Commit Graph

945 Commits

Author SHA1 Message Date
bangonicdd
9773dc48a9 fix: adjust pipelineness in prev PR for easing further managing 2025-02-15 00:41:15 +09:00
bangonicdd
b783dc9874 feat: reintroduce module integration 2025-02-10 09:02:57 +09:00
kwaroran
852a629a34 fix: stringify object in HypaProcesser to display actual error content instead of [object Object] (#753)
# PR Checklist
- [x] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [x] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?

# Description

![1](https://github.com/user-attachments/assets/04012607-375c-4128-abf0-50ef6daae3b6)

The error messages were not properly displayed, showing [object Object]
instead of the actual content.
<br>


![2](https://github.com/user-attachments/assets/5ff217ab-cb50-41e1-b2eb-a9ba8eeef094)

This PR improves error handling to display actual error content.
2025-02-09 16:25:09 +09:00
kwaroran
7e71d03d21 Merge branch 'main' into patch-25 2025-02-09 16:24:49 +09:00
Bo26fhmC5M
80ba79e2ab fix: stringify object in HypaProcesser to display actual error content instead of [object Object] 2025-02-08 21:33:34 +09:00
Bo26fhmC5M
fb941148e0 feat: add trigger effect RunAxLLM 2025-02-08 17:15:45 +09:00
Bo26fhmC5M
60118e6e8f Merge branch 'kwaroran:main' into patch-23 2025-02-08 14:48:56 +09:00
Bo26fhmC5M
2d455840a4 feat: add localization for HypaV3 settings and modal 2025-02-08 02:17:35 +09:00
Bo26fhmC5M
2fa11ebbe4 fix: add length check before summarization in HypaV3 2025-02-07 23:31:41 +09:00
Bo26fhmC5M
6d79f45d32 feat: add doNotSummarizeUserChat option in HypaV3
- Add doNotSummarizeUserChat option to exclude user messages from summarization
- Add early return logic to prevent unnecessary similarity checks when summaries are empty
2025-02-07 21:08:50 +09:00
bangonicdd
ef6f671792 feat: custom toggles for modules 2025-02-06 19:45:55 +09:00
Kwaroran
7b57bdf5f1 Merge branch 'main' of https://github.com/kwaroran/RisuAI 2025-02-06 09:49:23 +09:00
Kwaroran
1b171cab66 Update version, gemini models, and new progress dialoge, and charxjpeg 2025-02-06 09:48:55 +09:00
bangonicdd
ad6f7e0be4 feat: charjs style button trigger 2025-02-04 09:04:55 +09:00
Kwaroran
243984d788 Add CharX-Jpeg 2025-02-02 07:49:08 +09:00
Kwaroran
25aa83877b Add reasoning effort 2025-02-01 09:05:07 +09:00
Kwaroran
3139eac739 Add paste post 2025-01-31 23:04:01 +09:00
Kwaroran
614f7b2f17 fix: improve error handling in chat message logging 2025-01-31 17:39:34 +09:00
Kwaroran
757a944686 Add inlayErrorResponse 2025-01-31 17:38:14 +09:00
Kwaroran
338d1cfec2 Add models 2025-01-29 05:38:26 +09:00
Kwaroran
62ea10cc32 fix: remove logit_bias from request body if empty 2025-01-29 04:25:59 +09:00
kwaroran
e073d66bca feat: improve HypaV3 (#721)
# PR Checklist
- [x] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [x] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [x] Have you added type definitions?

# Description
- feat: add translate button to HypaV3 modal
- feat: add dual-action translation (cached/regenerate) in HypaV3 modal
- Implements shift+click (desktop) and double tap (mobile) for
regenerating translations while maintaining regular click/tap for cached
translations.
- feat: improve ratio sliders interaction in HypaV3 settings
- feat: add lastSelectedSummaries property to store selected memory
indices
- feat: display next message to be summarized in HypaV3 modal
2025-01-17 22:54:08 +09:00
kwaroran
1d98a63d4c feat: apply positionParser to alternate global note (#724)
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?

# Description
This PR ensures that the 'position' lorebook decorator is correctly
applied to alternate (replaced) GlobalNotes.
Thank you for your time and consideration.
2025-01-17 22:53:45 +09:00
bangonicdd
172efe4d68 suggestion: apply 'processScriptFull()' to 'editprocess' mode regex script 2025-01-17 03:58:20 +09:00
bangonicdd
23fd706d9b feat: apply positionParser to alternate global note 2025-01-17 00:23:14 +09:00
Bo26fhmC5M
3c62317f3a feat: add lastSelectedSummaries property to store selected memory indices 2025-01-17 00:17:12 +09:00
Bo26fhmC5M
6a13b33103 refactor: extract repeated summarization logic into retryableSummarize function 2025-01-16 23:36:32 +09:00
Bo26fhmC5M
fac11bfe67 fix: improve HypaV3 logging 2025-01-16 22:40:08 +09:00
Bo26fhmC5M
3e234dcb15 feat: add dual-action translation (cached/regenerate) in HypaV3 modal
Implements shift+click (desktop) and double tap (mobile) for regenerating translations while maintaining regular click/tap for cached translations.
2025-01-15 13:45:34 +09:00
Bo26fhmC5M
a10a2c5502 refactor: extract HypaV3 modal into separate component 2025-01-14 13:01:14 +09:00
Bo26fhmC5M
f3c6278d21 feat: add important button in HypaV3 Data modal 2025-01-13 23:30:18 +09:00
Bo26fhmC5M
4176a647a5 fix: restore undefined value from null after importing hypaDataV3 2025-01-13 19:31:24 +09:00
Bo26fhmC5M
a1158ebdb1 fix: adjust memory selection order 2025-01-13 14:09:18 +09:00
Bo26fhmC5M
cfdd5d6bf5 fix: resolve summarize function issues with instruct35 2025-01-13 13:30:10 +09:00
Bo26fhmC5M
04e640a791 refactor: improve array conversion and sorting syntax 2025-01-13 13:02:22 +09:00
Bo26fhmC5M
ab7a2aa499 feat: add resummarize button to HypaV3 Data modal 2025-01-12 23:32:20 +09:00
Bo26fhmC5M
f08c31612b fix: prevent over-summarization and improve logging 2025-01-12 17:15:11 +09:00
Bo26fhmC5M
6e49970b76 fix: correct targetTokens calculation in summarization and improve logging 2025-01-12 14:49:01 +09:00
Bo26fhmC5M
85bdf1d544 fix: improve memory token tracking and logging 2025-01-12 13:17:56 +09:00
Bo26fhmC5M
50361d7aa2 feat: Implement HypaV3 ratio-based memory 2025-01-12 11:05:18 +09:00
kwaroran
c363d50aa3 fix: gemini multimodal (#712)
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?

# Description
fix gemini multimodal error.
ERROR MESSAGE : Invalid value at 'contents[6].parts[1]' (oneof), oneof
field 'data' is already set. Cannot set 'text'
2025-01-11 01:44:30 +09:00
kwaroran
edb4964da7 fix: Fix message handling and summarization in HypaV2 (#711)
# PR Checklist
- [x] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [x] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?

# Description
This PR addresses several issues in the HypaV2 memory system:

1. Improved Summarization Error Handling
- Before: When unable to summarize messages while exceeding context
size, HypaV2 would continue and make API requests with unintentionally
truncated context
- After: HypaV2 now provides clear error messages asking users to adjust
their settings when:
  - Unable to summarize last 4 messages
  - A single message exceeds chunk size

2. Message Order Preservation
- Before: lastTwoChats logic was causing the first message (index 1) and
user input (index 2) to appear in the wrong order
- After: Fixed by adjusting the initial index to preserve the original
message sequence

3. Message Filtering
- Added logic to skip unnecessary messages during summarization:
  - Excludes [Start a new chat] message at index 0
  - Skips empty messages
<br>
Requesting review from @LightningHyperBlaze45654
2025-01-11 01:44:10 +09:00
kwaroran
9896b68b7a fix: resolve state_unsafe_mutation in getChatVar() (#707)
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?

# Description
While investigating an issue where `{{getvar::A}}` didn't work properly
in background embedding, I encountered a `state_unsafe_mutation` error.
It appears that modifying the null check operator on the relevant line
can resolve this issue. Thank for your time.
2025-01-11 01:44:01 +09:00
Bo26fhmC5M
7c1faee6f4 fix: Fix message handling and summarization in HypaV2
- Add clear error messages when summarization is not possible
- Fix message order issues caused by lastTwoChats logic
- Skip [Start a new chat] and empty messages during summarization
2025-01-08 20:45:19 +09:00
donmarble
2d11b05e6c fix: gemini multimodal text 2025-01-07 23:45:01 +09:00
Kwaroran
9fc8978d1d Add GeminiBlockOff 2025-01-07 00:05:20 +09:00
bangonicdd
6537e0926c fix: add missing check for regex order flag 2025-01-06 15:39:57 +09:00
Kwaroran
c0e1311568 Add branches 2025-01-06 00:24:03 +09:00
Bo26fhmC5M
0317a941f1 fix: token calculation for HypaV2 2025-01-02 20:52:37 +09:00
Bo26fhmC5M
2b92582df4 fix: resolve chatMemos serialization issue in HypaV2Data 2025-01-02 18:47:16 +09:00