zap
|
b1dd738966
|
docs(memory): add naming and maintenance guidance
|
2026-03-11 18:59:53 +00:00 |
|
zap
|
36c2c3fa25
|
docs(memory): add taxonomy and retrieval guide
|
2026-03-11 18:58:55 +00:00 |
|
zap
|
fba23985c6
|
chore(memory): reclassify topical notes into subfolders
|
2026-03-11 18:56:55 +00:00 |
|
zap
|
575e4a8ba6
|
chore(memory): archive low-value session summaries
|
2026-03-11 18:53:57 +00:00 |
|
zap
|
24edec6704
|
docs(memory): tighten long-term memory hygiene
|
2026-03-11 18:52:33 +00:00 |
|
zap
|
eb9522d5c2
|
feat(skills): install gog-calendar
|
2026-03-10 21:25:44 +00:00 |
|
zap
|
b59943ba25
|
docs(memory): record brave, telegram, and daily-brief progress
|
2026-03-10 21:22:41 +00:00 |
|
zap
|
4428790bdb
|
docs(agents): add session classification step
|
2026-03-10 21:15:17 +00:00 |
|
zap
|
03f5025eb0
|
docs(tools): note tui and telegram session routing
|
2026-03-10 21:11:20 +00:00 |
|
zap
|
9a6ccfe9d5
|
docs(tools): note brave search api rate limit
|
2026-03-10 20:42:41 +00:00 |
|
zap
|
6b9ab3c122
|
docs(workflow): enforce state-first checks before setup advice
|
2026-03-10 20:18:43 +00:00 |
|
zap
|
7cc8ff8966
|
docs(tools): add search cheat sheet
|
2026-03-10 20:08:39 +00:00 |
|
zap
|
8d288918e3
|
docs(search): record routing policy and fallback tuning
|
2026-03-10 20:04:32 +00:00 |
|
zap
|
1de793fb8d
|
feat(search): add local meta search wrapper
|
2026-03-10 19:55:44 +00:00 |
|
zap
|
610f2e40b8
|
fix(search): stabilize brave mcp skill args
|
2026-03-10 19:53:37 +00:00 |
|
zap
|
d98174b609
|
feat(search): add local brave mcp search skill
|
2026-03-10 19:46:26 +00:00 |
|
zap
|
d0089f076e
|
docs(tools): note brave search mcp port
|
2026-03-10 19:33:30 +00:00 |
|
zap
|
5fa4368573
|
docs(memory): restore and update long-term notes
|
2026-03-10 19:26:51 +00:00 |
|
zap
|
d0e02e8959
|
docs(identity): update assistant identity
|
2026-03-10 19:18:23 +00:00 |
|
zap
|
eead3856ed
|
docs(tools): note ollama memory endpoint
|
2026-03-10 19:13:35 +00:00 |
|
zap
|
d74eae62bd
|
chore(memory): update boot last run and startup health data
|
2026-03-10 00:38:07 +00:00 |
|
zap
|
54b4435aaa
|
feat(skills): add inbox-priority-agent triage skill
|
2026-03-09 19:00:40 +00:00 |
|
zap
|
f80530a042
|
chore(boot): refresh startup health snapshot
|
2026-03-09 03:32:48 +00:00 |
|
zap
|
9bc4b4a560
|
chore(boot): refresh startup health snapshot
|
2026-03-09 03:18:39 +00:00 |
|
zap
|
5aa4f6e2d3
|
chore(memory): record 2026-03-09 stability and skill notes
|
2026-03-09 02:14:20 +00:00 |
|
zap
|
32a16769ee
|
chore(boot): refresh startup health snapshot
|
2026-03-09 00:32:55 +00:00 |
|
zap
|
c065895af1
|
chore(boot): refresh startup health status
|
2026-03-09 00:27:26 +00:00 |
|
zap
|
607571d0c9
|
chore(boot): record startup health check status
|
2026-03-09 00:16:08 +00:00 |
|
zap
|
cd0b088cdc
|
feat(backup): add MinIO recovery smoke test script
|
2026-03-08 21:57:43 +00:00 |
|
zap
|
bdb25ee6be
|
feat(ops): include openclaw update status in infra sentinel
|
2026-03-07 19:59:37 +00:00 |
|
zap
|
83a0e8924f
|
feat(ops): set lan model ports and gate local systemd checks
|
2026-03-07 19:44:59 +00:00 |
|
zap
|
1f3a1a6899
|
chore(ops): default ollama probe to known lan host
|
2026-03-07 19:34:02 +00:00 |
|
zap
|
5d5fc87c01
|
feat(ops): add systemd checks for ollama and llama.cpp
|
2026-03-07 19:03:13 +00:00 |
|
zap
|
6535f0a18e
|
feat(ops): expand sentinel checks for lan services and embeddings
|
2026-03-07 18:43:40 +00:00 |
|
zap
|
25f377cfc9
|
chore(instructions): add Claude ACP model-tier routing preference
|
2026-03-07 00:13:50 +00:00 |
|
zap
|
1bea15d573
|
docs(soul): add debug/update discipline and execution truth contract
|
2026-03-06 20:13:10 +00:00 |
|
zap
|
04987af144
|
docs(backup): record minio versioning and lifecycle policy
|
2026-03-06 01:38:13 +00:00 |
|
zap
|
a7d91318af
|
feat(backup): archive full ~/.openclaw to minio
|
2026-03-06 01:31:00 +00:00 |
|
zap
|
21f8c374e8
|
feat(skills): add clawddocs skill v1.2.2
|
2026-03-06 00:40:01 +00:00 |
|
zap
|
3c898aafd1
|
chore(security): quarantine stale acpx.bak and clear audit findings
|
2026-03-05 21:42:04 +00:00 |
|
zap
|
b76815b4da
|
chore(security): refresh deep-audit status and clear stale warning
|
2026-03-05 21:37:25 +00:00 |
|
zap
|
23c2546fc1
|
chore(memory): clear stale hooks warning from startup health
|
2026-03-05 21:34:19 +00:00 |
|
zap
|
bf6581f242
|
fix(boot): make hook readiness check use openclaw hooks output
|
2026-03-05 21:32:36 +00:00 |
|
zap
|
ad385d6462
|
chore(model-hints): sync OpenAI and Anthropic best-practice guidance
|
2026-03-05 21:29:09 +00:00 |
|
zap
|
21e631b615
|
feat(hooks): track model-skill-injector in workspace repo
|
2026-03-05 21:08:42 +00:00 |
|
zap
|
52c64e6f39
|
feat(skills): add model-family hint files for agent:bootstrap injection (anthropic/openai/generic)
|
2026-03-05 20:55:23 +00:00 |
|
zap
|
06202bcfbe
|
chore(skills): drop OpenAI o-series from llm-tool-best-practices scope
|
2026-03-05 20:44:57 +00:00 |
|
zap
|
a34826908d
|
feat(skills): add llm-tool-best-practices reference from Anthropic + OpenAI official docs
|
2026-03-05 20:44:00 +00:00 |
|
zap
|
23782735a1
|
docs(cost): update plan with corrections from official docs
- Phase 1: clarify cacheRetention only applies to Claude models; GPT auto-caches; GLM has none
- Phase 1: add TTL reality check (short=5min, long=1h) and implications for heartbeat timing
- Phase 2: explain why long TTL + 25m heartbeat is the right combo
- Phase 4: replace generic prompt tips with model-specific guidance from official Anthropic/OpenAI docs
- Added prompt structure notes for cache efficiency, GLM-4.7 tighter prompting requirements
- References: memory/references/*.md
|
2026-03-05 20:37:32 +00:00 |
|
zap
|
79e61f4528
|
docs(references): add Anthropic + OpenAI official best practices
- anthropic-prompt-caching.md: KV cache mechanics, TTLs, pricing, auto vs explicit
- openai-prompt-caching.md: automatic caching, in-memory vs 24h retention, prompt_cache_key
- anthropic-prompting-best-practices.md: clear instructions, XML tags, few-shot, model-specific notes
- openai-prompting-best-practices.md: message roles, optimization framework, structured outputs, model selection
Key findings:
- Anthropic caching: only for Claude models, 5m default TTL, 1h optional, 10% cost for reads
- OpenAI caching: automatic/free, 5-10min default, 24h extended for GPT-5+
- GLM/ZAI models: neither caching mechanism applies
- Subagent model routing table added to openai-prompting-best-practices.md
|
2026-03-05 20:34:38 +00:00 |
|