let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,512 Commits 1 Branch 0 Tags
8d74578ceb0c3b913555dff6265821eb0fc09749
Commit Graph

1027 Commits

Author SHA1 Message Date
Tyler Yust
8d74578ceb feat: native image injection for vision-capable models 
- Auto-detect and load images referenced in user prompts
- Inject history images at their original message positions
- Fix EXIF orientation - rotate before resizing in resizeToJpeg
- Sandbox security: validate paths, block remote URLs when sandbox enabled
- Prevent duplicate history image injection across turns
- Handle string-based user message content (convert to array)
- Add bounds check for message index in history processing
- Fix regex to properly match relative paths (./  ../)
- Add multi-image support for iMessage attachments
- Pass MAX_IMAGE_BYTES limit to image loading

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-18 08:15:21 +00:00
Peter Steinberger
ec27c813cc fix(fallback): handle timeout aborts 
Co-authored-by: Mykyta Bozhenko <21245729+cheeeee@users.noreply.github.com>
 2026-01-18 07:52:44 +00:00
Peter Steinberger
ae0b4c4990 feat: add exec host routing + node daemon 2026-01-18 07:46:00 +00:00
Peter Steinberger
df752d4706 Merge pull request #1149 from radek-paclt/feature/memory-plugin-v2 
feat(memory): add lifecycle hooks and vector memory plugin
 2026-01-18 07:10:06 +00:00
Peter Steinberger
d3b15c6afa ci: stabilize vitest runs 2026-01-18 06:58:54 +00:00
Radek Paclt
ebfeb7a6bf feat(memory): add lifecycle hooks and vector memory plugin 
Add plugin lifecycle hooks infrastructure:
- before_agent_start: inject context before agent loop
- agent_end: analyze conversation after completion
- 13 hook types total (message, tool, session, gateway hooks)

Memory plugin implementation:
- LanceDB vector storage with OpenAI embeddings
- kind: "memory" to integrate with upstream slot system
- Auto-recall: injects <relevant-memories> when context found
- Auto-capture: stores preferences, decisions, entities
- Rule-based capture filtering with 0.95 similarity dedup
- Tools: memory_recall, memory_store, memory_forget
- CLI: clawdbot ltm list|search|stats

Plugin infrastructure:
- api.on() method for hook registration
- Global hook runner singleton for cross-module access
- Priority ordering and error catching

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-18 06:34:43 +00:00
Peter Steinberger
ac1b2d8c40 chore(gate): fix lint and protocol 2026-01-18 06:31:02 +00:00
Peter Steinberger
f7fcfafb4c fix: resolve lint after rebase 2026-01-18 06:30:01 +00:00
Peter Steinberger
0b00e591e1 fix(streaming): emit assistant deltas 
Co-authored-by: Andrew Lauppe <andy@t5tele.com>
 2026-01-18 06:24:52 +00:00
Peter Steinberger
28f8b7bafa refactor: add hook guards and test helpers 2026-01-18 06:15:24 +00:00
Peter Steinberger
8f7f7ee7dc feat: add /exec session overrides 2026-01-18 06:12:54 +00:00
Peter Steinberger
d4bd387e0e chore(gate): fix lint and formatting 2026-01-18 06:01:25 +00:00
Peter Steinberger
88b37e80fc refactor: expand bootstrap helpers and tests 2026-01-18 05:51:55 +00:00
Peter Steinberger
9c0ff87c86 fix: align plugin runtime and exec wiring 2026-01-18 05:44:22 +00:00
Peter Steinberger
cf8b3ed988 fix: harden memory indexing and embedded session locks 2026-01-18 05:41:45 +00:00
Peter Steinberger
2dabce59ce feat(slash-commands): usage footer modes 2026-01-18 05:35:35 +00:00
Peter Steinberger
e7a4931932 refactor: centralize bootstrap file resolution 2026-01-18 05:31:04 +00:00
Peter Steinberger
ad3c12a43a feat: add bootstrap hook and soul-evil hook 2026-01-18 05:24:47 +00:00
Peter Steinberger
016693a1f5 fix: abort embedded prompts on cancel 2026-01-18 05:18:10 +00:00
Peter Steinberger
b105745299 feat: expand subagent status visibility 2026-01-18 04:46:04 +00:00
Peter Steinberger
1ae415e395 fix: align agent exec config 2026-01-18 04:37:15 +00:00
Peter Steinberger
e4e1396a98 perf: improve batch status logging 2026-01-18 04:28:14 +00:00
Peter Steinberger
efdb33c975 feat: add exec host approvals flow 2026-01-18 04:27:41 +00:00
Peter Steinberger
82e49af5a7 fix: resolve plugin tool meta typing 2026-01-18 04:24:16 +00:00
Peter Steinberger
fabc2882aa fix: avoid keychain prompts in embedded runner 2026-01-18 04:19:28 +00:00
Peter Steinberger
6b3d3f5e21 refactor: centralize plugin tool policy helpers 2026-01-18 04:18:32 +00:00
Peter Steinberger
6da6582ced feat: add optional plugin tools 2026-01-18 04:08:00 +00:00
Peter Steinberger
afb877a96b perf: speed up memory batch polling 2026-01-18 03:55:14 +00:00
Peter Steinberger
787bed4996 test: stabilize doctor + pi-embedded suites 2026-01-18 03:40:47 +00:00
Peter Steinberger
5fa1a63978 Merge pull request #1136 from cheeeee/fix/prompt-failover 
fix(agent): Enable model fallback for prompt-phase quota/rate limit errors
 2026-01-18 03:32:03 +00:00
Peter Steinberger
0f6f7059d9 test: stabilize embedded runner tests 2026-01-18 02:55:41 +00:00
Peter Steinberger
67f63ecd7e chore: remove tracked artifacts 2026-01-18 02:55:07 +00:00
Peter Steinberger
1420d113d8 refactor: migrate extensions to plugin sdk 2026-01-18 02:55:07 +00:00
Peter Steinberger
34590d2144 feat: persist session origin metadata across connectors 2026-01-18 02:42:10 +00:00
Peter Steinberger
0c93b9b7bb style: apply oxfmt 2026-01-18 02:19:35 +00:00
Peter Steinberger
9fd9f4c896 feat(plugins): add memory slot plugin 2026-01-18 02:12:10 +00:00
Peter Steinberger
005b831023 test: stabilize env-dependent tool defaults 2026-01-18 01:57:54 +00:00
Peter Steinberger
14e6b21b50 test: cover perplexity baseUrl precedence 2026-01-18 01:56:34 +00:00
Peter Steinberger
ccb30665f7 feat: add hybrid memory search 2026-01-18 01:47:58 +00:00
Peter Steinberger
0fb2777c6d feat: add memory embedding cache 2026-01-18 01:47:58 +00:00
Peter Steinberger
568b8ee96c refactor: split web tools and docs 2026-01-18 01:42:54 +00:00
Peter Steinberger
0674f1fa3c feat: add exec approvals allowlists 2026-01-18 01:34:31 +00:00
Mykyta Bozhenko
448394a0de fix(agent): Enable model fallback for prompt-phase quota/rate limit errors 
When a prompt submission fails with quota or rate limit errors, throw
FailoverError instead of the raw promptError. This enables the model
fallback system to try alternative models.

Previously, rate limit errors during the prompt phase (before streaming)
were thrown directly, bypassing fallback. Only response-phase errors
triggered model fallback.

Now checks if fallback models are configured and the error is failover-
eligible. If so, wraps in FailoverError to trigger the fallback chain.
 2026-01-18 01:29:48 +00:00
Peter Steinberger
8b1bec11d0 feat: speed up memory batch indexing 2026-01-18 01:24:51 +00:00
Peter Steinberger
1d83389776 Merge pull request #1131 from CMLKevin/feat/perplexity-search-provider 
feat(web): add Perplexity Sonar as alternative search provider
 2026-01-18 01:16:00 +00:00
Peter Steinberger
36d88f6079 fix: normalize gateway dev mode detection 2026-01-18 01:08:47 +00:00
Muhammed Mukhthar CM
b56b67cdbd UI: label Qwen provider 2026-01-18 01:03:08 +00:00
Muhammed Mukhthar CM
8eb80ee40a Models: add Qwen Portal OAuth support 2026-01-18 01:03:08 +00:00
Peter Steinberger
d593a809f0 fix: apply openai batch defaults 2026-01-18 00:29:18 +00:00
Peter Steinberger
4d590f9254 refactor(slack): centralize target parsing 2026-01-18 00:15:05 +00:00