8fd56dece3
v0.8.2: cleanup + prose + structure + decomposition + budget + errors
...
Phase 1 — dedup + hardening (~9 items):
- Remove duplicate *skill-registry* defvar from core-skills
- Merge *backend-registry* into *probabilistic-backends*, delete backend-register
- Remove inject-stimulus alias, standardize on stimulus-inject
- Add pre-eval sandbox (skill-source-scan) blocks restricted symbols before eval
- Remove dead plist-get function; remove duplicate json-alist-to-plist export
- Fix read-framed-message whitespace DoS (4096-iteration max)
- Add *read-eval* nil to dispatcher-approvals-process read-from-string (RCE)
- Add test-op to ASDF; update .asd version 0.4.3→0.7.2
Phase 2 — prose + contracts + reorder:
- Split ROADMAP: 2623→1089 lines (TODO only), CHANGELOG: 260→1528 lines (full DONE history, 14 versions reverse chron)
- Add Contracts + Overview to 6 channel files + embedding-native + programming-standards + symbolic-scope
- Reorder 28 .org files: Contract → Test Suite → Implementation (TDD order)
- Add 7-phase inline prose to think() in core-reason
- Expand USER_MANUAL: 183→461 lines (10 new sections)
Phase 3 — decomposition + export organization:
- Decompose think() into think-assemble-prompt, think-call-llm, think-parse-response orchestrator
- Organize 188 exports into 16 grouped sections by module
Phase 4 — budget enforcement + error protocol:
- Per-session budget enforcement (SESSION_BUDGET_USD env var, budget-exhausted-p, guard in think-call-llm)
- Error condition hierarchy (6 conditions: pipeline-error, llm-error, gate-error, budget-error, protocol-error)
- Restarts in loop-process: skip-signal, use-fallback, abort-pipeline
2026-05-13 09:17:48 -04:00
2ac87b626a
v0.8.0: Information Radiator, Command Palette, TrueColor Themes, Setup Wizard
...
- Sidebar: permanent 42-col panel with 7 data panels (Gate Trace, Focus,
Rules, Context gauge, Files, Cost, Protection); 4-window Croatoan layout
at >=120 cols, toggle via Ctrl+X+B
- Command palette: Ctrl+P overlay with fuzzy-filtered categorized items,
keyboard navigation, Enter to execute; view-palette rendering
- TrueColor themes: 4 new presets (nord, tokyonight, catppuccin, monokai)
with 27 hex keys via theme-hex-to-rgb
- Setup wizard: Ctrl+\ /setup 4-step overlay (provider, key, memory, save)
writing .env with in-TUI rendering
- Daemon enrichment: dispatcher block counts, cost session summary,
modified files tracking, context usage percentage
- Daemon fixes: fboundp guards for count-tokens/provider-token-cost,
tool registry save/restore in safety tests, SELF_BUILD_MODE cleanup
- 139 tests pass across all suites (0 failures)
2026-05-13 09:17:48 -04:00
1201b916d8
v0.7.2: tool hardening — read-only response caching — TDD
...
*tool-cache* hash table caches read-only tool results keyed by
tool-name-args. Cache check before execution in
action-tool-execute; cache miss → execute + store. Cache hit
skips tool execution entirely.
tool-cache-key and tool-cache-clear helpers. cache-test tool
verifies re-execution is skipped on second call.
- core-act: *tool-cache*, tool-cache-key, tool-cache-clear,
cache check wired into action-tool-execute, 1 test
- Core: 92/92 TUI Main: 102/102
v0.7.2 complete. All 14 items + 10 refinements. 92 core, 102 TUI.
2026-05-08 21:30:09 -04:00
44f927e8f1
v0.7.2: wire with-tool-timeout into action-tool-execute — TDD
...
call-with-tool-timeout wraps tool execution with sb-ext:with-timeout
using per-tool timeout from *tool-timeouts*. On timeout returns
(:status :error :message "Timed out after Ns"). Wired into
action-tool-execute before the funcall. Timeout result detected and
propagated as :tool-error.
- core-act: call-with-tool-timeout fn, wired into action-tool-execute
- Act tests: +3 (timeout enforcement test)
- Core: 88/88
2026-05-08 19:30:51 -04:00
96370cc4b1
v0.7.2: tool execution hardening — TDD
...
Per-tool timeouts: shell=300s, search-files=30s, eval-form=10s,
unknown=120s default. Write verification: after write-file,
reads back content and compares, logs mismatches.
- core-act: *tool-timeouts* hash, tool-timeout, verify-write
- programming-tools: verify-write call in write-file body
- Act tests: +3 (timeout shell, timeout unknown, verify match)
- Core: 84/84
2026-05-08 18:06:36 -04:00
26fd756222
v0.7.2: undo/redo — TDD
...
Operation-level memory undo/redo built on existing Merkle snapshot
infrastructure. undo-snapshot captures state before destructive tool
execution. /undo and /redo TUI commands send structured events.
- core-memory: undo-snapshot, undo, redo functions + 3 tests
- core-perceive: :undo/:redo sensor handlers
- core-act: auto-snapshot before non-read-only tools
- core-package: undo/redo symbol exports
- channel-tui-main: /undo, /redo commands + 2 tests
- Core: 73/73 TUI Main: 74/74
2026-05-08 16:39:00 -04:00
da160b71e3
passepartout: v0.5.0 File Reorganization
...
Deploy (Gitea) / deploy (push) Failing after 2s
Extract non-core fragments using self-repair criterion:
- core-context -> symbolic-awareness (224 lines, fboundp guards in think())
- heartbeat generation -> symbolic-events (renamed events-start-heartbeat)
Rename 23 files for clarity and new naming scheme:
- 6 core: core-package, core-transport, core-pipeline,
core-perceive, core-reason, core-act
- 13 system: symbolic-*, neuro-*, embedding-*, channel-shell
- 4 gateway: channel-cli, channel-tui-*, channel-tui-state
Utility relocations:
- markdown-strip -> programming-markdown
- plist-keywords-normalize -> programming-lisp
- cognitive-tool-prompt -> programming-tools
- VAULT-MEMORY -> security-vault
- Merge *backend-registry* into *probabilistic-backends*
Split gateway-messaging into channel-telegram/channel-signal/
channel-discord/channel-slack (4 independent skills)
Delete dead system-model.lisp (16-line wrapper)
Document self-repair criterion in DESIGN_DECISIONS
Version bump: 0.4.3 -> 0.5.0
2026-05-07 18:20:48 -04:00
