by MiniMax API
- Returns hardcoded model list since MiniMax doesn't expose /v1/models
- Full UI integration: model selector, sampler parameters, streaming
Co-Authored-By: octo-patch <octo-patch@users.noreply.github.com>
* feat: upgrade MiniMax default model to M2.7
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model
- Keep all previous models as alternatives
* feat: independent request function, vision support, temp clamping for MiniMax
- Extract sendMinimaxRequest() following Chutes pattern (PR #4844)
with function calling and JSON Schema structured output support
- Clamp temperature to (0.01, 1.0] on backend; limit frontend UI max to 1.0
- Enable image inlining for MiniMax M2.7 model
- Add MiniMax to slash-commands model selector and tokenizer mapping
- Add minimax_model to default preset
* feat: add VLM-based vision support for MiniMax M2.7
M2.7 does not natively accept image input. When images are detected
in messages, pre-process them via the MiniMax VLM endpoint
(/v1/coding_plan/vlm) to convert images to text descriptions before
sending to the chat completions API. Uses the same API key.
* feat: add M2-her model to MiniMax provider
M2-her is MiniMax's dialogue/roleplay-optimized model with 64K context
and 2048 max completion tokens. Text-only (no vision).
* feat: add MiniMax China endpoint (minimaxi.com) support
Add endpoint selector (Global/China) for MiniMax, mirroring the
SiliconFlow pattern. Users can now choose between api.minimax.io
(international) and api.minimaxi.com (China domestic).
* fix: merge consecutive same-role messages for MiniMax
MiniMax API rejects consecutive messages with the same role with
error 'invalid chat setting (2013)'. Merge them before sending.
* review: address PR feedback on MiniMax provider
Backend (src/endpoints/backends/chat-completions.js):
- Drop the entire MiniMax VLM image-preprocessing path; vision is no
longer advertised for this provider, so M2.7 messages now go straight
to /chat/completions without a separate VLM round-trip.
- Drop the json_schema -> response_format mapping (MiniMax does not
document structured-output support; relying on it was speculative).
- Drop the backend temperature clamp; the same clamp now lives in the
frontend so the wire payload matches what the user sees.
- Drop the MINIMAX branch in /status that returned a hard-coded model
list; the frontend hardcodes the same list and bypasses /status via
noValidateSources, so the round-trip was wasted.
- Add a streaming Transform + non-streaming helper that move
<think>...</think> blocks from delta.content / message.content to
reasoning_content. MiniMax M2.x emit chain-of-thought inline in
content; without this transform the raw <think> tags leak into the
rendered chat. Includes a state machine that holds back partial
marker bytes so a marker split across SSE chunks is still detected.
Frontend:
- public/scripts/openai.js: add MINIMAX to noValidateSources so the key
is accepted without a /models call; remove the dead saveModelList
branch; clamp temperature to (0.0, 1.0] in createGenerationParameters.
- public/scripts/reasoning.js: add MINIMAX to the non-streaming
reasoning_content extraction case (the backend transform now produces
this field for MiniMax responses).
- public/scripts/slash-commands.js: add MINIMAX to the /api enum and
add a MiniMax case to /api-url so users can switch endpoint by
command.
- public/scripts/custom-request.js: pass minimax_endpoint through the
override-payload merge alongside the other per-source endpoint fields.
- public/scripts/tokenizers.js: stop returning openai_model (which was
always a MiniMax model id and thus an unknown tokenizer); fall back
to gpt-3.5-turbo for a coarse but functional estimate.
- public/scripts/tool-calling.js: add MINIMAX to supportedSources so
function-calling settings are exposed.
- public/index.html: drop the "-- Connect to the API --" placeholder
option from the model select (the model list is hardcoded and always
populated); remove minimax from the vision data-source attributes
on the inline-media controls.
- public/img/minimax.svg: replace the multicolor brand SVG with a
single-color currentColor version that matches the other provider
icons in the connect panel.
* review: drop backend <think> parsing, defer to frontend
Per reviewer feedback: SillyTavern's reasoningHandler / reasoning_auto_parse
setting already extracts <think>...</think> blocks on the client side, so the
backend doesn't need to rewrite MiniMax responses. Removes the SSE Transform,
the non-streaming helper, and the corresponding case in reasoning.js.
* fix: remove isImageInliningSupported declaration for MINIMAX
* fix: remove MINIMAX from stream reasoning parsing
* fix: add to autoconnect logic
* fix: add missing MINIMAX models from docs
* fix: freq. and pres. pen aren't supported for MINIMAX
* fix: use clamp function for adjusting temperature
* fix: pass minimax_endpoint from connection profile to ChatCompletionService
* fix: update supported APIs in slash command documentation
* fix: replace bespoke merge with standard MERGE_TOOLS processing
* fix: add data-i18n attributes for headers
---------
Co-authored-by: octo-patch <octo-patch@users.noreply.github.com>
Co-authored-by: octo-patch <octo-patch@github.com>
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Display OpenRouter credit balance in UI
Adds a "View Remaining Credits" click handler that fetches the
current balance from the OpenRouter /credits endpoint via a new
server-side /api/openrouter/credits route, and renders it next
to the link. The anchor still points at openrouter.ai/account
so middle-click / right-click "open in new tab" keeps working.
* Return 500 on OpenRouter credits failure
* Reduce to two decimals
* Update view credits URL
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat: add slug parameter to action-loader for programmatic identification
Add optional `slug` parameter to ActionLoaderHandle for easier identification via code or CSS. Update all loader.show() calls across the codebase to include descriptive slugs ('app-init', 'chat-rename', 'chat-delete', 'bulk-delete', 'chat-load', 'image-generation', 'legacy-loader'). Add data attributes (data-slug, data-loader-id, data-blocking) to toast content div. Expose slug via getter and make id private with getter.
* Apply suggestions from code review
Fix slug jsdoc wording
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix: Add identifier to second loader in img gen
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* fix (vectors): Fixed Vectorize All progress report and ETA issues
* fix (vectors): Added strip reasoning block function for extras/WebLLM summaries
* feat(vectors): Retry failed summaries with configurable attempts
* feat(vectors): Skip summarization for short messages
* feat(vectors): Skip failed messages during Vectorize All instead of aborting all
Prevents the "Vectorize All" process from stopping on single-message
errors. Failed items are now skipped and reported at the end of the
session rather than aborting the entire sync.
Summarization: Implements per-message retries; failures use the original
text as a fallback or mark for skipping.
Vector Insertion: Differentiates fatal configuration errors (abort) from
transient batch failures (skip and notify).
* Resolved: 'account_id_missing' is missing
* Resolved: Refactored out summarizeSkipOnFailure() functionality into summarize() via options parameter
* Fix eslint and type checks
* feat(vectors): add types to maps and sets, improve summarize function options
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Add persona CRUD slash commands with enhanced utilities
- Add `/persona-create`, `/persona-update`, `/persona-delete`, `/persona-duplicate`, and `/persona-get` slash commands for programmatic persona management
- Move `persona_description_positions` enum from power-user.js to personas.js for better encapsulation
- Add position and role parsing utilities (`parsePersonaPosition`, `parsePersonaRole`) with name-to-value mapping
- Extend `initPersona()` to accept optional position, depth, role, and lorebook parameters
- Refactor `deleteUserAvatar()` to delegate to new `deletePersona
* Add NaN validation for descriptionDepth parameter in createPersonaCallback
- Add isNaN() check for depth parameter after Number() conversion
- Display warning toast when invalid depth value is provided
- Fall back to DEFAULT_DEPTH when depth is NaN
- Change depth from const to let to allow reassignment after validation
* Refactor persona lookup to support avatar key targeting and fix enum provider currying
- Refactor `autoSelectPersona()` to accept optional `personaKey` parameter for targeting specific persona when multiple share the same name
- Replace manual persona lookup loops with `findPersona()` helper calls in `autoSelectPersona()` and `setNameCallback()`
- Update `setNameCallback()` to pass both persona name and avatar key to `autoSelectPersona()` for precise targeting
- Refactor `commonEnumProviders.personas()`
Extend click-to-edit functionality to reasoning blocks in addition to message text. When clicking on a reasoning block, automatically focus the reasoning textarea after entering edit mode.
* fix: prevent event bubbling on show more messages button
Replace mouseup/touchend with click event and add stopPropagation/preventDefault to prevent unintended event bubbling when loading more messages.
* Add hover style to "show more messages"
* add button role to show_more_messages
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* refactor: replace custom generation indicator with action-loader
Remove custom generation tracking (activeGenerations counter, generationToast) and replace with action-loader's non-blocking stoppable toast. Import loader from action-loader.js and use loader.show() with onStop callback in generatePicture() and generateMediaSwipe(). Remove updateGenerationIndicator(), startGenerationTracking(), and endGenerationTracking() functions. Remove manual stop button show/hide logic and generation counter updates
* Remove legacy stop button, add sentinel handler value
* fix: reassign loaderHandle in generateMediaSwipe
* feat: add data attributes to action-loader toast for easier selection
Add loaderId, title, and blocking data attributes to toast content div to enable programmatic identification and filtering of active loader toasts
* Revert "feat: add data attributes to action-loader toast for easier selection"
This reverts commit e8da27b4c9.
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* fix: enhance URL validation for Z.AI image generation and handle potential delays
Fixes#5480
* fix: retry 404 in a loop
* fix: handle Z.AI image and video unavailability with appropriate warnings and responses
* feat: add bulk extension field updates with UNSET_VALUE sentinel for key deletion
- Add `UNSET_VALUE` sentinel constant to signal complete field removal from character cards
- Add `writeExtensionFieldBulk()` function to update extension fields across multiple characters in a single API call
- Add `deleteValueByPath()` utility function to remove nested object keys by dot-path
- Update `writeExtensionField()` to support `UNSET_VALUE` for deleting extension keys
- Extend `/api/characters/merge-attributes
* Revert package-lock.json changes
* Allow null values in merge-attributes filter path validation
Change filter.path existence check to only skip on undefined, not null. This allows merging attributes when the existing value is explicitly null, treating null as a valid value rather than absence of a value.
* fix: share forbiddenRegExp between modules
* feat: add writeExtensionFieldBulk and UNSET_VALUE constant to getContext
* Update src/endpoints/characters.js
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: validate for .png extension
* Update public/scripts/extensions.js
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* refactor: extract shouldSkip logic as a function param to avoid double parsing
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
In group chats, only include reasoning from the currently generating character instead of all group members. This prevents reasoning from other characters being injected into the prompt context when generating responses.
- Filter reasoning in coreChat loop based on message author matching name2
- Filter reasoning in setOpenAIMessages based on message author matching name2
- Add isOtherGroupMember check before adding reasoning to messages
Raises the maximum allowed Top K sampling parameter from 200 to 500 in both the range slider and number input controls to support higher token selection limits.
* Fix internationalization issues
* fix(i18n): update world creation key and zh-cn translations
Changes the i18n key for the world editor's "New" button to "Create" to
avoid conflict with listing filters. Updates the Chinese translation
for the "New" key to "最新" (Latest).
* fix(i18n): correct translation key for world creation button
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Add range and silent parameters to /persona-sync command with optional confirmation suppression
- Add optional start/end range parameters to syncUserNameToPersona() function
- Add silent parameter to suppress confirmation popup when needed
- Update /persona-sync slash command to accept range argument (index or range string) and named silent argument
- Parse range using stringToRange() utility, default to full chat if not provided
- Update confirmation message to reflect whether syncing all messages or specified
* Add `from` named argument to /persona-sync command for filtering by persona name
- Add `from` named argument to filter messages by persona name (case-insensitive)
- Rename `silent` argument to `quiet` with inverted default (true) for consistency
- Add userMessageNamesEnumProvider() to provide autocomplete for existing user message names in chat
- Update syncUserNameToPersona() to accept nameFilter parameter and filter messages accordingly
- Update confirmation message to reflect name filtering when
* Add async/await wrapper to sync_name_button click handler for proper promise handling
Function now has arguments, so using just the function as the event is shown as wrong usage
* Post-merge imports fix
* Use canonical command name in examples
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* fix: extensions OpenRouter model lists
* fix: update JSDoc for optional mapping function parameter in fetchModelsByModality
* fix: update JSDoc to clarify return type of fetchModelsByModality function
* fix: encode output modality in fetchModelsByModality API request
* enable interleaved tool reasoning for custom OpenAI-compat endpoints
Add chat_completion_sources.CUSTOM to interleaved_reasoning_providers so
that local OpenAI-compatible endpoints (e.g. KoboldCPP in Chat Completions
mode) can forward reasoning context in tool-call chains when the user has
configured Interleaved Thinking.
Also expose the Interleaved Thinking UI control for the Custom source so
users can actually opt in — previously the dropdown was hidden behind a
data-source="openrouter" guard.
The custom streaming path already correctly accumulates delta.reasoning_content
from streaming chunks; this change only removes the provider gate that was
silently discarding that data before it reached the API payload.
* don't override invocation reasoning with prior-turn assistant reasoning
When an invocation already has its own reasoning captured at execution
time, preserve it instead of replacing it with previousAssistantReasoning
from the backward scan. The override was correct when invocations never
carried their own reasoning, but now that the custom/openrouter paths
capture per-invocation reasoning, the unconditional replacement caused
all tool calls in a chain to receive the same stale reasoning from an
earlier unrelated assistant turn.
Fall back to previousAssistantReasoning only when clone.reasoning is empty.
* Add StreamingDisplay class for live LLM generation output with floating toast panel
- Add StreamingDisplay class to show streaming reasoning and content in a floating toast panel
- Extract createModelIcon() helper from insertSVGIcon() for reusable API/model icon creation
- StreamingDisplay automatically appends inside topmost open dialog (same pattern as fixToastrForDialogs)
- Add CSS with fade-in animation, pulsating activity indicator, and separate reasoning/content sections
- Support optional model icon in header
* Add ConnectionManagerRequestService.getProfileIcon() method for retrieving profile API icons
- Add static getProfileIcon() method to ConnectionManagerRequestService
- Returns HTMLImageElement created via createModelIcon() for a given profile's API/model
- Accepts optional profileId parameter, defaults to currently selected profile
- Returns null if Connection Manager is disabled, profile not found, or profile has no API
- Import createModelIcon from script.js
* Use animation_duration directly in hide() and CSS transition instead of constant
- Remove ANIMATION_DURATION_MS constant and use animation_duration directly in hide() method
- Replace hardcoded 0.3s CSS transitions with CSS variable var(--animation-duration, 125ms)
- Read animation_duration value inline in hide() for accurate timing
* Add /genstream slash command with live streaming display and reasoning support
- Add /genstream slash command that generates text via Connection Manager with live streaming UI
- Add formatReasoning() helper function (inverse of parseReasoningFromString) to format reasoning/content into template-wrapped strings
- Add connectionProfiles enum provider for profile selection in slash commands
- StreamingDisplay: add delay parameter to hide() method (default 1000ms) to show final result before dismiss
* Add /reasoning-format slash command to format reasoning and content into template-wrapped strings
- Add /reasoning-format (alias: /format-reasoning) slash command that wraps reasoning/content using Reasoning Formatting settings
- Accept required 'reasoning' named argument and optional unnamed 'content' argument
- Validate that prefix/suffix are configured before formatting
- Return formatted string via formatReasoning() helper for use with /reasoning-parse
- Show warning toasts if prefix/suffix missing
* Rename /genstream command to /profile-genstream and move to appropriate module
* Apply messageFormatting to StreamingDisplay reasoning and content text for proper rendering
- Import messageFormatting from script.js
- Replace textContent with innerHTML using messageFormatting() in updateReasoning() and updateText()
- Pass isSystem=true for reasoning, isSystem=false for content to match formatting expectations
- Update css to utilize pre-formatted paragraphs correctly
* Strip auto-added quotes from <q> tags in StreamingDisplay and add 'mes_text' class for consistent chat message formatting
- Add CSS rules to remove browser-default quotes from <q> tags in reasoning and content sections
- Add 'mes_text' class to textContent div to match chat message formatting behavior
- Prevents double quotes when messageFormatting already adds them via <q> tags
* Add minimize/close buttons and complete state to StreamingDisplay with configurable auto-hide
- Add minimize button to collapse/restore content sections while keeping header visible
- Add close button to manually dismiss display (generation continues in background)
- Replace CSS pseudo-element with explicit LED indicator element for better state control
- Add complete() method to mark generation done: changes LED from pulsing orange to solid green
- Add configurable auto-hide delay after completion
* Add stop button to StreamingDisplay with abort support and onStop/onComplete closures for /profile-genstream
- Add stop button to StreamingDisplay when onStop handler is provided
- Add markStopped() method with solid red LED state indicator
- Add AbortController integration to /profile-genstream for request cancellation
- Add onStop and onComplete closure arguments to /profile-genstream command
- Update complete() method signature to use options object with label and delay
- Disable stop button immediately
* Position StreamingDisplay above bottom form block using CSS variable with fallback
- Change bottom positioning from fixed 20px to dynamic calculation
- Use max() to position above --bottomFormBlockSize + 5px or minimum 20px
- Ensures StreamingDisplay doesn't overlap with bottom UI elements
* Rename /profile-genstream arguments for clarity: label→generating, completedLabel→completed, hideDelay→delay
- Rename `label` argument to `generating` to better reflect its purpose as the in-progress state label
- Rename `completedLabel` to `completed` for consistency and brevity
- Rename `hideDelay` to `delay` for simpler naming
- Update all internal references and variable names to match new argument names
- Update argument descriptions and default values accordingly
* Remove variable resolution from /profile-genstream arguments: system, length, and delay
- Remove ARGUMENT_TYPE.VARIABLE_NAME from typeList for system, length, and delay arguments
- Replace resolveVariable() calls with direct argument access for system, length, and delay
- Simplify type checking to use typeof directly on args properties
- Maintain existing default values and validation logic
* Add warning toast and early return when connection profile not found in /profile-genstream
- Display toastr warning when fuzzy search fails to find matching profile
- Return empty string to prevent execution with invalid profile
- Improves user feedback for incorrect profile names or IDs
* Extract buildResultText() helper in /profile-genstream to return partial results when stopped
- Add buildResultText() helper function to centralize result formatting logic
- Return partial generated text when user stops generation instead of empty string
- Reuse buildResultText() for both stopped and completed states
- Maintains consistent reasoning formatting in both cases
* fix lint
* Update documentation to reflect argument name change from hideDelay to delay
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat: emit PERSONA_CREATED event when duplicating a persona
Adds PERSONA_CREATED event emission in duplicatePersona() to notify listeners when a persona is duplicated. Includes the new avatarId, name, and duplicatedFromAvatarId in the event payload.
* fix: event data and execution order
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Add 'clean' extension hook support with optional cleanup on delete
- Add hasExtensionHook() helper to check if an extension defines a specific manifest hook
- Add 'clean' hook type to callExtensionHook() JSDoc
- Add clean button to extension UI when 'clean' hook is present
- Add onCleanClick() handler to run clean hook with confirmation
- Add cleanExtension() function to execute clean hook and reload page
- Modify deleteExtension() to optionally run clean hook before deletion
- Show cleanup checkbox on extension delete popup
* fix lint
Remove unused `callGenericPopup` import from extensions.js
* Force save settings before page reload in extension clean and delete operations
Add explicit saveSettings() calls in cleanExtension() and deleteExtension() to prevent race conditions where clean/delete hooks might update settings that get lost during the subsequent page reload.
* Remove admin permission check from extension clean operation
The clean hook is extension-defined and may not require admin privileges. Permission checks should be handled by the extension's clean hook implementation if needed, rather than enforcing a blanket restriction at the UI level.
* fix: show clean button for built-ins
* Update hasExtensionHook to support built-in extensions
* Revert "Update hasExtensionHook to support built-in extensions"
This reverts commit 31be55ea66.
* Revert "fix: show clean button for built-ins"
This reverts commit 5f86fec70c.
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* allow grammar to keep place during continue
* lint
* fix: require kai flag for grammar to be set
* fix: don't retain if grammar is empty
* fix: default to undefined if not retain
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Adds optional `disabled` boolean property to PopupInputConfiguration JSDoc and implements it across all input types (checkbox, text, textarea, number). When set to true, the input element will be rendered in a disabled state.
Returns a structuredClone of the loaded manifest for the given extension name.
Accepts either the short name or full internal key (third-party/...).
Returns null if the extension is not registered.
* feat: add /regex-state command to check script enabled status
Adds a new slash command that returns 'on' or 'off' to indicate whether a regex script is currently enabled or disabled.
* refactor: change /regex-state return values from 'on'/'off' to 'true'/'false'
Updates the /regex-state slash command to return boolean string values ('true'/'false') instead of ('on'/'off') for better consistency with standard boolean conventions.
* fix: include model field in sd.cpp SDAPI requests and preserve URL path
The sd.cpp integration overwrites the URL pathname when constructing
requests, which breaks proxy servers like llama-swap that use path-based
routing (e.g. /upstream/model-name). Additionally, the model field was
never included in SDAPI requests, which is required by llama-swap to
route requests to the correct backend.
Changes:
- Server: Append to URL pathname instead of overwriting (same pattern as #5178)
- Server: Pass model field through to sd-server payload
- Client: Add model name text input for sd.cpp source settings
- Client: Send model name in generate request payload
* fix: fetch models from server and populate standard Model dropdown
Instead of a separate text input for the model name, fetch the model
list from the sd.cpp server's /v1/models endpoint and populate the
standard Model dropdown. This provides a seamless experience where
users just pick a model from the dropdown like any other source.
Works with both standalone sd-server and proxy servers like llama-swap
that expose multiple models via the OpenAI-compatible models endpoint.
* fix: don't send clip_skip=1 to sd.cpp, it produces blank images
sd-server generates blank white images when clip_skip is set to 1.
Since clip_skip=1 means 'use all CLIP layers' (the default behavior),
only send the parameter when it's > 1.
* Fix eslint
* Replace string appends with urlJoin
* fix: convert URL strings to URL objects in sdcpp routes
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Extends the #logDeprecated helper to accept and log the arguments passed to deprecated methods, providing better debugging context for migration. Updates all deprecated method calls (get, has, registerMacro, unregisterMacro) to forward their arguments to the deprecation logger.
Prevents invalid CSS by skipping rules containing `::` (pseudo-elements like `::before`, `::after`, `::-webkit-scrollbar`) when converting `:hover` to `:focus-visible`, as pseudo-elements cannot receive focus.
Previously only exact 'en' was accepted as fallback when a language wasn't found. Now accepts any English variant (en-US, en-AU, etc.) to prevent spurious warnings for valid English locales.
* feat: add Workers AI text embeddings and multimodal captioning
Extends the Cloudflare Workers AI integration to the vectors and
caption extensions.
Embeddings: adds workers_ai source to the vectors extension using the
OpenAI-compatible /v1/embeddings endpoint, with dynamic model listing
from the Cloudflare model search API.
Captioning: adds workers_ai as a multimodal caption API with dynamic
vision model discovery via the multimodal-models endpoint.
* Add logo svg
* Refactor caption dropdown population
* Fix order of sources
* feat: add error handling for missing Workers AI account ID
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* refactor(tts): remove redundant 4-space codeblock filter
- Deleted the regex that removed lines starting with four spaces.
- Original intent was to strip "indented code blocks" (Markdown legacy syntax).
- In practice, SillyTavern already handles explicit code fences (```...``` and ~~~...~~~).
- Indented code blocks are rarely used and the regex caused unnecessary text loss in normal messages.
- Simplifies codeblock skipping logic and avoids accidental removal of valid content.
* Remove commented out code
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat: add entry preview to world info deletion confirmation dialog
Displays entry comment or first two lines of content in the deletion confirmation popup to help users verify they're deleting the correct entry.
* fix: sanitize world info entry preview text in deletion confirmation dialog
Adds DOMPurify sanitization to the entry preview text displayed in the deletion confirmation popup to prevent potential XSS vulnerabilities from unsanitized user content.
* DOMPurify -> escapeHtml
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat: add Cloudflare Workers AI provider
Adds support for Cloudflare Workers AI using its OpenAI-compatible API.
Workers AI-specific stuff includes:
- Model list fetching and capabilities detection
- Tokenizer auto-detection for typical hosted model families
- Streaming not supported when using structured output
Closes#5305
* Make the entire header clickable
* Add missing samplers
* Fix non-streaming reasoning parsing
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Add unit tests for prompt-converters.js
* fix: add type annotation for prompt-converters module
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Skip TTS for voices explicitly set to disabled (fixes#4970)
* Always show disabled message in commands and fix restoring voice map UI
* Always show a message on manual TTS trigger
* Fix null current job on disabled
* Adjust type annotation
* Force update worker when disabled play is attempted
* Treat audio control queue as manual
* Update TTS message processing to include manual flag
* Don't show toast if was already shown by manual playback
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Use custom init script instead of postinstall
* Revert changes to start scripts in src\electron
* Add global data to content manager
* Add migration for public overrides and user.css location update
* Update npm publish workflow to use 'omit=dev' flag in npm ci commands
* Rename user.css readme file
* Fix indentation in userCssMiddleware function
* Add directory creation for content target
* Restore template compile location
* Move stylesheet up in index.json
* Use path.resolve for user.css file path in userCssMiddleware
* Correct capitalization in "Not Found" error page title and heading
* Remove init run from startup scripts
* Simplify user CSS file path resolution
* Update userCssMiddleware comment
* Use custom init script instead of postinstall
* Revert changes to start scripts in src\electron
* feat: add --ignore-scripts flag to npm install commands in batch and shell scripts
* feat: add --ignore-scripts flag to npm ci in Dockerfile
* fix: require long press to open swipe picker on phones
* fix: clarify parameter description in assignLorebookToChat function
* fix: update event parameter type in onSwipeCounterClick to include TouchEvent
* fix: update event parameter types in onSwipeCounterClick and addLongPressEvent
* fix: return Error objects from invokeFunctionTool and create error invocations
invokeFunctionTool previously called .toString() on caught errors,
converting them to plain strings. This made the instanceof Error
check in invokeFunctionTools dead code.
Changes:
- Return Error objects directly from invokeFunctionTool
- Create error invocations with error: true flag when tools fail
- Record failed stealth tools in stealthCalls
- Preserve signature/reasoning on error invocations
- Add error field to ToolInvocation typedef
* fix: use Error.toString to avoid behavioral changes
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat(secrets): update readSecret function to accept optional secret ID
* add secret_id to ConnectionManagerRequestService payload
* fix: pass secret_id for Text Completion types
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
The delete handler had a missing `return` before `sendStatus(400)`,
causing execution to fall through to `sendStatus(200)`, a double-send
that triggers ERR_HTTP_HEADERS_SENT, which the catch block then
compounds by attempting a third `sendStatus(500)`.
Both the delete and download handlers used callback-based `fs.unlink()`
without awaiting completion. In the download handler, this caused a race
with `createWriteStream({ flags: 'wx' })` (which fails if the file
still exists). In both handlers, `throw err` inside the callback was an
unhandled exception that could never be caught by the outer try/catch.
Replace callback-based `fs.unlink()` with `await fs.promises.unlink()`
and add missing `return` statements to prevent response cascades.
* fix: conditionally include secrets in user data backup
* feat: add full data backup toggle
* 418 -> 403
I'm not a teapot
* Distinguish fails from disabled
* feat(ui): add popup to jump to a specific swipe
Adds a new "Jump to swipe history" button to message actions and makes
the swipe counter clickable on the latest message. This opens a
searchable popup allowing users to quickly find and jump to a
specific alternate swipe without having to click through them
sequentially.
- Adds a searchable swipe picker popup menu
- Makes the swipe counter interactive when multiple swipes exist
- Adds a dedicated swipe picker button to message controls
* fix(ui): hide swipe picker when there are no swipes
Ensures the newly added swipe picker button is only shown when a
message has multiple swipes available. It explicitly hides the
button for non-swipeable messages or messages with a single swipe.
* feat(ui): redesign swipe picker with direct id input
Replace text-based search with a numeric input for direct swipe navigation.
Update popup layout with a sticky header and improved scrolling behavior.
Sync input value with the currently selected swipe in the list.
Refactor styling to align with chat selection components.
* feat(ui): allow branching from specific swipes via picker
- Enable swipe picker for historical messages to inspect alternate swipes
- Add branch button to picker entries to create new chats from specific swipes
- Update saveChat and createBranch to accept chat snapshots
- Restrict swipe jumping to the active message only
* refactor(logic): consolidate swipe sync logic and simplify helpers
Update `syncSwipeToMes` to accept a target message object, enabling its
use in the bookmarks module and removing the duplicate
`applySwipeToSnapshot` function.
Also simplify `canOpenSwipePickerForMessage` and
`canJumpToSwipeForMessage` signatures by removing the redundant message
parameter.
* refactor(a11y): support dynamic roles via classes
Introduce a managed role system in the accessibility script to handle
elements that dynamically gain or lose interactive states. The mutation
observer now watches for class attribute changes and automatically
applies or clears roles (e.g., `role="button"`) using active selectors.
Updated the swipe counter to rely on this centralized system by toggling
an `.interactable` class instead of manually modifying tabindex and role
attributes. Removed the redundant 'Enter' keydown handler for the swipe
counter to prevent duplicate trigger events.
* fix(ui): compute missing token counts in swipe picker
Update renderSwipeList to asynchronously calculate token counts when
missing from swipe metadata. Introduce SWIPE_SOURCE.SWIPE_PICKER to
correctly identify swipes triggered from the picker and bypass
generation checks.
* feat(ui): enable deleting specific swipes via swipe picker
- Adds a delete button to swipe picker entries, allowing removal of specific message versions.
- Refactors deletion logic to handle removing non-current swipes without triggering animations and correctly updates indices.
- Includes confirmation dialogs and improves input focus behavior.
* refactor:Delete process inline to button click processor
* feat: universal swipe inspection and picker improvements
- Permit opening the swipe browser on any chat entry to review past generations.
- Parallelize the retrieval of token statistics to speed up list rendering.
- Format message metrics (length and tokens) into a single, concise string.
- Update the `getBranchChatSnapshot` API to accept an options object.
- Register swipe list items as interactable elements for keyboard control.
- Apply styling to prevent text highlighting on picker entries.
* fix:remove unused CSS
* fix: fix disabled styling for swipe delete button
Remove tooltips and prevent hover animations or glow effects when the
delete button is disabled in the swipe picker. Update CSS to enforce
default cursor and fixed opacity on hover for the disabled state.
* remove: Unused CSS
* Extract swipe-picker.js module
* Revert to manual ARIA role management
* Avoid scrollIntoView and scroll on open
* Fix keyboard interaction in past chats menu
* Fix a11y attribute
* fix: call refreshSwipeButtons when deleting not selected swipe
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat: add finalizeIntermediaryMessage for streaming tool call chains
Add a lighter finalization method on StreamingProcessor that runs
before tool invocation. This ensures CHARACTER_MESSAGE_RENDERED is
emitted for streamed text messages before the tool call chain
continues, allowing extensions (TTS, image forwarding, etc.) to
process intermediary messages.
finalizeIntermediaryMessage performs essential processing:
- Code block styling (addCopyToCodeBlocks)
- Reasoning handler finalization
- Logprobs saving
- Image attachment processing
- Reasoning signature storage
- MESSAGE_RECEIVED and CHARACTER_MESSAGE_RENDERED events
Without the heavier onFinishStreaming operations:
- UI unlock (markUIGenStopped)
- Auto-swipe
- Sound playback
- Chat saving
- Swipe counter update
* fix: return Error objects from invokeFunctionTool and create error invocations
invokeFunctionTool previously called .toString() on caught errors,
converting them to plain strings. This made the 'instanceof Error'
check in invokeFunctionTools dead code - errors silently became
successful invocations, showToolCallError never fired, and the
result.errors array was always empty.
Changes:
- Return Error objects directly from invokeFunctionTool
- Create error invocations with error: true flag when tools fail
- Add error field to ToolInvocation typedef
* fix: record failed stealth tools in stealthCalls and preserve signature/reasoning on error invocations
When a stealth tool errors, its name was not added to stealthCalls, causing
shouldStopGeneration to evaluate as false. This led to an incorrect recursive
Generate('normal') call instead of stopping generation as the stealth tool
contract requires ('no follow-up generation').
Also preserve toolCall.signature and reasoningText on error invocations to
match the success path, preventing Gemini/OpenRouter multi-turn tool context
from breaking when a tool call fails.
* Clarify method comments
* fix: initialize error property in ToolInvocation to false
* Apply review suggestions
* Make options object required
* fix: remove unnecessary return statement in updateSwipeCounter method
* refactor: split tool call error handling into separate PR (#5351)
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* renaming a lorebook prompts to update existing links
* used suggested api and logic
* add world property to shallow function
* Fix type error in assignLorebookToChat invoke
* Remove debug console logs
* Fix activeCharacterUpdated
* Extract updateWorldInfoLinks into a func
* Invert if for an early return
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Handle port conflicts during server startup
* Fix return type of startHTTPorHTTPS
* Update language in getAddressInUseMessage
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat(popup): add allowEscapeClose option to override default escape key behavior
Add `allowEscapeClose` parameter to PopupOptions to explicitly control whether Escape key closes the popup, overriding the default logic that checks for visible cancel/close buttons. When null (default), uses existing behavior; when true, allows escape even without buttons; when false, prevents escape even with buttons present.
* feat(popup): enable Escape key closing for informational popups
Add `allowEscapeClose: true` option to TEXT-type popups in export preset, persona lore, sampler select, stats, and world info assignment dialogs to allow users to dismiss these informational popups with the Escape key.
* Improve Escape key interaction in popups
* Adjust jsdoc for allowEscapeClose
* Always return CANCELLED on Escape
* fix(popup): correct jsdoc for allowEscapeClose property description
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Fix missing model name in tokenize requests for llama.cpp (fixes#4962)
The new router mode of llama.cpp allows to switch models on the fly,
what is already supported by SillyTavern. The call to the `/tokenize`
endpoint did not contain the model name, and failed in router mode.
This patch adds the `model` parameter similar to the implementation
for other backends.
* fix: migrate vllm and aphrodite to new payload field
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Refactor loader.js to use action-loader system and move overlay management into action-loader module
- Deprecate showLoader() and hideLoader() in favor of action-loader API
- Implement legacy functions as thin wrappers around ActionLoaderHandle
- Move overlay management (showOverlay, hideOverlay, isOverlayDisplayed) into action-loader.js
- Move Popup-based loader implementation and preloader cleanup to action-loader
- Add loader.isBlocking() method to check for active blocking overlays
* Migrate from legacy loader functions to action-loader API throughout codebase
- Replace showLoader()/hideLoader() imports with loader from action-loader.js
- Update firstLoadInit() to use loader.show() with title, message, and ToastMode.STATIC
- Pass initLoaderHandle to getSettings() for early hide during onboarding flow
- Refactor renameGroupOrCharacterChat() to use loader.show() instead of boolean flag
- Wrap handleDeleteChat() with loader.show() and proper error handling
- Update BulkEditOver...
* Update loader titles and remove redundant reload notification
- Change bookmark loader title from "Bookmark" to "Chat History" for clarity
- Remove loader notification before extensions reload (redundant with browser reload)
* lint fix
* Add splash screen support to action loader with custom overlay content
- Add `overlayContent` option to ActionLoaderOptions for custom HTML in overlay
- Implement splash screen styles with centered logo, spinner, and message
- Update firstLoadInit() to use custom splash screen instead of static toast
- Pass custom content through showOverlay() to replace default spinner
- Adjust non-blocking loader warning to account for custom overlay content
* Refactor loader overlay to use DOM elements instead of HTML strings
- Add createDefaultLoaderOverlay() function to generate fresh loader overlay elements
- Export createOverlay() method on loader utility API for external use
- Change overlayContent parameter type from string-only to string|HTMLElement|null
- Add getOverlayContent() helper to normalize custom content for Popup
- Update firstLoadInit() to build splash screen using DOM manipulation instead of template literals
- Add splash-logo class and
* Use a true ellipsis
* Adjust sizing for desktop
* Even truer ellipsis
* Add transition to splash screen and fix blur animation on hideOverlay (#5338)
* Initial plan
* Blur entire splash screen on hideOverlay, not just spinner
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
Agent-Logs-Url: https://github.com/SillyTavern/SillyTavern/sessions/eee6c06d-7c9d-4363-bc8f-2647ed390368
* Add transition to splash-screen and fix transition detection
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
Agent-Logs-Url: https://github.com/SillyTavern/SillyTavern/sessions/9368bc36-31a0-4a58-aebd-7b569696ff2e
---------
Co-authored-by: anthropic-code-agent[bot] <242468646+Claude@users.noreply.github.com>
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* Add translations to supported locales
* Localize logo alt on welcome screen
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Claude <242468646+Claude@users.noreply.github.com>
* Stop strings apply to Chat Completions and should not be greyed out.
* Revert "Stop strings apply to Chat Completions and should not be greyed out."
This reverts commit 51e5cfee41.
* Stopping strings should only apply to Text Completions https://github.com/SillyTavern/SillyTavern/pull/5337#pullrequestreview-3987164461
* Custom stop strings still apply
* Also apply to non-streaming message clean-up
* This comment is now misplaced
* Oops, wrong file
* Revert package-lock change
---------
Co-authored-by: user <user@exmaple.com>
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat: add SiliconFlow.cn endpoint support and embedding vectors
Chat completion:
- Add endpoint selection dropdown (Global/.com vs China/.cn) to existing
SiliconFlow provider, following the Z.AI endpoint pattern
- Backend switches API URL based on selected endpoint
- Add /api-url slash command support for endpoint switching
Embeddings:
- Add SiliconFlow as a vector/embedding source (OpenAI-compatible)
- Support both .com and .cn endpoints via siliconflow_endpoint setting
borrowed from the main connection panel (Vertex AI pattern)
- Superset model list with platform attribution (.cn) markers
- Models: Qwen3-Embedding (0.6B/4B/8B) + BGE/BCE models (.cn only)
* Add filter by models type
* Load embedding models from endpoint
* Improve api-url command declaration
* Support endpoint override in custom-request service
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* fix(popup): prevent Escape key from closing popups when both cancel and close buttons are hidden
Add validation in cancel listener to check visibility of cancel and close buttons before allowing Escape key to close popup. Set isClosingPrevented flag to block subsequent close events when neither button is visible.
* feat(popup): add double-escape force-close mechanism for blocking popups
Add double-escape detection (within 500ms) to allow force-closing blocking popups that have both cancel and close buttons hidden. Show confirmation dialog warning about potential inconsistent state before allowing force-close. Track last escape press timestamp and confirmation popup state to prevent duplicate dialogs. Gracefully cancel force-close confirmation if main popup closes naturally.
The grok-2-image-1212 model was deprecated on 2026-02-24 and is no
longer available. Only grok-imagine-image and grok-imagine-image-pro
remain as valid xAI image generation models.
* feat: add placeholder and tooltip support to popup system with icon buttons
Add `placeholder` and `tooltip` options to main popup configuration. For INPUT type popups, placeholder applies to input field; for other types, tooltip applies to content area. Enhance custom buttons with optional `icon` parameter for Font Awesome icons and `tooltip` for hover text. Add tooltip support to custom inputs (placeholder for text/textarea, tooltip icon for checkboxes).
* fix: preserve default toastClass when applying custom cssClass in /echo command
Modify cssClass argument handling in echoCallback to append custom class to existing toastClass instead of replacing it. Use filter(Boolean).join(' ') to combine default and custom classes while handling undefined values.
* feat: add placeholder, tooltip, and icon support to popup system slash commands
Add `placeholder` and `tooltip` named arguments to /input command for input field customization. Add `tooltip` argument to /popup command for content area hover text. Enhance /buttons command to support button objects with `text`, `tooltip`, and `icon` (Font Awesome) properties alongside simple string labels. Update help text and examples for all three commands. Normalize button labels to ButtonLabel format internally
* Fix jsdoc wording
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix: add validation for button labels in /buttons command
Add validation check to ensure each button entry is either a string or an object with a non-empty string `text` property. Return empty string and log warning if validation fails. Fix capitalization of 'Popup' in /popup command return value description.
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Add action loader utility with stoppable toast notifications
* Add slash commands for action loader control (/loader-wrap, /loader-show, /loader-hide, /loader-stop)
* Refactor action loader to support stacking multiple loaders with individual toast management
- Convert action loader from singleton to class-based handle system (ActionLoaderHandle)
- Support multiple concurrent loaders with single overlay and stacked toasts
- Add unique ID generation and tracking for each loader instance
- Implement onHide callback alongside existing onStop callback
- Add getActiveLoaderHandles() and getLoaderHandleById() utility functions
- Refactor hideActionLoader() to accept...
* Improve action loader overlay and toast handling with better state checks and cleanup timing
- Check isLoaderDisplayed() before showing overlay to prevent conflicts with existing loaders
- Use toastr.options.hideDuration for toast removal timing instead of hardcoded 250ms
- Simplify hideActionLoader() by using getActiveLoaderHandles() helper
- Remove redundant empty check in hideActionLoader()
- Add clarifying comment for intentional error throw in createClosureHandler()
- Remove redundant 'onStop' default
* fix stop button toast removal issue by using toastr.clear force option instead of manual removal with timeout
* Fix isLoaderDisplayed() by using double negation operator instead of null comparison
* Add non-blocking loader support with `blocking` parameter for toast-only action loaders
- Add `blocking` option to ActionLoaderHandle (default: true)
- Implement hasBlockingLoaders() helper to check for active blocking loaders
- Show/hide overlay only when blocking loaders are active
- Add `blocking` named argument to /loader-wrap and /loader-show commands
- Update help strings with non-blocking usage examples
- Import commonEnumProviders for boolean enum and isFalseBoolean utility
* Add optional title parameter to action loader toast notifications and reorder constructor parameters for consistency
- Add `title` parameter to ActionLoaderOptions and ActionLoaderHandle constructor
- Pass title to toastr.info() for toast notifications
- Reorder parameters: blocking, toastMode, message, title, stopTooltip (grouped by importance)
- Add warning when creating non-blocking loader without toast (invisible to user)
- Update /loader-wrap and /loader-show commands with title argument
* Add loader utility API to action-loader and expose it in ST context for convenient programmatic access
- Create `loader` object with show/hide/active/get methods and ToastMode/Handle exports
- Add JSDoc examples for basic usage, non-blocking tasks, and hiding all loaders
- Import and expose `loader` in ST context alongside existing loader functions
* Split slash command and functional modules
* Create abort controller on app init
* Remove HTML tags from "returns" declaration
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Make description and firstMessage optional parameters in createCharacterCallback, allowing character creation with only a name. Remove validation checks that previously required these fields to be non-empty strings.
The addOpenRouterSignatures function was previously converting and appending message.signature to reasoning_details unconditionally, ignoring the `enableThoughtSignatures` setting.
This change adds a check for `enableThoughtSignatures` before converting message.signature, while still ensuring the original signature property is deleted to prevent API schema validation errors (HTTP 400).
* feat: add character CRUD slash commands (char-create, char-update, char-get, char-delete)
Implement comprehensive character management commands allowing programmatic creation, modification, retrieval, and deletion of characters without UI interaction. All commands support named arguments with proper validation and error handling.
* feat: enhance char CRUD commands with favorite, avatar, and improved defaults
Add `favorite` and `avatar` named arguments to char-create and char-update commands. Make `char` argument optional in char-delete (defaults to current character). Improve documentation with clarifications on card tags vs ST tags, avatar URL sources, and usage examples. Add `fav` field to char-get output.
* feat: add /tag-import slash command for programmatic character tag import
Implement /tag-import command with `name` (defaults to {{char}}) and `mode` arguments (all/existing/none/ask). Command imports character card tags as ST tags for filtering/organizing. Returns 'true' if tags were imported, 'false' otherwise. Mode argument maps to existing tag_import_setting enum values.
* feat: enhance char-create and char-update with avatar upload and tag parsing
Add avatar resolution and upload support for char-create and char-update commands. Implement resolveAvatarData() to handle URLs, base64 data URLs, and local paths. Add uploadCharacterAvatar() to upload resolved images via /api/characters/edit-avatar. Parse tags argument as comma-separated array. Refresh side panel after char-update when modifying current character. Add char-get2 alias for testing.
* feat: enhance avatar argument in char CRUD commands with file picker and local path support
Add `prompt` value to avatar argument to open file picker dialog. Implement promptForAvatarFile() to handle image selection with validation. Add folderEnumMatchProvider() for autocomplete matching of folder paths. Update avatar enumList with common ST paths (characters/, backgrounds/, User Avatars/, assets/, user/images/). Remove external URL support from resolveAvatarData() - now only accepts "prompt", base
* feat: add /char-duplicate slash command with avatar resize support and enhanced avatar upload handling
Implement /char-duplicate command with `char` and `select` named arguments. Add `avatarPromptResize` argument to char-create and char-update for optional resize/crop dialog. Refactor duplicateCharacter() to accept avatar and silent parameters, returning the new avatar key. Enhance uploadCharacterAvatar() to handle resize prompts and return success status. Add cache busting and DOM refresh for avatar thumbnails
* refactor: optimize avatar refresh after upload by using cache busting and DOM query
Replace message-specific avatar refresh logic with generic image refresh targeting all thumbnails using the updated avatar URL. Remove unnecessary delay and character name matching. Add cache busting for both thumbnail and full character image. Use querySelectorAll to find and refresh all affected img elements in one pass.
* refactor: rename char-get alias from char-get2 to char-data
* refactor: move /dupe command to alias of /char-duplicate and fix characterIndex type
Move standalone /dupe command to alias of /char-duplicate for consistency with character CRUD commands. Cast characterIndex to String in char-update to match expected type.
* docs: clarify /imagine command integration with avatar argument in char CRUD commands
Update avatar argument descriptions and examples to explicitly mention /imagine command return value support. Reorder piped /imagine example to show correct command flow (generate image first, then update character).
* feat: add i18n support to char-create and char-update command error messages
Wrap validation error toastr messages in t`` template literals for translation support in /char-create and /char-update commands.
* feat: add group chat validation to /tag-import command
Add early validation check to prevent tag import in group chats. Display warning toastr message and return 'false' when selected_group is not null.
* Fix char update world property
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Fix help text documentation to match arg name
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix: return empty string instead of throwing errors in char-create and char-update commands
Replace `throw error` with `return ''` in error handlers for /char-create and /char-update commands to prevent unhandled promise rejections while still displaying error toastr messages.
* refactor: make deleteCharacter return boolean success status and update char-delete command to use it
Change deleteCharacter to return boolean indicating success/failure instead of void. Return false on user cancellation or failed chat close, true when character is successfully deleted. Update /char-delete command to use returned success value instead of always returning 'true'.
* refactor: make description and firstMessage optional in /char-create command
Remove description and firstMessage from required fields array, allowing character creation with only a name. Update help text to reflect that only name is required.
* refactor: extract external URL check to utility function and add same-origin URL support for avatar resolution
Extract external URL check into `isExternalUrl` utility function in utils.js. Update `resolveAvatarData` to use new utility and add support for same-origin URLs by converting them to pathname before fetching.
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Fix AICC direct link import parsing
Update parseAICC in src/endpoints/content-manager.js to dynamically extract the author and character name from the end of the URL path. This resolves a 404 import error caused by AICC adding category subfolders and changing their base URL structure from /character-cards/ to /charactercards/.
* Clean up whitespace in content-manager.js
Remove unnecessary whitespace in URL path processing.
* Use isValidUrl for URL validation
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Unify chat lorebook button click behavior with character lorebook button
* Update locale strings for chat lorebook button
* Unify chat lorebook button click behavior with character lorebook button
* Update locale strings for chat lorebook button
* Also unify character lorebook button to support Alt modifier
* Update locale strings for character lorebook button
* Update public/locales/fr-fr.json
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Add long-press support for lorebook buttons on mobile
* Update locale strings for lorebook button long-press
* Fix long-press to use event delegation for dynamic elements
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat: add array-wrap and array-unwrap commands
* Add LIST as available argument type
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Throw when trying to wrap a closure
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Throw on closure in array-unwrap
* Add the rest of argument types for array-unwrap
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Add Python-friendly aliases
* Don't filter out just strings
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* Proper primitive value unwrapping
* Throw on multiple unnamed arguments
* Enhance parsed object wrapping
* Update comment to clarify boolean support in value wrapping
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix(extensions/Summarize): prioritize UI memory content for {{summary}} macro
The {{summary}} macro previously relied solely on history-based metadata, causing it to return empty when starting a new chat if 'None (not injected)' was selected as the injection position.
This change prioritizes the #memory_contents UI value to ensure the macro resolves immediately, even before the first history-based summary is generated.
* Implement for legacy macro
* Restore original trim call
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* add Slash commands regenerate and swipe
* Update /swipe slash command direction handling
* Fix await not working in groups
* Add SLASH_COMMAND source to swipe functionality and update constants
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* group add
* make button not wide
* make single and batch add to folder use the same style popup
* prevent stuck UI, allow scrolling, prevent ::after conflicts
* extremely large commit, beware
* clear everything after performing bulk actions
* Unify bulk selection design language
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Add gpt-5.3-chat-latest model support
- Add to OpenAI model dropdown (index.html)
- Add to captioning multimodal model list (caption/settings.html)
- Add to OPENAI_REASONING_EFFORT_MODELS (constants.js)
- Add OPENAI_FIXED_REASONING_EFFORT map to clamp effort to 'medium' (the only value this model accepts)
- Apply fixed effort override in both Azure and general OpenAI request paths (chat-completions.js)
- Update frontend gpt-5.x regex for parameter handling (openai.js)
* Update public/scripts/openai.js
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
System messages in the OpenRouter messages array were being counted
toward depth and could receive cache_control breakpoints. Since
OpenRouter hoists system messages into Claude's separate system
parameter, this misplaced breakpoints and could prevent caching
entirely if the hoisted content fell below minimum cache size.
Closes#5227
77 tests covering 24 pure functions: keyToEnv, getBasicAuthHeader,
getHexString, normalizeZipEntryPath, deepMerge, uuidv4,
humanizedDateTime, tryParse, clientRelativePath, getUniqueName,
removeFileExtension, removeColorFormatting, getSeparator, isValidUrl,
urlHostnameToIPv6, toBoolean, stringToBool, trimV1, trimTrailingSlash,
mutateJsonString, isPathUnderParent, isFileURL, getRequestURL, and
formatBytes (via getBasicAuthHeader pattern).
These are all deterministic, side-effect-free functions tested without
any mocking. Placed in a separate file from the existing util.test.js
to keep concerns separated.
* Use Ollama /api/embed endpoint for vector embeddings
The deprecated /api/embeddings endpoint does not properly support the
truncate parameter, causing "input length exceeds context length" errors
when vectorizing files. Migrate to /api/embed which correctly handles
truncation and supports native batch input.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Wrap single Ollama vector calculation into batch
Fixes https://github.com/SillyTavern/SillyTavern/pull/5221/changes#r2850052729
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* backend, frontend, bugfixes
* Mobile button and sizing
* lint
* clear folder thumbnailFile on delete, rename thumbnailFile on rename
* use filteredImages when changing sort option
* Address all the review comments
* Fix friendly title generation to handle empty strings
* Move add folder button to the header
* instead of search filtering the backgrounds in a folder and showing the folder if the results > 0, search the folder names.
* Trade button places
* Adjust button text
* feat: restrict folder creation to the Global tab
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Added filter for OpenRouter models provider selection
Now if a model is selected, only available providers for that model will show. Wanted to do the same for the quants, but I think the API is not returning the quants available for each model at the moment. Used existing API that for some reason was not consumed.
* Added filter for OpenRouter providers
Now if a model is selected, only the providers available show. Wanted to do the same with the quants but it seems the OpenRouter API is not giving the available quants list at the moment for each model.
* gua
* Now it also works on chat completion and only disables options
* detail
* Warning added
* eslint
* Move inline styles to CSS
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* feat(openrouter): disable reasoning if "Request model reasoning" is disabled
* feat(openrouter): map minimum reasoning to none if request reasoning is off
* Add hint how to disable reasoning
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Initial plan
* feat: preserve image width/height when generating swipe images
Save width and height in ImageGenerationAttachmentProps when creating
MediaAttachment objects, and apply saved dimensions when generating
image swipes. Falls back to current extension settings if not specified.
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* fix: validate dimension override with Number.isInteger and skip setTypeSpecificDimensions when override is present
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* fix: call restoreOriginalDimensions when setTypeSpecificDimensions was used
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* Contain the logic to setTypeSpecificDimensions
* Diff clean-up
* feat: enhance prompt refinement with negative input and saved resolution options
* fix: Only save image dimensions when running from command
* Fix wording in refine prompt dialog
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* fix(openrouter): forward reasoning across active tool-call chains
* feat(reasoning): add tool-chain forwarding toggle and honor edited reasoning
* feat(reasoning): add OpenRouter interleaved forwarding modes
* moved the reasoning forwarding dropdown into a separate line
* feat(reasoning): default tool reasoning forwarding to disabled
* refactor(openrouter): move tool reasoning mode to CC settings
Move OpenRouter tool reasoning forwarding control to response configuration and scope it to OpenRouter.
Store mode in chat completion settings (presettable), remove legacy power_user boolean/fallback, and use constants for mode values.
Preserve OpenRouter Gemini signature forwarding independently from plaintext tool reasoning mode.
* fix(openrouter): tighten active-chain reasoning forwarding
Use trailing contiguous tool-chain boundary for active-chain eligibility.
Also rename the UI control to Interleaved Thinking Forwarding and place selector on its own line.
* fix(openrouter): use adjacent assistant reasoning for tool calls
For interleaved thinking forwarding, source reasoning only from the immediately preceding assistant non-tool message.
Keep mode gating behavior unchanged and avoid history-window reasoning carryover.
* fix(openrouter): skip tool messages for reasoning source
When forwarding interleaved reasoning, ignore intervening tool result messages when resolving the preceding assistant reasoning source.
This keeps only the first tool call in a chain tied to a prior assistant reasoning block unless a later invocation carries its own reasoning.
* fix(openrouter): keep plaintext reasoning with signatures
Do not suppress forwarded tool-call reasoning when thought signatures are present.
* fix(openrouter): split interleaved thinking mode behavior
Restore distinct mode semantics: active_chain uses nearest assistant-text boundary after skipping tool/tool-call messages, while since_last_user scans for latest assistant reasoning since user.
Update UI label to Interleaved Thinking with right-aligned dropdown and explanatory tooltip.
* style(openrouter): align interleaved thinking dropdown row
Match OpenRouter interleaved thinking control layout with existing oneline-dropdown patterns.
Also update reasoning-forwarding inline comment wording for current mode behavior.
* docs(ui): clarify interleaved thinking tooltip
Use explicit API-request wording for OpenRouter interleaved thinking tooltip text.
* i18n(openrouter): localize interleaved thinking UI
Add locale keys for OpenRouter interleaved thinking label, mode options, and inline helper description.
Wire dropdown option text to data-i18n in index.html.
* fixed helper text wrapping
* fix(ui): make interleaved thinking helper text wrap
* i18n(openrouter): translate interleaved thinking labels
Replace placeholder English values for interleaved thinking keys in non-English locale files.
* fix(ui): restore interleaved thinking dropdown alignment
* Remove changes from en.json
* Type fixes
* Reworked the interleaved reasoning provider logic
* Renamed the variables in preparation for potential implementation for other providers
* Gate interleaved tool reasoning on reasoning request setting
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* build llama.cpp embedding url path by appending instead of overwriting
When using a llama-swap frontend, this allows choosing the embedding model
by path; for instance, with the secondary embedding endpoint URL configured
to http://127.0.0.1:5001/upstream/emb-model to pick the "emb-model" model.
With this approach, the same llama-swap instance can be used to serve both
the main LLM and the embedding model from local llama-server commands.
* Trim trailing v1 from URL
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* check png for apng headers
* isAnimated flag
* refactor: centralize background animation extension checks
* refactor: scope animated extension dedupe to backgrounds
* remove precompute from startup
* Fix animation preference not being loaded, fix type-check of customInputs
* Fix eslint
* Fix sort on removal type
* Update metadata before returning from endpoint on CRUD operations
* Remove race condition in metadata load
* Load metadata after loading the list
---------
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Add gallery argument to /imagine to skip character gallery save
Adds a `gallery` named argument (default: true) to the /imagine slash
command. When `gallery=false`, the generated image is saved to the
generic images directory instead of the character-specific gallery
folder, while still returning a usable image URL.
This is useful for extensions that manage their own image display
(e.g. inline in chat messages) and don't need gallery copies.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Can't assign to a constant
* Update help string to clarify image saving behavior in generation requests
* Fix file name template if no char name provided
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
- Add 'textarea' as a valid input type alongside 'checkbox' and 'text'
- Add optional `rows` property to control textarea height (default: 1)
- Implement textarea rendering with proper label, placeholder, and styling
- Update result collection logic to handle textarea values like text inputs
- Update warning message to include textarea in supported types
* feat: add prefers-reduced-motion and prefers-contrast media queries
- Integrate OS prefers-reduced-motion into existing JS toggle system:
when OS preference is active, force reduced_motion on and disable
the UI checkbox with an explanatory tooltip
- Add body.reduced-motion CSS rules for hardcoded animations that
bypass the --animation-duration variable (text_segment fade-in,
dragover pulse)
- Add prefers-contrast: more media query for enhanced focus outlines
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Support translating title text
* Use duration variable
* Removed stream fade-in override
* Combine hi-contrast selectors
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
* Initial plan
* Overhaul /bgcol command: Oklab color space, dominant color extraction, full theme palette generation
- Create ThemeGenerator module in public/scripts/util/ with:
- Oklab color space conversions (sRGB ↔ Oklab ↔ LCH)
- Chroma-weighted dominant color extraction (vivid over muddy averages)
- Color theory palette: complementary, analogous, triadic hue relationships
- WCAG contrast ratio enforcement (≥3.5:1 for all text colors)
- Replace old setAvgBG with new implementation using ThemeGenerator
- Save generated theme as "Generated - <background name>" instead of overwriting
- Update command help string to reflect production-ready status
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* Extract hue shift constants for clarity (code review feedback)
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* Add name and bg arguments to /bgcol command
- Add `name` named argument to override the generated theme name
- Add `bg` named argument with enum provider listing available backgrounds
from /api/backgrounds/all to override the current background
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* Improve types, add enum provider, reduce transparency
* Adjust alpha channel for better readability
* Refactor ThemeGenerator to work directly in Oklch, removing intermediate Oklab conversions
Replaced srgbToOklab/oklabToSrgb + oklabToLCH/lchToOklab with direct
srgbToOklch/oklchToSrgb functions. All color manipulations now use
{L, C, h} directly without converting through {a, b} intermediates.
The ensureContrast function now takes (L, C, h) parameters instead of
an Oklab object.
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
* Add custom background URL check and enhance theme generation logic
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Cohee1207 <18619528+Cohee1207@users.noreply.github.com>
@@ -36,7 +36,7 @@ Angefangen im Februar 2023 als Fork von TavernAI 1.2.8 hat SillyTavern nun über
## Brauche ich einen leistungsstarken PC, um SillyTavern auszuführen?
Die Hardwareanforderungen sind minimal: Es läuft auf allem, was NodeJS 18 oder höher ausführen kann. Wenn du LLM-Inferenz auf deinem lokalen Rechner durchführen möchtest, empfehlen wir eine NVIDIA-Grafikkarte der 3000er-Serie mit mindestens 6 GB VRAM, aber die tatsächlichen Anforderungen können je nach Modell und Backend, das du verwendest, variieren.
Die Hardwareanforderungen sind minimal: Es läuft auf allem, was NodeJS 20 oder höher ausführen kann. Wenn du LLM-Inferenz auf deinem lokalen Rechner durchführen möchtest, empfehlen wir eine NVIDIA-Grafikkarte der 3000er-Serie mit mindestens 6 GB VRAM, aber die tatsächlichen Anforderungen können je nach Modell und Backend, das du verwendest, variieren.
@@ -36,7 +36,7 @@ SillyTavern(짧게는 ST)은 텍스트 생성 LLM, 이미지 생성 엔진, TTS
## SillyTavern을 위해서 좋은 성능의 PC가 필요한가요?
하드웨어 요구 사항은 거의 없습니다: NodeJS 18 이상을 실행할 수 있는 모든 환경에서 작동합니다. 다만 로컬 LLM 모델을 사용할 경우, 최소 6GB VRAM 이상의 3000번대 NVIDIA 그래픽 카드를 권장하지만, 실제 요구 사항은 사용하는 모델과 백엔드에 따라 달라질 수 있습니다.
하드웨어 요구 사항은 거의 없습니다: NodeJS 20 이상을 실행할 수 있는 모든 환경에서 작동합니다. 다만 로컬 LLM 모델을 사용할 경우, 최소 6GB VRAM 이상의 3000번대 NVIDIA 그래픽 카드를 권장하지만, 실제 요구 사항은 사용하는 모델과 백엔드에 따라 달라질 수 있습니다.
@@ -36,7 +36,7 @@ SillyTavern (или сокращенно ST) - это локально уста
## Нужен ли мне мощный компьютер для запуска SillyTavern?
Требования к оборудованию минимальны: он будет работать на всем, что может запустить NodeJS 18 или выше. Если вы собираетесь выполнять инференс LLM на своем локальном компьютере, мы рекомендуем видеокарту NVIDIA 3000-й серии с не менее чем 6 ГБ видеопамяти, но фактические требования могут варьироваться в зависимости от модели и используемого вами бэкенда.
Требования к оборудованию минимальны: он будет работать на всем, что может запустить NodeJS 20 или выше. Если вы собираетесь выполнять инференс LLM на своем локальном компьютере, мы рекомендуем видеокарту NVIDIA 3000-й серии с не менее чем 6 ГБ видеопамяти, но фактические требования могут варьироваться в зависимости от модели и используемого вами бэкенда.
@@ -23,17 +23,17 @@ We have a [Documentation website](https://docs.sillytavern.app/) to answer most
SillyTavern (or ST for short) is a locally installed user interface that allows you to interact with text generation LLMs, image generation engines, and TTS voice models.
Beginning in February 2023 as a fork of TavernAI 1.2.8, SillyTavern now has over 200 contributors and 2 years of independent development under its belt, and continues to serve as a leading software for savvy AI hobbyists.
Beginning in February 2023 as a fork of TavernAI 1.2.8, SillyTavern now has over 300 contributors and 3 years of independent development under its belt, and continues to serve as a leading software for savvy AI hobbyists.
## Our Vision
1. We aim to empower users with as much utility and control over their LLM prompts as possible. The steep learning curve is part of the fun!
2. We do not provide any online or hosted services, nor programmatically track any user data.
3. SillyTavern is a passion project brought to you by a dedicated community of LLM enthusiasts, and will always be free and open sourced.
3. SillyTavern is a passion project brought to you by a dedicated community of LLM enthusiasts, and will always be free and open source.
## Do I need a powerful PC to run SillyTavern?
The hardware requirements are minimal: it will run on anything that can run NodeJS 18 or higher. If you intend to do LLM inference on your local machine, we recommend a 3000-series NVIDIA graphics card with at least 6GB of VRAM, but actual requirements may vary depending on the model and backend you choose to use.
The hardware requirements are minimal: it will run on anything that can run NodeJS 20 or higher. If you intend to do LLM inference on your local machine, we recommend a 3000-series NVIDIA graphics card with at least 6GB of VRAM, but actual requirements may vary depending on the model and backend you choose to use.
## Questions or suggestions?
@@ -75,7 +75,7 @@ but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.**
* [TavernAI](https://github.com/TavernAI/TavernAI) 1.2.8 by Humi: MIT License
* [TavernAI](https://github.com/TavernAI/TavernAI-v1) 1.2.8 by Humi: MIT License
* Portions of CncAnon's TavernAITurbo mod used with permission
* Visual Novel Mode inspired by the work of PepperTaco (<https://github.com/peppertaco/Tavern/>)
if:contains(fromJSON('["👩💻 Good First Issue", "🙏 Help Wanted", "🪲 Confirmed", "⚠️ High Priority", "❕ Medium Priority", "💤 Low Priority"]'), github.event.label.name)
@@ -62,6 +62,16 @@ Write at least somewhat meaningful PR descriptions and commit messages. There's
- What did you do to achieve this?
- How would a reviewer test the change?
### Discuss new provider integrations before implementing them
Do not use a completed pull request as the first product discussion for a new named external provider or service.
- Model routers, resellers, rerouters, gateways, and aggregators should use **Custom (OpenAI-compatible)** and publish provider-owned setup instructions. Provider-specific convenience may be implemented as a third-party UI extension or server plugin.
- New first-party model, TTS, speech, web search, image, vectorization, embedding, reranking, and similar integrations are exceptional and should begin with a public issue and maintainer discussion before implementation.
- Existing-provider maintenance and provider-neutral improvements to generic compatibility remain welcome.
Read [Integrating an External Provider](https://docs.sillytavern.app/for-contributors/provider-integrations/) before starting implementation.
### We (likely) don't speak your language
English is the primary language of communication in this project. Please use only English when writing commit messages, PR descriptions, comments and other text. This does not apply to contributions to localization files.
@@ -81,5 +91,6 @@ We do not prohibit nor encourage the use of AI tools for coding assistance to he
## Further reading
1. [How to write UI extensions](https://docs.sillytavern.app/for-contributors/writing-extensions/)
2. [How to write server plugins](https://docs.sillytavern.app/for-contributors/server-plugins)
1. [How to integrate an external provider](https://docs.sillytavern.app/for-contributors/provider-integrations/)
2. [How to write UI extensions](https://docs.sillytavern.app/for-contributors/writing-extensions/)
3. [How to write server plugins](https://docs.sillytavern.app/for-contributors/server-plugins)
# Interval in seconds to write a heartbeat file. Set to 0 to disable.
# This is used primarily for Docker healthchecks.
heartbeatInterval:0
# Enable HTTP/HTTPS keep-alive globally.
# Disabling restores old Node 18 behavior, can help if ECONNRESET and other network errors occur.
enableKeepAlive:false
# -- SSL options --
ssl:
# Enable SSL/TLS encryption
@@ -55,7 +58,7 @@ ssl:
# -- SECURITY CONFIGURATION --
# Toggle whitelist mode
whitelistMode:true
# Whitelist will also verify IP in X-Forwarded-For / X-Real-IP headers
# When enabled, whitelist will also verify IP in headers enabled in `forwardedHeaders` section.
enableForwardedWhitelist:true
# Whitelist of allowed IP addresses
whitelist:
@@ -127,6 +130,13 @@ sso:
# as that used for authentik. (Ensure the username in authentik
# is an exact match in lowercase with that in sillytavern).
authentikAuth:false
# List of trusted proxy IPs for SSO authentication.
# Supports wildcards or CIDR notation for subnets.
# Example: ['127.0.0.1', '192.168.1.1']
# Set to ['*'] to trust all proxies (NOT RECOMMENDED unless you have other security measures in place)
trustedProxies:
- ::1
- 127.0.0.1
# Host whitelist configuration. Recommended if you're using a listen mode
hostWhitelist:
@@ -141,6 +151,26 @@ hostWhitelist:
# - .trycloudflare.com
hosts:[]
# Perform whitelist checks against server-side HTTP requests that resolve to private IP addresses.
# This is an additional layer of security to prevent Server-Side Request Forgery (SSRF) attacks.
# Recommended when listen mode is enabled, or if your server is accessible by untrusted users.
privateAddressWhitelist:
# Enable private address whitelist to block requests to private IP ranges.
enabled:false
# If true, requests to hosts that cannot be resolved will be allowed instead of blocked.
allowUnresolvedHosts:false
# Log blocked and allowed requests to the console.
log:
# Log blocked requests to the console with a warning message
blockedRequests:true
# Log allowed requests to the console with an info message
allowedRequests:false
# List of allowed private IP ranges (in CIDR notation or wildcard format).
# Allows loopback IP ranges by default, but you can customize this list to fit your needs.
allowedRanges:
- '127.0.0.0/8'# Loopback (IPv4)
- '::1/128'# Loopback (IPv6)
# User session timeout *in seconds* (defaults to 24 hours).
## Set to a positive number to expire session after a certain time of inactivity
## Set to 0 to expire session when the browser is closed
@@ -159,12 +189,31 @@ logging:
minLogLevel:0
# -- RATE LIMITING CONFIGURATION --
rateLimiting:
# Use X-Real-IP header instead of socket IP for rate limiting
# Only enable this if you are using a properly configured reverse proxy (like Nginx/traefik/Caddy)
# Use any of the enabled headers in the `forwardedHeaders` section to identify the client IP for rate limiting.
# If disabled, only the socket IP will be used, which may not work correctly if you are behind a reverse proxy.
preferRealIpHeader:false
# Set the maximum number of allowed failed basic authentication attempts before rate limiting is applied. Set to 0 to disable rate limiting for basic auth.
basicAuthMaxAttempts:5
# Set the maximum number of allowed failed account login attempts before rate limiting is applied. Set to 0 to disable rate limiting for account logins.
accountsLoginMaxAttempts:5
# Set the maximum number of allowed failed account recovery attempts before rate limiting is applied. Set to 0 to disable rate limiting for account recovery.
accountsRecoverMaxAttempts:5
# Set the maximum number of allowed failed account reset attempts before rate limiting is applied. Set to 0 to disable rate limiting for account resets.
accountsResetMaxAttempts:5
# Set to true to enable support for real IPs in certain request headers for features like IP whitelisting, rate limiting and access logging.
# Only change if you are sure that you use a correctly configured reverse proxy, otherwise this may lead to IP spoofing.
forwardedHeaders:
# X-Real-IP header (common with Nginx and Caddy)
xRealIp:true
# X-Forwarded-For header (common with many proxies, but may contain multiple IPs - only the first one will be used)
xForwardedFor:true
# CF-Connecting-IP header (used by Cloudflare Tunnels)
cfConnectingIp:false
## BACKUP CONFIGURATION
backups:
# Allow users to create a full backup archive of their data
allowFullDataBackup:true
# Common settings for all backup types
common:
# Number of backups to keep for each chat and settings file
@@ -202,6 +251,16 @@ performance:
memoryCacheCapacity:'100mb'
# Enables disk caching for character cards. Improves performances with large card libraries.
useDiskCache:true
# Configures gzip compression for client requests with large payloads (e.g. settings or chat saves).
requestCompression:
# Enable request compression.
enabled:false
# Minimum payload size to trigger compression. Set to 0 to compress all requests regardless of size.
minPayloadSize:'256kb'
# Hard upper payload size limit for compression. Set to 0 to allow compression of any size.
maxPayloadSize:'8mb'
# Timeout for request compression in milliseconds.
timeout:4000
# CACHE BUSTER CONFIGURATION
# IMPORTANT: Requires localhost or a domain with HTTPS, otherwise will not work!
@@ -250,6 +309,13 @@ extensions:
speechToText:Xenova/whisper-small
textToSpeech:Xenova/speecht5_tts
# Git backend for plugin/extension repository operations.
# - Use "auto" to prefer system git, falling back to the integrated backend
# - Use "system" to force system backend
# - Use "builtin" to force integrated backend
git:
backend:auto
# Additional model tokenizers can be downloaded on demand.
# Disabling will fallback to another locally available tokenizer.
enableDownloadableTokenizers:true
@@ -293,7 +359,7 @@ claude:
# Otherwise, you'll just waste money on cache misses.
enableSystemPromptCache:false
# Enables caching of the message history at depth (if supported).
d="m 14.3423,8.42148 0.0218,-0.00723 2.1725,-0.51502 c 0.4642,-0.10879 0.8631,-0.40619 1.1025,-0.81965 l 0.5041,-0.87044 0.0146,-0.02902 0.0145,0.02902 0.5041,0.87044 c 0.2394,0.41346 0.6383,0.71086 1.1025,0.81965 l 2.1725,0.51502 0.0254,0.01087 H 21.9514 L 19.7789,8.94737 C 19.3147,9.0562 18.9158,9.35359 18.6764,9.76705 l -0.5041,0.87045 -0.0145,0.029 -0.0146,-0.029 -0.5041,-0.87045 C 17.3997,9.35359 17.0008,9.0562 16.5366,8.94737 L 14.3641,8.43239 14.3423,8.42512 Z"
id="path10" /><path
d="M 14.3423,2.245 14.3641,2.23775 16.5366,1.72274 C 17.0008,1.61393 17.3997,1.31653 17.6391,0.903078 L 18.1432,0.0290146 18.1578,0 18.1723,0.0290146 18.6764,0.899453 C 18.9158,1.31291 19.3147,1.61031 19.7789,1.71911 L 21.9514,2.23412 21.9768,2.245 H 21.9514 L 19.7789,2.76726 C 19.3147,2.87607 18.9158,3.17347 18.6764,3.58692 L 18.1723,4.45738 18.1578,4.48639 18.1432,4.45738 17.6391,3.58692 C 17.3997,3.17347 17.0008,2.87607 16.5366,2.76726 L 14.3641,2.25225 Z"
id="path11" /><path
d="M 18.183,15.7998 C 17.9328,13.7832 16.754,11.9807 14.9697,10.9507 11.749,9.03938 8.96364,8.82176 6.23265,6.73999 L 2.52967,8.79638 18.183,17.8344 33.8364,8.79638 30.1334,6.74359 c -2.731,2.08181 -5.5164,2.29943 -8.737,4.21071 -1.7844,1.0301 -2.9631,2.8326 -3.2134,4.8491 z"
id="path12" /><path
d="M 18.183,35.6603 C 17.824,35.653 17.4649,35.5551 17.1458,35.3701 L 2.52967,26.9269 V 8.79646 L 17.1458,17.236 c 0.3227,0.185 0.6782,0.2829 1.0372,0.2902 0.3591,-0.0073 0.7181,-0.1052 1.0373,-0.2902 L 33.8364,8.79646 V 26.9306 l -14.6161,8.4395 c -0.3228,0.185 -0.6782,0.2829 -1.0373,0.2902 z"
id="path13" /><path
d="m 18.183,35.6603 c 0.3591,-0.0073 0.7181,-0.1052 1.0373,-0.2902 l 14.616,-8.4395 V 8.79646 L 19.2203,17.236 c -0.3228,0.185 -0.6782,0.2829 -1.0373,0.2902"
id="path14" /><path
d="M 18.183,17.5262 C 17.824,17.5189 17.4649,17.421 17.1458,17.236 L 2.52967,8.79646 V 26.9306 l 14.61613,8.4395 c 0.3227,0.185 0.6782,0.2829 1.0372,0.2902"
id="path15" /><path
d="M 18.1831,17.5262 C 17.824,17.5189 17.465,17.421 17.1458,17.236 l -1.4507,-0.8378 v 18.1341 l 1.4507,0.8378 c 0.3228,0.185 0.6782,0.2829 1.0373,0.2902 0.359,-0.0073 0.7181,-0.1052 1.0372,-0.2902 l 1.4508,-0.8378 V 16.3946 l -1.4508,0.8378 c -0.3227,0.1849 -0.6782,0.2829 -1.0372,0.2901 z"
id="path16" /><path
d="M 9,5.32055 9.02174,5.31328 11.1942,4.79826 c 0.4643,-0.10879 0.8632,-0.40618 1.1026,-0.81964 l 0.5041,-0.87044 0.0145,-0.02902 0.0145,0.02902 0.5041,0.87044 c 0.2394,0.41346 0.6384,0.71085 1.1026,0.81964 l 2.1725,0.51502 0.0253,0.01087 H 16.6091 L 14.4366,5.84644 C 13.9724,5.95523 13.5734,6.25263 13.334,6.66609 L 12.8299,7.53653 12.8154,7.56555 12.8009,7.53653 12.2968,6.66609 C 12.0574,6.25263 11.6585,5.95523 11.1942,5.84644 L 9.02174,5.33142 9,5.32415 Z"
id="path17" /><path
d="m 19.6593,5.32055 0.0218,-0.00727 2.1724,-0.51502 c 0.4642,-0.10879 0.8632,-0.40618 1.1026,-0.81964 l 0.5041,-0.87044 0.0145,-0.02902 0.0145,0.02902 0.5042,0.87044 c 0.2393,0.41346 0.6383,0.71085 1.1025,0.81964 l 2.1724,0.51502 0.0255,0.01087 H 27.2683 L 25.0959,5.84644 C 24.6317,5.95523 24.2327,6.25263 23.9934,6.66609 L 23.4892,7.53653 23.4747,7.56555 23.4602,7.53653 22.9561,6.66609 C 22.7167,6.25263 22.3177,5.95523 21.8535,5.84644 L 19.6811,5.33142 19.6593,5.32415 Z"
"OpenRouter API key already exists":"مفتاح API OpenRouter موجود بالفعل",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"هل تريد حقاً إنشاء مفتاح OpenRouter جديد؟ لن يتم حذف مفتاحك الموجود.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"احصل على رمز واجهة برمجة التطبيقات الخاص بك لموزع الاتصالات باستخدام تدفق OAuth. سيتم توجيهك إلى openrouter.ai",
"Bypass status check":"تجاوز فحص الحالة",
"Chat Completion Source":"مصدر استكمال الدردشة",
@@ -394,7 +396,7 @@
"Available Models":"النماذج المتاحة",
"Prompt Post-Processing":"موجه بعد المعالجة",
"Applies additional processing to the prompt before sending it to the API.":"يطبق معالجة إضافية على الموجه قبل إرساله إلى واجهة برمجة التطبيقات.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"تتحقق من اتصالك بواجهة برمجة التطبيقات من خلال إرسال رسالة اختبار قصيرة. كن على علم بأنك ستحصل على الفضل في ذلك!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"يتحقق من اتصال API الخاص بك عن طريق إرسال رسالة اختبار قصيرة. قد يؤدي ذلك إلى فرض رسوم استخدام.",
"Test Message":"رسالة اختبار",
"Auto-connect to Last Server":"الاتصال التلقائي بآخر خادم",
"Missing key":"❌المفتاح مفقود",
@@ -1438,5 +1440,19 @@
"Still have questions?":"هل ما زالت لديك اسئلة؟",
"Join the SillyTavern Discord":"انضم إلى ديسكورد SillyTavern",
"Post a GitHub issue":"نشر مشكلة على GitHub",
"Contact the developers":"الاتصال بالمطورين"
"Contact the developers":"الاتصال بالمطورين",
"Interleaved Thinking":"التفكير المتداخل",
"Since Last User Message":"منذ آخر رسالة من المستخدم",
"Active Tool Chain":"سلسلة الأدوات النشطة",
"openrouter_interleaved_thinking_hint":"يرسل الاستدلال من رسائل المساعد السابقة مع طلبات استدعاء الأدوات للحفاظ على سياق التفكير المتداخل.",
"SillyTavern Logo":"شعار SillyTavern",
"Initializing…":"جارٍ التهيئة…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"الاسم غير مقبول، لأنه نفسه كما كان من قبل (تجاهل حالة الأحرف والنبرات).",
"Rename Chat":"إعادة تسمية المحادثة",
"Renaming chat…":"جارٍ إعادة تسمية المحادثة…",
"Delete Chat":"حذف المحادثة",
"Deleting chat…":"جارٍ حذف المحادثة…",
"Loading chat…":"جارٍ تحميل المحادثة…",
"Bulk Delete":"حذف جماعي",
"Deleting ${0} character(s)…":"جارٍ حذف ${0} شخصية (شخصيات)…"
"OpenRouter API key already exists":"OpenRouter API-Schlüssel existiert bereits",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Möchten Sie wirklich einen neuen OpenRouter API-Schlüssel erstellen? Ihr vorhandener Schlüssel wird nicht gelöscht.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Hole dein OpenRouter-API-Token mit OAuth-Fluss. Du wirst zu openrouter.ai weitergeleitet",
"Bypass status check":"Umgehe Statusüberprüfung",
"Chat Completion Source":"Quelle für Chat-Vervollständigung",
"Applies additional processing to the prompt before sending it to the API.":"Wendet zusätzliche Verarbeitungsvorgänge auf die Eingabeaufforderung an, bevor sie an die API gesendet wird.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Überprüft deine API-Verbindung durch Senden einer kurzen Testnachricht. Sei dir bewusst, dass du dafür gutgeschrieben wirst!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Überprüft deine API-Verbindung durch Senden einer kurzen Testnachricht. Dabei können Nutzungsgebühren anfallen.",
"Test Message":"Testnachricht",
"Auto-connect to Last Server":"Automatisch mit dem letzten Server verbinden",
"Missing key":"❌ Fehlender Schlüssel",
@@ -1438,5 +1440,19 @@
"Still have questions?":"Hast du immer noch Fragen?",
"Join the SillyTavern Discord":"Trete dem SillyTavern Discord bei",
"Post a GitHub issue":"Veröffentliche ein GitHub-Problem",
"Contact the developers":"Kontaktiere die Entwickler"
"Contact the developers":"Kontaktiere die Entwickler",
"Interleaved Thinking":"Verschränktes Denken",
"Since Last User Message":"Seit letzter Nutzernachricht",
"Active Tool Chain":"Aktive Tool-Kette",
"openrouter_interleaved_thinking_hint":"Sendet Begründungen aus vorherigen Assistentennachrichten mit Tool-Aufrufen, um den Kontext für verschränktes Denken zu erhalten.",
"SillyTavern Logo":"SillyTavern-Logo",
"Initializing…":"Initialisierung…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Name nicht akzeptiert, da er derselbe wie zuvor ist (Groß-/Kleinschreibung und Akzente ignoriert).",
"Rename Chat":"Chat umbenennen",
"Renaming chat…":"Chat wird umbenannt…",
"Delete Chat":"Chat löschen",
"Deleting chat…":"Chat wird gelöscht…",
"Loading chat…":"Chat wird geladen…",
"Bulk Delete":"Massenlöschung",
"Deleting ${0} character(s)…":"${0} Charakter(e) werden gelöscht…"
"OpenRouter API key already exists":"La clave de API de OpenRouter ya existe",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"¿Realmente deseas crear una nueva clave de API de OpenRouter? Tu clave existente no será eliminada.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Obtenga su token de API de OpenRouter utilizando el flujo OAuth. Será redirigido a openrouter.ai",
"Bypass status check":"Saltar la verificación del estado",
"Chat Completion Source":"Fuente de Completado de Chat",
"Applies additional processing to the prompt before sending it to the API.":"Aplica procesamiento adicional al mensaje antes de enviarlo a la API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Verifica su conexión de API enviando un breve mensaje de prueba. ¡Tenga en cuenta que se le cobrará por ello!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Verifica su conexión API enviando un breve mensaje de prueba. Esto puede generar cargos de uso.",
"Test Message":"Mensaje de prueba",
"Auto-connect to Last Server":"Conexión automática al último servidor",
"Missing key":"❌ Llave faltante",
@@ -1545,5 +1547,19 @@
"Toggles sharing world tint with character sprites (This will override Character Tint)":"Alterna el tinte mundial compartido con los sprites de personajes (esto anulará el tinte de personajes)",
"Sets the expression of the user sprite":"Establece la expresión del sprite de usuario",
"Sets the user sprite set to use for the user sprite":"Establece el conjunto de sprites de usuario para usar en el sprite de usuario",
"Toggles the user sprite on the VN UI":"Alterna el sprite de usuario en la interfaz VN"
"Toggles the user sprite on the VN UI":"Alterna el sprite de usuario en la interfaz VN",
"Since Last User Message":"Desde el último mensaje del usuario",
"Active Tool Chain":"Cadena de herramientas activa",
"openrouter_interleaved_thinking_hint":"Envía razonamiento de turnos anteriores del asistente junto con solicitudes de herramientas para mantener el contexto del razonamiento intercalado.",
"SillyTavern Logo":"Logo de SillyTavern",
"Initializing…":"Inicializando…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Nombre no aceptado, ya que es el mismo que antes (ignorando mayúsculas y acentos).",
"OpenRouter API key already exists":"La clé API OpenRouter existe déjà",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Voulez-vous vraiment créer une nouvelle clé OpenRouter ? Votre clé existante ne sera pas supprimée.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Obtenez votre jeton API OpenRouter en utilisant le flux OAuth. Vous serez redirigé vers openrouter.ai",
"Bypass status check":"Contourner la vérification de l'état",
"Chat Completion Source":"Source de complétion de chat",
@@ -374,7 +376,7 @@
"Available Models":"Modèles disponibles",
"Prompt Post-Processing":"Post-traitement de prompt",
"Applies additional processing to the prompt before sending it to the API.":"Applique un traitement supplémentaire au prompt avant de l'envoyer à l'API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Vérifie votre connexion API en envoyant un court message de test. Soyez conscient que vous serez crédité pour cela !",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Vérifie votre connexion API en envoyant un court message de test. Cela peut entraîner des frais d'utilisation.",
"Test Message":"Message de test",
"Auto-connect to Last Server":"Connexion automatique au dernier serveur",
"Missing key":"❌ Clé manquante",
@@ -715,7 +717,7 @@
"Click to set a new User Name":"Cliquez pour définir un nouveau nom d'utilisateur",
"Click to lock your selected persona to the current chat. Click again to remove the lock.":"Cliquez pour verrouiller votre persona sélectionnée sur la discussion actuelle. Cliquez à nouveau pour supprimer le verrou.",
"Click to set user name for all messages":"Cliquez pour définir le nom d'utilisateur pour tous les messages",
"Persona Description":"Description de la persona",
"Persona Description":"Description du persona",
"Example: [{{user}} is a 28-year-old Romanian cat girl.]":"Exemple : [{{user}} est une fille chat roumaine de 28 ans.]",
"Tokens persona description":"Description des tokens",
"Position:":"Position :",
@@ -1516,10 +1518,10 @@
"Contain":"Contenir",
"Stretch":"Étirer",
"Center":"Centrer",
"Persona Lore Alt+Click to open the lorebook":"Lore de persona\nAlt+Click pour ouvrir le lorebook",
"persona_lore_button_title":"Lore de persona\n\nCliquer pour charger\nMajuscule/Alt-clic ou appui long pour ouvrir la fenêtre contextuelle « Lien vers le Lorebook de persona ».",
"None (disabled)":"Aucun (désactivé)",
"world_button_title":"Lore de personnage\n\nCliquer pour charger\nMajuscule-clic pour ouvrir la fenêtre contextuelle « Lien vers le Wold Info ».",
"Chat Lore Alt+Click to open the lorebook":"Lore du chat\nAlt+Click pour ouvrir le lorebook",
"world_button_title":"Lore de personnage\n\nCliquer pour charger\nMajuscule/Alt-clic ou appui long pour ouvrir la fenêtre contextuelle « Lien vers le World Info ».",
"chat_lorebook_button_title":"Lore du chat\n\nCliquer pour charger\nMajuscule/Alt-clic ou appui long pour ouvrir la fenêtre contextuelle « Lien vers le Lorebook du chat ».",
"Manual":"Manuel",
"Duplicate persona":"Dupliquer la persona",
"popup-button-crop":"Recadrer",
@@ -2012,7 +2014,7 @@
"Downloader Options":"Options de téléchargement",
"Extra parameters for downloading/HuggingFace API":"Paramètres supplémentaires pour le téléchargement/HuggingFace API.\rSi vous n'êtes pas sûr, laissez ces paramètres vides.",
"Revision":"Révision",
"Folder Name":"Nom du dossier de sortie",
"Output Folder Name":"Nom du dossier de sortie",
"HF Token":"Token HF",
"Include Patterns":"Inclure les patterns",
"Glob patterns of files to include in the download.":"Patterns globaux de fichiers à inclure dans le téléchargement.\rSéparer chaque pattern par une nouvelle ligne.",
@@ -2046,5 +2048,19 @@
"System Prompt Name":"Nom du prompt système:",
"Instruct Mode":"Mode Instruction:",
"Save and Update":"Sauvegarder et mettre à jour",
"Don't ask again for this URL":"Ne plus demander pour cette URL"
"Don't ask again for this URL":"Ne plus demander pour cette URL",
"Interleaved Thinking":"Raisonnement intercalé",
"Since Last User Message":"Depuis le dernier message utilisateur",
"Active Tool Chain":"Chaîne d'outils active",
"openrouter_interleaved_thinking_hint":"Envoie le raisonnement des tours précédents de l'assistant avec les requêtes d'outils pour conserver le contexte du raisonnement intercalé.",
"SillyTavern Logo":"Logo SillyTavern",
"Initializing…":"Initialisation…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Nom non accepté, car il est identique à l'ancien (en ignorant la casse et les accents).",
"Rename Chat":"Renommer la discussion",
"Renaming chat…":"Renommage de la discussion…",
"Delete Chat":"Supprimer la discussion",
"Deleting chat…":"Suppression de la discussion…",
"Loading chat…":"Chargement de la discussion…",
"Bulk Delete":"Suppression groupée",
"Deleting ${0} character(s)…":"Suppression de ${0} personnage(s)…"
"OpenRouter API key already exists":"OpenRouter API lykill er þegar til",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Viltu virkilega búa til nýjan OpenRouter lykil? Núverandi lykill þinn verður ekki eytt.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Fáðu API lykilinn þinn fyrir OpenRouter með því að nota OAuth strauminn. Þú verður endurvísað(ð/ur) á openrouter.ai",
"Bypass status check":"Hlaupa framhjá stöðutík",
"Chat Completion Source":"Heimild að fullvirkni spjalls",
@@ -392,7 +394,7 @@
"Available Models":"Módel í boði",
"Prompt Post-Processing":"Skjót eftirvinnsla",
"Applies additional processing to the prompt before sending it to the API.":"Beitir viðbótarvinnslu á boðunina áður en hún er send í API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Sannreynir API tengingu þína með því að senda stutt skilaboð til að prófa. Vertu meðvituð(ur/ur) um að þú færð fyrir það!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Staðfestir API tenginguna þína með því að senda stutt prufuskilaboð. Þetta gæti haft afnotagjöld í för með sér.",
"Test Message":"Prufu skilaboð",
"Auto-connect to Last Server":"Tengjast sjálfkrafa við síðustu framendurnar",
"Missing key":"❌ Vantar lykil",
@@ -1436,5 +1438,19 @@
"Still have questions?":"Ertu enn með spurningar?",
"Join the SillyTavern Discord":"Skráðu þig í SillyTavern Discord",
"Post a GitHub issue":"Senda inn GitHub málefni",
"Contact the developers":"Hafa samband við þróunaraðila"
"Contact the developers":"Hafa samband við þróunaraðila",
"Interleaved Thinking":"Fléttuð hugsun",
"Since Last User Message":"Frá síðustu notandaskilaboðum",
"Active Tool Chain":"Virk verkfærakeðja",
"openrouter_interleaved_thinking_hint":"Sendir röksemdir úr fyrri aðstoðarskilaboðum með verkfæraköllum til að viðhalda samhengi fléttaðrar hugsunar.",
"SillyTavern Logo":"SillyTavern merki",
"Initializing…":"Ræsir…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Nafn ekki samþykkt, því það er það sama og áður (hunsar há-/lágstafi og brottmerki).",
"OpenRouter API key already exists":"La chiave API di OpenRouter esiste già",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Desideri veramente creare una nuova chiave API di OpenRouter? La tua chiave esistente non verrà eliminata.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Ottieni il tuo token API di OpenRouter utilizzando il flusso OAuth. Sarai reindirizzato su openrouter.ai",
"Bypass status check":"Ignora controllo stato",
"Chat Completion Source":"Fonte di Completamento della Chat",
"Applies additional processing to the prompt before sending it to the API.":"Applica un'ulteriore elaborazione al prompt prima di inviarlo all'API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Verifica la tua connessione API inviando un breve messaggio di prova. Tieni presente che verrai accreditato per questo!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Verifica la tua connessione API inviando un breve messaggio di prova. Ciò potrebbe comportare costi di utilizzo.",
"Test Message":"Messaggio di prova",
"Auto-connect to Last Server":"Connetti automaticamente all'ultimo server",
"Missing key":"❌ Chiave mancante",
@@ -1438,5 +1440,19 @@
"Still have questions?":"Hai ancora domande?",
"Join the SillyTavern Discord":"Unisciti al SillyTavern Discord",
"Post a GitHub issue":"Pubblica un problema su GitHub",
"Contact the developers":"Contatta gli sviluppatori"
"Contact the developers":"Contatta gli sviluppatori",
"Since Last User Message":"Dall'ultimo messaggio utente",
"Active Tool Chain":"Catena di strumenti attiva",
"openrouter_interleaved_thinking_hint":"Invia il ragionamento dai turni precedenti dell'assistente con le richieste di strumenti per mantenere il contesto del ragionamento intercalato.",
"SillyTavern Logo":"Logo SillyTavern",
"Initializing…":"Inizializzazione…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Nome non accettato, poiché è lo stesso di prima (ignorando maiuscole e accenti).",
"Rename Chat":"Rinomina chat",
"Renaming chat…":"Rinominazione chat…",
"Delete Chat":"Elimina chat",
"Deleting chat…":"Eliminazione chat…",
"Loading chat…":"Caricamento chat…",
"Bulk Delete":"Eliminazione multipla",
"Deleting ${0} character(s)…":"Eliminazione di ${0} personaggio/i…"
"OpenRouter API key already exists":"OpenRouter API キーは既に存在します",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"新しい OpenRouter キーを作成してもよろしいですか?既存のキーは削除されません。",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"OAuthフローを使用してOpenRouter APIトークンを取得します。 openrouter.aiにリダイレクトされます",
"Bypass status check":"ステータスのチェックをバイパスする",
"Chat Completion Source":"チャット補完ソース",
@@ -394,7 +396,7 @@
"Available Models":"利用可能なモデル",
"Prompt Post-Processing":"迅速な後処理",
"Applies additional processing to the prompt before sending it to the API.":"プロンプトを API に送信する前に追加の処理を適用します。",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"短いテストメッセージを送信してAPI接続を検証します。それに対してクレジットが与えられることに注意してください!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"短いテストメッセージを送信してAPI接続を検証します。これにより利用料金が発生する場合があります。",
"OpenRouter API key already exists":"OpenRouter API 키가 이미 존재합니다",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"정말 새로운 OpenRouter 키를 만들기를 원하십니까? 기존 키는 삭제되지 않습니다.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"OAuth 플로우를 사용하여 OpenRouter API 토큰을 가져옵니다. openrouter.ai로 리디렉션됩니다.",
"Legacy API (pre-OAI, no streaming)":"레거시 API (OAI 이전, 스트리밍 없음)",
"Bypass status check":"상태 확인 우회",
@@ -402,7 +404,7 @@
"Prompt Post-Processing":"신속한 후처리",
"api_no_connection":"연결이 되지 않았습니다...",
"Applies additional processing to the prompt before sending it to the API.":"API로 보내기 전에 프롬프트에 추가 처리를 적용합니다.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"짧은 테스트 메시지를 보내어 API 연결을 확인합니다. 이에 대해 유료 크레딧이 지불될 수 있음을 인식하세요!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"짧은 테스트 메시지를 보내 API 연결을 확인합니다. 이로 인해 사용 요금이 부과될 수 있습니다.",
"Test Message":"테스트 메시지",
"Auto-connect to Last Server":"마지막 서버에 자동으로 연결",
"Missing key":"❌ 현재 저장된 키가 존재하지 않습니다.",
@@ -1533,7 +1535,7 @@
"Only apply color as accent":"색상은 오직 강조로써만 적용됩니다",
"OpenRouter API key already exists":"OpenRouter API-sleutel bestaat al",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Wilt u echt een nieuwe OpenRouter API-sleutel maken? Uw bestaande sleutel wordt niet verwijderd.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Haal uw OpenRouter API-token op met behulp van OAuth-flow. U wordt doorgestuurd naar openrouter.ai",
"Bypass status check":"Omzeil statuscontrole",
"Chat Completion Source":"Bron voor Chatvoltooiing",
@@ -390,7 +392,7 @@
"Available Models":"Beschikbare modellen",
"Prompt Post-Processing":"Snelle naverwerking",
"Applies additional processing to the prompt before sending it to the API.":"Past extra verwerking toe op de prompt voordat deze naar de API wordt verzonden.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Verifieert uw API-verbinding door een kort testbericht te verzenden. Wees ervan bewust dat u hiervoor wordt gecrediteerd!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Verifieert uw API-verbinding door een kort testbericht te verzenden. Hiervoor kunnen gebruikskosten in rekening worden gebracht.",
"Test Message":"Testbericht",
"Auto-connect to Last Server":"Automatisch verbinden met de laatste server",
"Missing key":"❌ Ontbrekende sleutel",
@@ -1434,5 +1436,19 @@
"Still have questions?":"Heb je nog vragen?",
"Join the SillyTavern Discord":"Word lid van de SillyTavern Discord",
"Post a GitHub issue":"Plaats een GitHub-probleem",
"Contact the developers":"Neem contact op met de ontwikkelaars"
"Contact the developers":"Neem contact op met de ontwikkelaars",
"Interleaved Thinking":"Verweven redenering",
"Since Last User Message":"Sinds laatste gebruikersbericht",
"Active Tool Chain":"Actieve toolketen",
"openrouter_interleaved_thinking_hint":"Verstuurt redenering uit eerdere assistentbeurten met tool-aanvragen om de context van verweven redenering te behouden.",
"SillyTavern Logo":"SillyTavern-logo",
"Initializing…":"Initialiseren…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Naam niet geaccepteerd, omdat deze hetzelfde is als voorheen (hoofdletters en accenten genegeerd).",
"OpenRouter API key already exists":"A chave de API do OpenRouter já existe",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Você realmente deseja criar uma nova chave OpenRouter? Sua chave existente não será excluída.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Obtenha seu token da API do OpenRouter usando o fluxo OAuth. Você será redirecionado para openrouter.ai",
"Bypass status check":"Ignorar verificação de status",
"Chat Completion Source":"Fonte de conclusão de chat",
"Applies additional processing to the prompt before sending it to the API.":"Aplica processamento adicional ao prompt antes de enviá-lo para a API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Verifica sua conexão com a API enviando uma mensagem de teste curta. Esteja ciente de que você será creditado por isso!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Verifica a ligação à API ao enviar uma mensagem de teste curta. Isto pode implicar custos de utilização.",
"Test Message":"Mensagem de Teste",
"Auto-connect to Last Server":"Conectar-se automaticamente ao último servidor",
"Missing key":"❌ Chave faltando",
@@ -1436,5 +1438,19 @@
"Still have questions?":"Ainda tem perguntas?",
"Join the SillyTavern Discord":"Junte-se ao Discord do SillyTavern",
"Post a GitHub issue":"Publicar um problema no GitHub",
"Contact the developers":"Contatar os desenvolvedores"
"Contact the developers":"Contatar os desenvolvedores",
"Interleaved Thinking":"Raciocínio intercalado",
"Since Last User Message":"Desde a última mensagem do utilizador",
"Active Tool Chain":"Cadeia de ferramentas ativa",
"openrouter_interleaved_thinking_hint":"Envia o raciocínio de turnos anteriores do assistente com pedidos de ferramentas para manter o contexto de raciocínio intercalado.",
"SillyTavern Logo":"Logótipo do SillyTavern",
"Initializing…":"A inicializar…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Nome não aceite, pois é o mesmo que antes (ignorando maiúsculas e acentos).",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Получите свой OpenRouter API токен используя OAuth. У вас будет открыта вкладка openrouter.ai",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Проверка работоспособности вашего соединенияс API путём отправки короткого тестового сообщения. Внимание: оно будет отправлено от вашего имени.",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Проверяет соединениес API, отправляя короткое тестовое сообщение. Это может повлечь плату за использование.",
"Edit":"Редактировать",
"Locked = World Editor will stay open":"Закреплено = Редактор мира останется открытым",
"Entries can activate other entries by mentioning their keywords":"Записи могут активировать другие записи, если в них содержатся ключевые слова",
@@ -758,6 +758,8 @@
"Doesn't work? Try adding":"Не работает? Попробуйте добавить в конце",
"at the end!":"!",
"Authorize":"Авторизоваться",
"OpenRouter API key already exists":"Ключ API OpenRouter уже существует",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Вы действительно хотите создать новый ключ OpenRouter? Ваш существующий ключ не будет удален.",
"No persona description":"[Нет описания]",
"Not connected to API!":"Нет соединения с API!",
"Type a message, or /? for help":"Введите сообщение, или /? для получения справки",
@@ -1902,7 +1904,7 @@
"Save":"Сохранить",
"Chat Lorebook":"Лорбук для чата",
"chat_world_template_txt":"Выбранный мир будет привязан к этому чату. Будет работать наряду с глобальным лорбуком и лором персонажа.",
"world_button_title":"Лор персонажа\n\nНажмите, чтобы загрузить\nShift + ЛКМ, чтобы открыть диалог привязки мира",
"world_button_title":"Лор персонажа\n\nНажмите, чтобы загрузить\nShift / Alt + ЛКМ или долгое нажатие, чтобы открыть диалог привязки мира",
"No auxillary Lorebooks set. Click here to select.":"Вспомогательный лорбук не выбран. Нажмите, чтобы выбрать.",
"ext_regex_ai_input_desc":"Полученные от API ответы.",
@@ -2128,7 +2130,7 @@
"openai_reasoning_effort_low":"Поверхностные",
"openai_reasoning_effort_medium":"Обычные",
"openai_reasoning_effort_high":"Подробные",
"Persona Lore Alt+Click to open the lorebook":"Лорбук данной персоны\nAlt + ЛКМ чтобы открыть лорбук",
"persona_lore_button_title":"Лорбук данной персоны\n\nНажмите, чтобы открыть\nShift / Alt + ЛКМ или долгое нажатие, чтобы открыть диалог привязки лорбука",
"Persona Lorebook for":"Лорбук для персоны",
"persona_world_template_txt":"Выбранный мир будет привязан к этой персоне. Будет работать вместе с глобальным лорбуком и лорбуками персонажа и чата.",
"Global list":"Глобальный список",
@@ -2143,7 +2145,7 @@
"Enter a valid API URL":"Введите корректный адрес API",
"No Ollama model selected.":"Не выбрана модель Ollama",
"Background Fitting":"Способ подгонки фона под разрешение",
"Chat Lore Alt+Click to open the lorebook":"Лорбук данного чата\nAlt + ЛКМ чтобы открыть лорбук",
"chat_lorebook_button_title":"Лорбук данного чата\n\nНажмите, чтобы открыть\nShift / Alt + ЛКМ или долгое нажатие, чтобы открыть диалог привязки лорбука",
"Token Counter":"Подсчитать токены",
"Type / paste in the box below to see the number of tokens in the text.":"Введите или вставьте текст в окошко ниже, чтобы подсчитать количество токенов в нём.",
"Selected tokenizer:":"Выбранный токенайзер:",
@@ -2738,5 +2740,19 @@
"Uses the voices provided by your operating system":"Используем стандартные голоса вашей ОС",
"Your browser or operating system doesn't support speech synthesis":"Ваш браузер либо ОС не поддерживают синтез речи",
"Works best when: Pass Asterisks to TTS Engine is enabled, and both Only narrate quotes and Ignore *text, even 'quotes', inside asterisks* are disabled.":"Работает лучше всего, когда: одновременно включена опция \"Передавать звёздочки TTS-движку\", а также отключены обе опции: \"Не озвучивать *текст, даже \"в кавычках\", если он внутри звёздочек*\", и \"Озвучивать только текст \"в кавычках\"\"",
"openrouter_interleaved_thinking_hint":"Отправляет рассуждение из предыдущих ходов ассистента вместе с запросами вызова инструментов, чтобы сохранять контекст чередующегося рассуждения.",
"SillyTavern Logo":"Логотип SillyTavern",
"Initializing…":"Инициализация…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Имя не принято, так как оно совпадает с предыдущим (игнорируя регистр и акценты).",
"OpenRouter API key already exists":"คีย์ API ของ OpenRouter มีอยู่แล้ว",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"คุณต้องการสร้างคีย์ OpenRouter ใหม่จริง ๆ หรือไม่ คีย์ที่มีอยู่ของคุณจะไม่ถูกลบ",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"โปรดเข้าสู่ระบบเพื่อรับ OpenRouter API Token โดยใช้ OAuth Flow จากนั้นคุณจะถูกเปลี่ยนเส้นทางไปยังเว็บไซต์ของ openrouter.ai",
"Applies additional processing to the prompt before sending it to the API.":"ใช้การประมวลผลเพิ่มเติมกับพรอมต์ก่อนส่งไปยัง API",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"ตรวจสอบการเชื่อมต่อ API โดยส่งข้อความทดสอบสั้นๆ โปรดทราบว่าคุณจะถูกเรียกเก็บเงินสำหรับการทดสอบนี้!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"ตรวจสอบการเชื่อมต่อ API โดยส่งข้อความทดสอบสั้นๆ ซึ่งอาจมีค่าใช้จ่ายในการใช้งาน",
"Test Message":"ทดสอบการส่งข้อความ",
"Auto-connect to Last Server":"เชื่อมต่อเซิฟเวอร์อัตโนมัติ",
"Name not accepted, as it is the same as before (ignoring case and accents).":"ชื่อไม่ได้รับการยอมรับ เนื่องจากเหมือนกับก่อนหน้านี้ (ไม่สนใจตัวพิมพ์ใหญ่เล็กและเครื่องหมายเสียง)",
"OpenRouter API key already exists":"API ключ OpenRouter вже існує",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Ви дійсно бажаєте створити новий ключ OpenRouter API? Ваш існуючий ключ не буде видалено.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Отримайте свій токен API OpenRouter за допомогою OAuth. Вас буде перенаправлено на openrouter.ai",
"Applies additional processing to the prompt before sending it to the API.":"Застосовує додаткову обробку запиту перед надсиланням його в API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Підтверджує ваше підключення до API, надсилаючи коротке тестове повідомлення. Пам'ятайте, що ви будете платити за це!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Перевіряє підключення до API, надсилаючи коротке тестове повідомлення. За це може стягуватися плата за використання.",
"Test Message":"Тестове повідомлення",
"Auto-connect to Last Server":"Автоматичне підключення до останнього сервера",
"Missing key":"❌ Відсутній ключ",
@@ -1436,5 +1438,19 @@
"Still have questions?":"Все ще є питання?",
"Join the SillyTavern Discord":"Приєднуйтесь до SillyTavern Discord",
"Post a GitHub issue":"Опублікуйте проблему на GitHub",
"Contact the developers":"Зв'яжіться з розробниками"
"Contact the developers":"Зв'яжіться з розробниками",
"Interleaved Thinking":"Черговане мислення",
"Since Last User Message":"Від останнього повідомлення користувача",
"openrouter_interleaved_thinking_hint":"Надсилає міркування з попередніх ходів асистента разом із запитами виклику інструментів, щоб зберегти контекст чергованого мислення.",
"SillyTavern Logo":"Логотип SillyTavern",
"Initializing…":"Ініціалізація…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Ім'я не прийнято, оскільки воно збігається з попереднім (ігноруючи регістр та акценти).",
"OpenRouter API key already exists":"Key API OpenRouter đã tồn tại",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"Bạn có thực sự muốn tạo khóa OpenRouter mới không? Khóa hiện có của bạn sẽ không bị xóa.",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"Nhận mã thông báo API OpenRouter của bạn bằng cách sử dụng luồng OAuth. Bạn sẽ được chuyển hướng đến openrouter.ai",
"Bypass status check":"Bỏ qua check trạng thái",
"Chat Completion Source":"Nguồn cho Chat Completion",
@@ -392,7 +394,7 @@
"Available Models":"Các Model hiện có",
"Prompt Post-Processing":"Xử lý hậu kỳ Prompt",
"Applies additional processing to the prompt before sending it to the API.":"Áp dụng xử lý bổ sung cho Prompt trước khi gửi nó tới API.",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"Xác minh kết nối API của bạn bằng cách gửi một tin nhắn kiểm tra ngắn. Hãy nhớ rằng bạn sẽ được ghi nhận về điều đó!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"Xác minh kết nối API của bạn bằng cách gửi tin nhắn kiểm tra ngắn. Việc này có thể phát sinh phí sử dụng.",
"Test Message":"Test tin nhắn",
"Auto-connect to Last Server":"Tự động kết nối với link trước đó",
"Missing key":"❌ Thiếu Key",
@@ -1436,5 +1438,19 @@
"Still have questions?":"Bạn còn thắc mắc?",
"Join the SillyTavern Discord":"Tham gia Kênh Discord của SillyTavern",
"Post a GitHub issue":"Đăng một vấn đề trên GitHub",
"Contact the developers":"Liên hệ với Devs"
"Contact the developers":"Liên hệ với Devs",
"Interleaved Thinking":"Lập luận xen kẽ",
"Since Last User Message":"Kể từ tin nhắn người dùng gần nhất",
"Active Tool Chain":"Chuỗi công cụ đang hoạt động",
"openrouter_interleaved_thinking_hint":"Gửi lập luận từ các lượt trợ lý trước đó cùng với yêu cầu gọi công cụ để duy trì ngữ cảnh lập luận xen kẽ.",
"SillyTavern Logo":"Logo SillyTavern",
"Initializing…":"Đang khởi tạo…",
"Name not accepted, as it is the same as before (ignoring case and accents).":"Tên không được chấp nhận vì giống như trước đó (bỏ qua chữ hoa/thường và dấu).",
"Rename Chat":"Đổi tên cuộc trò chuyện",
"Renaming chat…":"Đang đổi tên cuộc trò chuyện…",
"Delete Chat":"Xóa cuộc trò chuyện",
"Deleting chat…":"Đang xóa cuộc trò chuyện…",
"Loading chat…":"Đang tải cuộc trò chuyện…",
"Bulk Delete":"Xóa hàng loạt",
"Deleting ${0} character(s)…":"Đang xóa ${0} nhân vật…"
"OpenRouter API key already exists":"OpenRouter API 密鑰已存在",
"Do you really wish to create a new OpenRouter key? Your existing key will not be deleted.":"您確定要建立新的 OpenRouter API 金鑰嗎?您現有的金鑰不會被刪除。",
"Get your OpenRouter API token using OAuth flow. You will be redirected to openrouter.ai":"使用 OAuth 流程取得您的 OpenRouter API 符元。您將被重新導向到 openrouter.ai",
"Bypass status check":"繞過狀態檢查",
"Chat Completion Source":"聊天補全來源",
@@ -391,7 +393,7 @@
"Available Models":"可用模型",
"Prompt Post-Processing":"提示詞後處理",
"Applies additional processing to the prompt before sending it to the API.":"這個選項會在將提示詞送往 API 之前,對它進行額外的處理。",
"Verifies your API connection by sending a short test message. Be aware that you'll be credited for it!":"透過傳送簡短的測試訊息來驗證您的 API 連線。請注意,您將因此獲得榮譽!",
"Verifies your API connection by sending a short test message. This may incur usage charges.":"透過傳送簡短的測試訊息來驗證您的 API 連線。這可能會產生使用費用。",
"Test Message":"測試訊息",
"Auto-connect to Last Server":"自動連線至上次使用的伺服器",
"Missing key":"❌ 鑰匙遺失",
@@ -1541,7 +1543,7 @@
"When enabled, nodes that have swipes splitting off of them will appear subtly larger, in addition to having the double border.":"啟用後,具分支滑動的節點將顯示雙重邊框,還會略微放大。",
"Functions in this category are for advanced users only. Don't click anything if you're not sure about the consequences.":"此類功能僅供高階使用者使用。若不確定後果,請勿點選任何內容。",
"Are you sure you want to delete this user?":"確定要刪除該使用者嗎?",
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.