|
|
41de20d3f1
|
v0.2.1: polish, deploy, CI, and literate refactor
Deploy (Gitea) / deploy (push) Failing after 11s
- Secret Exposure Gate + Privacy Filter (Bouncer)
- Shell actuator safety harness (timeout, blocked patterns)
- REPL-first enforcement (lisp validation gate, system-prompt-augment)
- Engineering Standards lifecycle (two-track Org-first + REPL-first)
- Literate Programming discipline (one function per block, reflect-back)
- AGENTS.md: thin routing layer, skills are authoritative
- SKILLS_DIR removed, ~/notes fallback eliminated
- opencortex.sh: multi-distro (Debian+Fedora), configure, install service, backup, restore, help
- infrastructure/opencortex.service (systemd user unit)
- Docker: updated to debian:trixie, fixed build context
- GitHub CI: lint + test workflows fixed, trigger on tags only
- Gitea CI: deploy workflow paths fixed
- README: one-line curl install, badges
- USER_MANUAL: Deployment section (bare metal, Docker, backup)
- .gitignore: skills/*.lisp and tests/*.lisp as generated artifacts
- Prose/block refactor across all 35 org files
- Test suite Tier 1: 43/45 pass (env-dependent failures isolated)
|
2026-05-02 17:04:33 -04:00 |
|
|
|
b63f5477c1
|
fix(v0.2.0): resolve TUI crash and setup wizard errors
- Fix unbalanced parens in config-manager (set-config-value, setup-gateways)
- Fix assoc :key #'car SBCL compatibility issue in setup-llm-providers
- Add missing generate-tool-belt-prompt function
- Fix deterministic-verify to not overwrite action when skills return nil
- Add :explanation to think fallback responses for policy compliance
- Update opencortex.sh to tangle from repo org to XDG .lisp
- Remove generated .lisp artifacts from repo (skills, tests, state)
|
2026-04-30 17:04:01 -04:00 |
|
|
|
8be187a968
|
Update .env.example
Deploy-Agent-V15-Stdin / JOB-V15-STDIN (push) Failing after 3s
|
2026-04-27 12:41:54 -04:00 |
|
|
|
664ba8243d
|
refactor: Flatten directory structure library->harness, library/gen->skills
|
2026-04-27 08:41:26 -04:00 |
|
|
|
dfe318425f
|
Add v0.2.0 features: vector search + tool permissions
- Local vector search: Ollama embeddings + semantic search
- get-embedding with caching
- cosine-similarity computation
- semantic-search cognitive tool
- :semantic-search tool for LLM queries
- Tool permission tiers: security gating for cognitive tools
- Three tiers: :allow, :deny, :ask
- Gate in execute-tool-action before tool runs
- Defaults: :deny for shell/delete-file, :ask for eval/write-file
- :tool-permissions cognitive tool for management
- Embedding provider support: Ollama AND llama.cpp
- EMBEDDING_PROVIDER env var
- EMBEDDING_MODEL env var
- LLAMA_HOST for llama.cpp server
- .env.example: Add embedding config variables
- Fix parse-message in communication.lisp
- Update ASDF: add test files, tool-permissions skill
All 60 tests pass (6 suites x 100%)
|
2026-04-23 13:43:50 -04:00 |
|
|
|
b2d85ac4ae
|
refactor: Reorganize .env.example into logical sections
- Group variables by purpose (Identity, LLM, Daemon, Security, etc.)
- Remove unused variables (LLM_API_KEY, LLM_ENDPOINT, GTD_ENFORCE_INTEGRITY, ORG_AGENT_WEB_PORT, RECIPIENT_ID)
- Add section headers for clarity
|
2026-04-22 16:02:24 -04:00 |
|
|
|
6a5695310c
|
fix(protocol): Resolve desync by handling HMAC signature in reader and normalizing env vars
Deploy-Agent-V15-Stdin / JOB-V15-STDIN (push) Failing after 2s
|
2026-04-19 20:03:19 -04:00 |
|
|
|
3374d27e75
|
fix(reason): Initialize neural provider cascade (resolves Neural-Dead kernel)
Deploy-Agent-V15-Stdin / JOB-V15-STDIN (push) Failing after 2s
|
2026-04-19 17:22:30 -04:00 |
|
|
|
d8236cb2cf
|
fix(mvp): 100% Green Boot, Llama.cpp backend, and setup refinement
Deploy-Agent-V15-Stdin / JOB-V15-STDIN (push) Failing after 2s
|
2026-04-17 20:25:01 -04:00 |
|
|
|
6d49e9b04b
|
fix(boot): Point SKILLS_DIR to repo skills/ folder and improve boot failure error messages
Deploy-Agent-V15-Stdin / JOB-V15-STDIN (push) Failing after 35s
|
2026-04-17 17:24:49 -04:00 |
|
|
|
849c078c37
|
REFAC: Global rename of org-agent to opencortex
|
2026-04-14 12:10:11 -04:00 |
|
|
|
898df4b7ff
|
REFAC: Applied literate granularity and configuration externalization to context stage
|
2026-04-13 17:31:36 -04:00 |
|
|
|
22e6d3c242
|
REFAC: Configurable mandatory skills via environment
|
2026-04-13 17:28:32 -04:00 |
|
|
|
7b56a46500
|
REFAC: Applied literate granularity and configuration externalization to loop
|
2026-04-13 16:55:11 -04:00 |
|
|
|
f4e74b732d
|
ALIGN: Updated boot loader to look for org-skill-policy
|
2026-04-13 13:18:48 -04:00 |
|
|
|
06432d3cdf
|
DOCS: Update .env.example with gateway and provider variables
|
2026-04-11 15:54:16 -04:00 |
|
|
|
1cd283ccb3
|
security: patch OACP reader vulnerability and implement HMAC foundations
|
2026-04-08 20:14:57 -04:00 |
|
|
|
9acc7713e0
|
Initial commit: extracted from memex
|
2026-03-27 15:41:57 -04:00 |
|
