Commit Graph

17 Commits

Author SHA1 Message Date
8aed017ccd v0.7.2: tag stack — trigger counts + PRIVACY_FILTER_TAGS fallback — TDD
*tag-trigger-count* hash table tracks per-session tag triggers.
tag-trigger-record increments count, called from
dispatcher-privacy-severity on each matched tag. /tags shows
trigger count per tag.

tag-categories-load now falls back to PRIVACY_FILTER_TAGS env var
when TAG_CATEGORIES is not set (backward compat). All entries
default to :block severity.

- security-dispatcher: *tag-trigger-count*, tag-trigger-record,
  updated tag-categories-load, wired dispatcher-privacy-severity
  +2 tests (trigger record, privacy fallback)
- channel-tui-main: /tags shows trigger counts
- Core: 88/88  TUI Main: 102/102
2026-05-08 21:20:06 -04:00
510643786b v0.7.2: wire tag severity into dispatcher-check — TDD
dispatcher-privacy-severity replaces binary dispatcher-check-privacy-tags.
Three-tier: :block (reject), :warn (log+allow), :log (silent).
Wired into dispatcher-check vector 5.

- security-dispatcher: dispatcher-privacy-severity fn, +3 tests
  Updated vector 5 in dispatcher-check with severity branching.
- Core: 88/88
2026-05-08 19:35:17 -04:00
19a9c99ef4 v0.7.2: tag stack severity tiers + tool hardening — TDD
Tag stack: TAG_CATEGORIES env var parses into *tag-categories* alist
(@tag . severity). Three tiers: :block (filter), :warn (log), :log
(silent). tag-category-severity lookup. /tags TUI command.

Tool hardening: per-tool timeouts (shell=300s, search=30s, eval=10s,
default=120s). verify-write after write-file reads back content.
tool-timeout accessor.

- security-dispatcher: *tag-categories*, tag-categories-load,
  tag-category-severity, 2 tests
- core-act: *tool-timeouts*, tool-timeout, verify-write, 3 tests
- programming-tools: verify-write wired into write-file
- channel-tui-main: /tags and /audit commands
- Core: 84/84
2026-05-08 18:18:14 -04:00
d2d61c5b44 v0.7.2: safe-tool read-only allowlist — TDD
Read-only cognitive tools auto-pass dispatcher-check unconditionally.
Added :read-only-p slot to cognitive-tool struct, :read-only-p keyword
to def-cognitive-tool macro, tool-read-only-p registry lookup.

- core-package: struct + macro + tool-read-only-p function
- security-dispatcher: early auto-pass in dispatcher-check, 2 new tests
- programming-tools: 7 tools marked :read-only-p t (search-files,
  find-files, read-file, list-directory, eval-form, run-tests,
  org-find-headline)
- Dispatcher: 38/38
2026-05-08 16:28:10 -04:00
924bf8f479 passepartout: v0.5.0 hotfix 2 — daemon stable
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 2s
- Restore (in-package :passepartout) to core-reason
- Move *VAULT-MEMORY* back to core-skills
- Fix ASDF and defstruct/defpackage ordering
- Increase daemon timeout to 120s
- Handshake: 0.5.0

Verified: daemon processes messages, TUI clean, gate trace works
2026-05-07 20:14:51 -04:00
eeb1234086 passepartout: v0.4.3 Shell Sandboxing & Safety Classification
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 3s
- bwrap sandbox: detect bwrap binary, wrap shell commands through
  Linux namespace isolation with --unshare-net --unshare-ipc
  when available, fall back to timeout bash -c otherwise
- Severity classification: extend shell-blocked patterns with
  :catastrophic/:dangerous/:moderate/:harmless severity tiers,
  dispatcher-severity-max for tier comparison
- dispatcher-check-shell-safety: returns (:matched <names> :severity <tier>)
- Version: 0.4.2 -> 0.4.3 across handshake, ASDF, README badge
2026-05-07 17:52:32 -04:00
639bc348d9 passepartout: v0.4.1 Design Cleanup
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 2s
- Remove system-prompt-augment mechanism, introduce *standing-mandates*
- Fix false token-overhead claims in DESIGN_DECISIONS + ROADMAP
- Update security vector count 9-10 across all docs and dispatcher docstring
- Rewrite README with agent section, soften aspirational claims
- Register 10 cognitive tools in programming-tools.org with test suite
- Enforce NO-HARDCODED-CONSTANTS in .env.example
- ROADMAP: mark v0.3.x patches DONE, add LOGBOOKs, mark releases
- AGENTS.md: rewrite compact (180 to 50 lines), move refs to CONTRIBUTING
- Normalize org tangle directives to file-level PROPERTY inheritance
2026-05-07 16:44:59 -04:00
385a6497ac v0.4.0: self-build safety boundary — core-* path protection
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 3s
Adds dispatcher-check-core-path: regex-based detection of core-*.org and
core-*.lisp files (Perceive-Reason-Act loop, Merkle-tree memory, skill
engine, Dispatcher gates).

Vector 2b in dispatcher-check: when SELF_BUILD_MODE=true and a core file
write is detected, produces :approval-required (Flight Plan HITL) instead
of allowing the write through. When SELF_BUILD_MODE=false (default),
writes pass through — development mode.

Core file protection is separate from secret-path protection
(*dispatcher-protected-paths*) which blocks credentials/keys/tokens.

Test test-self-build-core-protection:
- core-loop-reason.org, core-memory.lisp → protected
- gateway-tui-view.org → not protected
- SELF_BUILD_MODE=true → writes blocked as :approval-required
- SELF_BUILD_MODE=false → writes pass through

Test: 102/0 (dispatcher 24/0)
2026-05-06 19:19:28 -04:00
33993d2d73 rename: remaining Bouncer mentions → Dispatcher
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 2s
- BOUNCER-PRIVACY-TAGS → *DISPATCHER-PRIVACY-TAGS*
- BOUNCER-SHELL-TIMEOUT → *DISPATCHER-SHELL-TIMEOUT*
- BOUNCER-SHELL-MAX-OUTPUT → *DISPATCHER-SHELL-MAX-OUTPUT*
- bouncer-privacy-tags docstrings → Dispatcher privacy tags
- 'Bouncer' in log messages, docstrings, test descriptions
- 'Bouncer Security Dispatcher' → 'Security Dispatcher'
2026-05-06 18:43:25 -04:00
4bed6dd461 v0.3.2: shell safety, :system :eval approval, skill sandbox
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 3s
1. Shell actuator: remove double bash -c wrapping (format ~s produces
   S-expression-safe strings, not shell-safe). Now passes cmd directly
   to (timeout N bash -c cmd) via run-program arg list.

2. Dispatcher: extend high-impact approval gate to :system :eval.
   Previously only :shell, :tool "shell", and :emacs :eval triggered
   HITL. Now :system :eval also requires Flight Plan approval.

3. Skill sandbox: before promoting a skill from its jailed package to
   :passepartout, scan for restricted symbol references (uiop:run-program,
   uiop:shell, uiop:run-shell-command). Block promotion on violation.
   New skill-entry status :sandbox-blocked for blocked skills.

Test: 91 pass, 0 fail across 13 suites.
2026-05-06 16:46:49 -04:00
ea1150f38e security: contracts + tests for all 5 security modules (87→123 checks)
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 2s
2026-05-05 12:08:12 -04:00
ce90fd3e72 fix: HITL functions now properly loaded, define missing proto-get
Some checks failed
Deploy (Gitea) / deploy (push) Has been cancelled
Root cause chain:
1. proto-get was used throughout the pipeline but never defined — added
   to core-communication.org as a keyword-normalizing getf wrapper.
2. security-dispatcher.lisp was loaded by skill-initialize-all into a
   separate package, making HITL functions invisible to :passepartout.
   Fixed by adding to ASDF component list and excluding from skill loader.
3. org-id-generate was referenced from hitl-create but lives in an
   unexported skill package — replaced with uuid:make-v4-uuid.
4. uiop:string-prefix-p was called with :test keyword argument it does
   not accept — replaced with string-downcase normalization on both sides.

Also:
- Export hitl-create, hitl-approve, hitl-deny, hitl-handle-message,
  stimulus-inject from :passepartout for REPL accessibility.
2026-05-03 14:21:08 -04:00
a16f973b50 docs: add missing prose headlines in security-dispatcher.org HITL section
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 3s
Fixes 4 pre-existing PROSE-BEFORE-CODE violations in the HITL in-memory
store section. Each function (hitl-create, hitl-approve, hitl-deny,
hitl-handle-message) now has a *** sub-heading with explanatory prose
before its code block.
2026-05-03 14:00:24 -04:00
5e7b1cee33 feat: HITL — continuation-based human-in-the-loop
Some checks failed
Deploy (Gitea) / deploy (push) Failing after 3s
- dispatcher-check: add :level :approval-required to network/high-impact returns
- cognitive-verify: distinguish approval-required from hard rejection; pass
  approval requests through to act gate instead of returning early
- loop-gate-reason: don't retry approval requests; pass them as approved-action
  with :status :requires-approval
- loop-gate-act: detect approval-required, create Flight Plan, dispatch HITL
  message to user's client, don't execute original action
- loop-gate-perceive: handle re-injected approved signals from
  dispatcher-approvals-process; set :approved-action on signal
- dispatcher-approvals-process: fix function name (stimulus-inject) and wrap
  action in proper signal envelope with :sensor :approval-required
- Fix: list-objects-with-attribute → memory-objects-by-attribute
- Fix: org-id-new → org-id-generate
- Fix: inject-stimulus → stimulus-inject (correct function name)

Flow:
1. LLM proposes high-risk action → dispatcher returns approval-required
2. cognitive-verify collects approval request → passes to reason as :requires-approval
3. loop-gate-act creates Flight Plan → dispatches HITL message to client → exits
4. Human approves in Emacs → heartbeat re-injects with :approved t
5. Re-injected signal flows through pipeline → dispatcher passes through
6. Action executed normally
2026-05-03 13:00:19 -04:00
529f8d0782 feat: Context Manager skill + org-object→memory-object fix
Some checks failed
Deploy (Gitea) / deploy (push) Has been cancelled
- system-context-manager (new skill): stack-based project focusing with
  push-context/pop-context, path resolution relative to base path, and
  scope-aware memory queries via context-scoped-query.
- core-memory: add :scope slot to memory-object struct (default :memex).
- core-memory: ingest-ast accepts &key (scope :memex), propagates to children.
- core-context: context-query accepts :scope parameter for filtering.
- DEFECT FIX: renamed org-object-* accessors to memory-object-*
  across core-context, security-dispatcher, tests, and defpackage exports.
  The struct was renamed but accessor references were never updated —
  the code referenced nonexistent functions.
2026-05-03 12:08:04 -04:00
d35aea391e feat(v0.3.0): Event Orchestrator skill
- New system-event-orchestrator skill with hook registry, cron registry, and tier classifier

- Three dispatch tiers: :reflex (no LLM), :cognition (light), :reasoning (full)

- Org-mode timestamp parsing for repeat patterns (+1w, +1d, +1m)

- Registers on heartbeat via defskill, dispatches due cron jobs

- Fix all remaining harness-log → log-message references across org files
2026-05-02 22:36:39 -04:00
95d1ea3fed feat: add DeepSeek and NVIDIA NIM providers
- Add deepseek and nvidia entries to gateway-provider config

- Add DEEPSEEK_API_KEY and NVIDIA_API_KEY to .env.example

- Add deepseek and nvidia to doctor's LLM provider check

- Fix remaining harness-log → log-message reference
2026-05-02 22:25:24 -04:00