Commit Graph
26 Commits
Author SHA1 Message Date
jie65535 7a0969dc4e profile: return complete query results 2026-08-04 23:58:47 +08:00
jie65535 31803396a8 profile: require pending messages for bulk runs 2026-08-04 23:57:10 +08:00
jie65535 74bcf0b8d6 profile: rebase concurrent conversation updates 2026-08-03 17:58:58 +08:00
jie65535 94f303ec72 profile: optimize conversation analysis concurrency 2026-08-03 16:39:19 +08:00
jie65535 b96b732b92 profile: analyze all groups concurrently 2026-08-03 15:38:28 +08:00
jie65535 2ba5752494 retry: add exponential backoff 2026-08-03 15:28:11 +08:00
jie65535 fa93d48002 profile: parallelize and control analysis jobs 2026-08-03 11:55:21 +08:00
jie65535 2a5e7fd2f9 profile: add Overflow contact snapshots 2026-08-03 10:39:56 +08:00
jie65535 f102264a55 profile: harden batch analysis and compaction 2026-08-03 02:53:59 +08:00
jie65535 23299b2ae7 profile: add progressive user profiles
Add cache-expiry profile maintenance and contextual injection, reorganize runtime code by responsibility, remove automatic favorability decay, and prepare version 1.15.0.
2026-08-02 21:45:34 +08:00
jie65535 2ed39e9fe8 docs: update token command documentation 2026-07-29 10:08:19 +08:00
jie65535 07d11c2b16 history: replace external recorder with SQLite 2026-07-27 22:19:35 +08:00
jie65535 a4f5bad322 tools: improve visual image handling 2026-07-26 14:43:34 +08:00
jie65535 7b5a83ba9c tools: integrate QWeather JWT weather service
Replace the unavailable weather endpoint with QWeather location, forecast, minutely precipitation, and alert APIs. Add configurable JWT credentials, automatic alert lookup, setup documentation, and bump the plugin to 1.13.0.
2026-07-24 11:13:26 +08:00
jie65535andClaude Opus 4.8 826dc460df Add chat endpoint failover for resilience against unstable LLM APIs
Configure a list of fallback chat endpoints (chatFallbacks); each blank
field inherits the primary, so you can swap just the API key, just the
model, or the whole vendor. On LLM streaming failure the retry loop
advances to the next endpoint, and a failed endpoint enters a cooldown
(fallbackCooldownMinutes) so a dead primary is skipped instead of
wasting a timeout on every message.

Co-Authored-By: Claude Opus 4.8 <[email protected]>
2026-06-24 22:23:43 +08:00
jie65535andClaude Opus 4.8 4307019ee8 Add global skill system for self-accumulated knowledge
Introduce a cross-group skill system that lets the bot distill reusable
knowledge into markdown docs and load them on demand, keeping day-to-day
context pollution low.

- SkillStore manages data/skills/*.md files with name/description
  frontmatter and an in-memory index cache (rebuilt on init/reload)
- Only the skill index (name + one-line description) is injected via the
  new {skills} system-prompt placeholder; bodies load on demand
- New tools: loadSkill / saveSkill (upsert, iterate = load+overwrite) /
  deleteSkill, gated by PluginConfig.skillsEnabled
- Skill names validated against ^[A-Za-z0-9_-]+$ to prevent traversal
- Wire SkillStore.init into onEnable and refresh on /jgpt reload; add
  /jgpt skills listing command
- Bump version to 1.12.0; update README

Co-Authored-By: Claude Opus 4.8 <[email protected]>
2026-06-20 23:37:44 +08:00
jie65535andClaude Opus 4.7 92acbb2310 Upgrade TTS to qwen3-tts-instruct-flash with instruction control
Adds an optional instructions parameter to sendVoiceMessage so the model
can describe tone, pace and emotion in natural language. Defaults the
TTS model to qwen3-tts-instruct-flash; Chelsie voice is unchanged.

Co-Authored-By: Claude Opus 4.7 <[email protected]>
2026-05-22 15:57:15 +08:00
jie65535andClaude Opus 4.7 39b49bb302 Replace ImageEdit with ImageAgent for Qwen Image 2.0
Supports text-to-image, single-image edit and multi-image fusion (0-3
reference images) via a single tool. Renames imageEditModel config to
imageModel (default qwen-image-2.0) and adds imageWatermark toggle.

Co-Authored-By: Claude Opus 4.7 <[email protected]>
2026-05-22 15:47:08 +08:00
jie65535 98bb1066c4 Update README 2026-05-22 14:16:18 +08:00
jie65535 e629d37fa8 Relax searchChatHistory limits 2026-05-22 14:15:54 +08:00
jie65535 200a404927 Update README for v1.11.0 2026-05-22 14:15:48 +08:00
jie65535andClaude Sonnet 4.6 2d3045e110 Add tokens report command and optimize statistics queries
- Add /jgpt tokens [days] command for usage summary report
- Add /jgpt tokensUserDaily <userId> [days] for daily user stats
- Fix tokensDaily day calculation (was showing 4 days for 3-day query)
- Optimize tokens() from 5-6 passes to single pass (5-10x faster)
- Fix tokensUserDaily inefficient nickname lookup
- Add number formatting with thousand separators to all outputs
- Extract helper functions: calculateCutoffTimestamp, calculateTodayStartTimestamp
- Add parameter validation for days and limit
- Update README with new commands and formatted examples

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
2026-03-25 12:36:11 +08:00
jie65535 b0c985e220 Add token consumption tracking system Update version to v1.10.0 2026-03-18 12:09:23 +08:00
jie65535 0f482407d4 Add favorability system
Update version to v1.9.0
2025-10-30 15:03:38 +08:00
jie65535 ffa7f78c25 Update README by Qwen 2025-09-10 11:12:30 +08:00
jie65535 f7b05cc8e0 Add README 2023-12-17 14:45:18 +08:00