Repository navigation
Commit 02f7288
authored
* docs(memory): implement multi-memory chunking for remory token limits (#100)
- Add token limit warnings to /session-start (256 tokens = ~1,000 chars)
- Replace single large workflow memory with 7 focused memories
- Update memory-and-remory.md with chunking best practices
- Add troubleshooting section for embedding failures
- Document safe memory size: 1,200-1,500 characters per entry
- Explain why --infer false doesn't affect token limits
Prevents 'Failed to generate embedding' errors that blocked session
initialization when storing comprehensive workflow documentation.
* fix(memory): correct character limits to 800-1,000 chars for 256-token limit (#100)
Research confirmed:
- Upstream API enforces 256-token hard limit
- 1:4 character-to-token ratio verified
- Previous 1,200-1,500 char guidance = 300-375 tokens (exceeds limit)
- Corrected to 800-1,000 chars = 200-250 tokens (safe margin)
Evidence: remory embedding.rs disables truncation, passes to OpenAI API
which enforces 256 tokens. Math: 1,000 chars ÷ 4 = 250 tokens < 256 ✓
Files modified:
- command/session-start.md (30 line changes)
- instructions/memory-and-remory.md (32 line changes)
* fix(config): enable bash tool for research-specialist (#104)
Add "bash": true to research-specialist tools section. Agent had bash
permissions configured but was missing the tool enablement, blocking
all bash commands including remory memory operations.
Enables:
- remory search/add for memory protocol compliance
- Read-only bash commands (cat, grep, rg, git status, gh commands)
- Maintains existing permission restrictions (no git writes, etc.)
1 parent 4d75d04 commit 02f7288
1 file changed
Lines changed: 3 additions & 2 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
946 | 946 | | |
947 | 947 | | |
948 | 948 | | |
949 | | - | |
950 | | - | |
| 949 | + | |
| 950 | + | |
| 951 | + | |
951 | 952 | | |
952 | 953 | | |
953 | 954 | | |
| |||
0 commit comments