Commit Graph
14 Commits
Author SHA1 Message Date
retoor 58786386cf v1.43.0: automatic MCP GitHub resolver agent plus stdlib-only OAuth login
- mcp_resolve_agent: bounded fork subagent fallback when the
  deterministic GitHub pass finds no run contract (MCP_RESOLVER_*).
- McpOAuth/McpOAuthCallback: discovery, DCR, PKCE loopback, token
  exchange, sealed per-profile token storage, one-shot refresh.
- McpHttpError carries status plus WWW-Authenticate through the
  client; bridge retries once after refresh, else names mcp_login.
- mcp_add stores 401-gated servers disabled; mcp_login approves,
  verifies, enables; mcp_remove drops tokens.
- Docs, conclusions, 17 new tests (1209 + 16 green).
2026-10-18 20:38:52 +02:00
retoor 251c3dc2ba research: mcp-client-support subject (106 sources, 3 conclusions)
- wire spec: lifecycle, stdio + Streamable HTTP transports, tools,
  utilities, legacy SSE, versioning, changelog (14 Tier 1)
- client ecosystem: Claude Code/VS Code/Cursor/Codex configs,
  mcp-remote, Smithery, registries, Glama (12 Tier 1)
- security/ops: authorization draft, trust model, poisoning,
  rug pulls, production hardening (12 Tier 1) + 68 Tier 2 cards
- conclusions: minimal stdlib client on 2025-11-25, normalizer +
  resolver agent for pasted configs/GitHub URLs, untrusted-until-
  consent trust model; nothing built yet
- audit PASS (14 subjects, 797 sources, 32 conclusions)
2026-10-18 19:23:02 +02:00
retoor cc1c130b51 CAP protocol both directions: agent speak plus orchestrator drivers (1.39.0)
- Agent side: --cap-manifest plus --cap-speak stream-json binding with
  transcript-diff frames, diff/transcript artifacts, session config
- Orchestrator: PTY driver (settle heuristics on PtyProc/TuiVtScreen),
  stream-json, ACP-stdio (permission/elicit/fs/terminal serving) and
  A2A drivers (dual draft/current spelling, SSE mapping)
- Sessions, fleets: worktrees, master plans, mediated routing,
  budget refusal, audit log, research auto-answerer, --cap CLI
- cap.md contract with drift tests; research/cap-protocol archive
- Suites 1119 + 16 green
2026-10-18 13:17:35 +02:00
retoor af080fe68e Strict goal verification, approval hardening, retrieval eval, work limits, sandbox caps (1.38.0)
- Approval: re-prompt unknown answers (max 3), shell-only affirmative
  guidance recovery; destructive actions stay strict
- GoalVerifier subagent with strict JSON verdicts, bounded follow-up
  rounds, nonzero exit plus open turn on unverified one-shots
- Retrieval eval (Hit@K/MRR/nDCG/Context Precision), FTS cascade with
  title weighting, query/read event logging, --eval-retrieval CLI
- Supervisor caps (8 parallel, 64 records) and scheduler hardening
  (4 fires/tick, per-schedule lease, stated misfire policy)
- Sandbox box resource trio: 2g/2.0/256 at create, best-effort
  update for existing boxes, rm -f recovery pointer
- Research archive: 12 subjects, 667 sources, 27 conclusions;
  suites 979 + 16 green
2026-10-18 12:13:24 +02:00
retoorandClaude Sonnet 5.5 a103fa0611 Free model lists discovered live for zen, pollinations, openrouter, devplace; fallbacks refreshed; research archived
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-12 19:57:12 +02:00
retoor dfc97c31be Update. 2026-10-12 17:02:51 +02:00
retoor 3038c5724b Update 2026-10-12 00:53:52 +02:00
retoor afc88b8087 ask_user tool, prompt-JSON CLI repair loop, tool-loop research archive
- New ask_user core tool: mid-turn user question with option picking,
  refusing cleanly in autonomous mode, for background workers, and
  without a tty; system prompt points at it instead of prose questions.
- Structural loop control for prompt-JSON CLI backends (opencode,
  grok, claude, codex, gemini): shared cli_json_turn repairs a
  missing JSON envelope exactly once, then accepts prose; prompt
  contract hardened against narrate-without-calling.
- research/agentic-tool-loop-design: 74 sources plus 2 conclusions
  backing the loop-control decisions; INDEX updated to 6 subjects.
2026-10-11 02:54:17 +02:00
retoor 16211480a7 Update 2026-10-11 00:10:46 +02:00
retoor 871f3e5ae6 Docs audit: fix stale claims, cross-link hub docs
- README: 42 tools (was 38), /demo row, TUI section, testing plus
  integration line, full layout map
- tui.md: research link, tests pointer, soften shot-tested claim
- AGENTS.md/tests/README.md/research hubs: cross-links between docs
- Research: forward-correct tui conclusion plus INDEX activity row
  (19 failures fixed, tai_pkg deleted, 320/320 green); audit PASS
2026-10-10 23:51:06 +02:00
retoor 29c489e27a Standalone tai.py: native TUI framework, grouped classes, full suite green
- In-tai.py TUI framework (panels, compositor, z-layers, mouse, focus,
  VT screen, pty sub-terminals, widgets, animation) plus /demo, --demo,
  --demo-shot, tui.md docs, and research/tui-framework-design archive
- Focus safety: Tab/Shift+Tab always cycle, auto-focus prefers
  non-terminals, dialogs restore previous focus on close
- Native Consts/Install/Sandbox/Opencode/SysInfo classes in tai.py;
  module functions delegate so live patches apply; fixes 19 failures
- Retargeted 4 test patches to the real tai.* seams (assertions unchanged)
- Deleted tai_pkg/; tai.py is standalone stdlib-only (bare copy imports)
- AGENTS.md/README.md updated to the standalone architecture
- test_tai.py 320/320 OK, test_seal.py 16/16 OK
2026-10-10 23:45:12 +02:00
retoor 0821adebfa Update. 2026-10-10 22:44:51 +02:00
retoor da51e44359 Some research 2026-10-10 09:25:33 +02:00
retoorandClaude Sonnet 5 9dbd1fe667 Add plexer subsystem, container test infra, and last-resort opencode box backend
- Plexer: always-active terminal multiplexing. NativePlexerController/
  TmuxPlexerController share one interface, chosen by which env var is
  already set (TAI_PLEXER_SOCKET vs TMUX_PANE); NativePlexerBackend is
  the pty.fork()-based wrapper (raw mode, SIGWINCH resize forwarding,
  a Unix-socket control protocol, continuous session logging, a
  Ctrl+A prefix key distinct from tmux's own Ctrl+B). Auto-wraps new
  interactive shells via a .bashrc hook mirroring the existing
  command-not-found install pattern, gated on $TMUX/$TAI_PLEXER_ACTIVE/
  a $HOME/.tai-no-plexer bypass. New plexer_send/read/type/status
  tools, env-gated on a detected controller.
- tests/container.py + docker-compose.yml + tests/docker/Dockerfile:
  a disposable podman/docker image for the tests that must never touch
  a real machine (installing the plexer hook into a real ~/.bashrc, a
  live tmux session). Required suite (test_seal.py, test_tai.py,
  tests/plexer.py, tests/bashrc.py) gates the result; tests/rag.py
  runs as best-effort since its real-LLM dependency can't be satisfied
  inside a disposable container with no nested engine.
- tests/bashrc.py: real end-to-end hook install + bash -i auto-wrap,
  anti-recursion, tmux-active skip, non-interactive skip, a live
  TmuxPlexerController test, and an install/uninstall round-trip.
- tests/plexer.py: NativePlexerBackend under a real pty, plus a
  dedicated robustness pass (file permissions, >64KB payload framing,
  a malformed control request, a genuine self-deadlock fix in the
  write-to-child path).
- tai_test.py: the shared async process-driving framework (pipe/pty
  transport, group-wide kill-and-reap, a StdinBridge for --interactive)
  both test files build on.
- ChatClient last-resort backend: when there's no local opencode CLI
  but the sandbox box is already running, install opencode into it
  (official Node tarball, not apt -- apt's nodejs/npm pull in
  webpack/babel/jest as transitive deps) and route through it instead
  of giving up. Only reachable after the first retry round already
  failed everything else; never creates the box itself. TmuxPlexerController.status()
  fixed to use `list-panes` instead of `display-message -p`, which
  silently fell back to the default pane instead of erroring against
  a dead target.
- Fix 4 pre-existing test_tai.py bugs surfaced by running it in a
  clean environment for the first time: two stale mock signatures
  (subprocess.run's stdout= kwarg, Chat.complete's deadline= kwarg),
  one $TMUX-dependent catalog assertion, one tty-dependent color
  assertion.
- research/: a sourced research archive (Source Dossier/Citation
  Card/Conclusion tiers) backing the above design decisions, with its
  own audit.py consistency checker.
- .gitignore: fix a blanket *.md rule that was about to silently drop
  the entire research/ archive from version control; add __pycache__/
  and the one-off debug transcript this session started from.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-10-10 04:36:05 +02:00