gitea/conjurer
1
0
Fork 0
mirror of https://github.com/migatu/conjurer.git synced 2026-07-14 21:38:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

ai: single-switch GPT/Claude backend for the chat cog

Browse Source 
Wire the bot's AI chat pipeline (ai_functions.handle_response) to talk to
either OpenAI or the Anthropic Messages API, chosen by one active-config
switch. Behaviour on the default "gpt" config is unchanged.

constants.py:
* guarded `import anthropic` + CLAUDECLIENT (mirrors OPENAICLIENT), netrc
  machine 'anthropic' / ANTHROPIC_API_KEY;
* CLAUDE_LATEST_MODEL / CLAUDE_CHEAP_MODEL (opus-4-8 / haiku-4-5);
* AI_CONFIGS + DEFAULT_AI_CONFIG loaded from an optional 3rd element of
  system_gpt_settings.json (backward compatible - a 2-element file falls
  back to built-in defaults, active "gpt"). Single switch: CONJURER_AI_CONFIG
  env > settings "active" > "gpt".

ai_functions.py:
* provider_generate() dispatches to OpenAI (unchanged openai_call) or the new
  _anthropic_call() (splits system out, alternating messages, max_tokens,
  temperature omitted - Opus 4.8 rejects sampling params);
* AIError normalises both SDKs' exceptions into one category set so
  handle_response keeps its single set of in-character error replies;
* select_model() reads the active config; legacy "gpt-4o" default auto-maps
  to the active provider's model so the switch actually changes the backend;
* set_active_ai_config()/list_ai_configs() with best-effort persistence back
  into system_gpt_settings.json index 2.

ai_commands.py:
* $gadaj_teraz <config> hybrid command (Vykidailo-gated) switches backend at
  runtime;
* graceful guards when OPENAICLIENT is None: personal assistants (OpenAI
  Assistants API) and DALL-E image gen degrade instead of crashing, so a
  Claude-only deployment boots.

system_gpt_settings.json: add the configs block (gpt/claude/_template) as the
collection point for future backends. requirements_bot.txt: add anthropic.
bot.env.example: ANTHROPIC_API_KEY + CONJURER_AI_CONFIG. Unit tests cover the
message splitter, model selection, config listing, and error mapping.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Michal Tuszowski
2026-07-09 21:34:59 +02:00
parent 4bde02e992
commit 3d9d47aa90
8 changed files with 572 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/unit/test_constants.py
+15
View File
@@ -33,3 +33,18 @@ def test_conan_defaults_present():
# Feature toggles default to "off" so the bridge stays dormant.
assert constants.CONAN_JOIN_CHANNEL_ID == 0
assert constants.CONAN_RCON_HOST == ""
def test_ai_configs_expose_gpt_and_claude_backends():
cfgs = constants.AI_CONFIGS
assert cfgs["gpt"]["provider"] == "openai"
assert cfgs["claude"]["provider"] == "anthropic"
# Claude carries a max_tokens (Anthropic requires it) and omits temperature
# (Opus 4.8 / Sonnet 5 reject sampling params).
assert "max_tokens" in cfgs["claude"]
assert "temperature" not in cfgs["claude"]
def test_default_ai_config_is_a_known_config():
# The single startup switch must always resolve to a real, selectable config.
assert constants.DEFAULT_AI_CONFIG in constants.AI_CONFIGS