vikingowl
2c0ff5ff1f
docs: mark M7 deliverables complete in milestones.md
2026-04-06 00:59:16 +02:00
vikingowl
43dcc7e9de
docs: M6/M7 close-out implementation plan — 8 tasks, TDD, full file map
2026-04-05 21:33:42 +02:00
vikingowl
252ffde732
docs: M6/M7 close-out design spec — tool persistence, tokenizer, router feedback, coordinator
2026-04-05 21:22:26 +02:00
vikingowl
abb3e3ca90
feat: spawn_elfs batch tool for guaranteed parallel elf execution
...
New spawn_elfs tool takes array of tasks, spawns all elfs simultaneously.
Solves the problem of models (Mistral Small, Devstral) that serialize
tool calls instead of batching them.
Schema: {"tasks": [{"prompt": "...", "task_type": "..."}], "max_turns": 30}
Also:
- Suppress spawn_elfs tool output from chat (tree handles display)
- Update M7 milestones to reflect completed deliverables
- Add CC-inspired features to M8/M10: task notification system,
task framework, /batch skill, coordinator mode, StreamingToolExecutor,
git worktree isolation
2026-04-03 21:03:51 +02:00
vikingowl
8e5ddb20cb
feat: hybrid system inventory — dynamic PATH scan + runtime probing
...
No hardcoded tool lists. Scans all $PATH directories for executables
(5541 on this system), then probes known runtime patterns for version
info (23 detected: Go, Python, Node, Rust, Ruby, Perl, Java, Dart,
Deno, Bun, Lua, LuaJIT, Guile, GCC, Clang, NASM + package managers).
System prompt includes: OS, shell, runtime versions, and notable
tools (git, docker, kubectl, fzf, rg, etc.) from the full PATH scan.
Total executable count reported so the LLM knows the full scope.
Milestones updated: M6 fixed context prefix, M12 multimodality.
2026-04-03 14:36:22 +02:00
vikingowl
c54471a37b
refactor: migrate mistral sdk to github.com/VikingOwl91/mistral-go-sdk
...
Same package, new GitHub deployment with fixed tests.
somegit.dev/vikingowl → github.com/VikingOwl91, v1.2.0 → v1.2.1
2026-04-03 12:06:59 +02:00
vikingowl
69f5dba091
feat: complete M1 — core engine with Mistral provider
...
Mistral provider adapter with streaming, tool calls (single-chunk
pattern), stop reason inference, model listing, capabilities, and
JSON output support.
Tool system: bash (7 security checks, shell alias harvesting for
bash/zsh/fish), file ops (read, write, edit, glob, grep, ls).
Alias harvesting collects 300+ aliases from user's shell config.
Engine agentic loop: stream → tool execution → re-query → until
done. Tool gating on model capabilities. Max turns safety limit.
CLI pipe mode: echo "prompt" | gnoma streams response to stdout.
Flags: --provider, --model, --system, --api-key, --max-turns,
--verbose, --version.
Provider interface expanded: Models(), DefaultModel(), Capabilities
(ToolUse, JSONOutput, Vision, Thinking, ContextWindow, MaxOutput),
ResponseFormat with JSON schema support.
Live verified: text streaming + tool calling with devstral-small.
117 tests across 8 packages, 10MB binary.
2026-04-03 12:01:55 +02:00
vikingowl
951ab3b970
docs: update essentials for router, security, task learning
...
Restructure milestones from M1-M11 to M1-M15:
- M3: Security Firewall (secret scanner, incognito mode)
- M4: Router Foundation (arm registry, pools, task classifier)
- M5: TUI with full 6 permission modes
- M6: Full compaction (truncate + LLM summarization)
- M9: Router Advanced (bandit learning, ensemble strategies)
- M11: Task Learning (pattern detection, persistent tasks)
Add ADR-007 through ADR-012 for security-as-core, router split,
Thompson Sampling, MCP replaceability, task learning, incognito.
Add risks R-010 through R-015 for router, security, feedback,
task learning, ensemble quality, shell parser.
Update architecture dependency graph with security, router,
elf, hook, skill, mcp, plugin, tasklearn packages.
Update domain model with Router, Arm, LimitPool, Firewall entities.
2026-04-03 10:47:11 +02:00
vikingowl
154d978564
docs: add project essentials (12/12 complete)
...
Vision, domain model, architecture, patterns, process flows,
UML diagrams, API contracts, tech stack, constraints, milestones
(M1-M11), decision log (6 ADRs), and risk register.
Key decisions: single binary, pull-based streaming, Mistral as M1
reference provider, discriminated unions, multi-provider collaboration
as core identity.
2026-04-02 18:09:07 +02:00
vikingowl