Update CHANGELOG

This commit is contained in:
Griatch 2024-12-15 16:11:54 +01:00
parent bf94618e41
commit 40aac81314
3 changed files with 53 additions and 4 deletions

View File

@ -1,5 +1,29 @@
# Changelog
## Main branch
- [Feat][pull3633]: Default object's default descs are now taken from a `default_description`
class variable instead of the `desc` Attribute always being set (count-infinity)
- [Fix][pull3677]: Make sure that `DefaultAccount.create` normalizes to empty
strings instead of `None` if no name is provided, also enforce string type (InspectorCaracal)
- [Fix][pull3682]: Allow in-game help searching for commands natively starting
with `*` (which is the Lunr search wildcard) (count-infinity)
- [Fix][pull3684]: Web client stopped auto-focusing the input box after opening
settings (count-infinity)
- [Fix][pull3689]: Partial matching fix in default search, makes sure e.g. `b sw` uniquely
finds `big sword` even if another type of sword is around (InspectorCaracal)
- [Fix][pull3690]: In searches, allow special 'here' and 'me' keywords only be valid queries
unless current location and/or caller is in valid search candidates respectively (InspectorCaracal)
- [Docs]: Fixes from InspectorCaracal
[pull3633]: https://github.com/evennia/evennia/pull/3633
[pull3677]: https://github.com/evennia/evennia/pull/3677
[pull3682]: https://github.com/evennia/evennia/pull/3682
[pull3684]: https://github.com/evennia/evennia/pull/3684
[pull3689]: https://github.com/evennia/evennia/pull/3689
[pull3690]: https://github.com/evennia/evennia/pull/3690
## Evennia 4.5.0
Nov 12, 2024

View File

@ -1,5 +1,29 @@
# Changelog
## Main branch
- [Feat][pull3633]: Default object's default descs are now taken from a `default_description`
class variable instead of the `desc` Attribute always being set (count-infinity)
- [Fix][pull3677]: Make sure that `DefaultAccount.create` normalizes to empty
strings instead of `None` if no name is provided, also enforce string type (InspectorCaracal)
- [Fix][pull3682]: Allow in-game help searching for commands natively starting
with `*` (which is the Lunr search wildcard) (count-infinity)
- [Fix][pull3684]: Web client stopped auto-focusing the input box after opening
settings (count-infinity)
- [Fix][pull3689]: Partial matching fix in default search, makes sure e.g. `b sw` uniquely
finds `big sword` even if another type of sword is around (InspectorCaracal)
- [Fix][pull3690]: In searches, allow special 'here' and 'me' keywords only be valid queries
unless current location and/or caller is in valid search candidates respectively (InspectorCaracal)
- [Docs]: Fixes from InspectorCaracal
[pull3633]: https://github.com/evennia/evennia/pull/3633
[pull3677]: https://github.com/evennia/evennia/pull/3677
[pull3682]: https://github.com/evennia/evennia/pull/3682
[pull3684]: https://github.com/evennia/evennia/pull/3684
[pull3689]: https://github.com/evennia/evennia/pull/3689
[pull3690]: https://github.com/evennia/evennia/pull/3690
## Evennia 4.5.0
Nov 12, 2024

View File

@ -66,7 +66,8 @@ LLM_PATH = "/api/v1/generate"
# if you wanted to authenticated to some external service, you could
# add an Authenticate header here with a token
LLM_HEADERS = {"Content-Type": "application/json"}
# note that the content of each header must be an iterable
LLM_HEADERS = {"Content-Type": ["application/json"]}
# this key will be inserted in the request, with your user-input
LLM_PROMPT_KEYNAME = "prompt"
@ -77,7 +78,7 @@ LLM_REQUEST_BODY = {
"temperature": 0.7, # 0-2. higher=more random, lower=predictable
}
# helps guide the NPC AI. See the LLNPC section.
LLM_PROMPT_PREFIx = (
LLM_PROMPT_PREFIX = (
"You are roleplaying as {name}, a {desc} existing in {location}. "
"Answer with short sentences. Only respond as {name} would. "
"From here on, the conversation between {name} and {character} begins."
@ -148,8 +149,8 @@ Here is an untested example of the Evennia setting for calling [OpenAI's v1/comp
```python
LLM_HOST = "https://api.openai.com"
LLM_PATH = "/v1/completions"
LLM_HEADERS = {"Content-Type": "application/json",
"Authorization": "Bearer YOUR_OPENAI_API_KEY"}
LLM_HEADERS = {"Content-Type": ["application/json"],
"Authorization": ["Bearer YOUR_OPENAI_API_KEY"]}
LLM_PROMPT_KEYNAME = "prompt"
LLM_REQUEST_BODY = {
"model": "gpt-3.5-turbo",