Commit Graph
4 Commits
Author SHA1 Message Date
retoor 225babd70a Update documentation: Add file diff rendering to REPL, bump version to 1.17.0, enhance AGENTS.md, and add test for resume interrupt 2026-10-07 06:40:45 +02:00
retoor 85ab7d0b89 Full HTTP web_fetch, live shell streaming, progress budget (v1.16.0)
web_fetch is now a real HTTP client: methods, custom headers, string
bodies, configurable timeout, status plus content-type plus size on
every response, content-aware rendering (HTML to text, JSON raw),
and server error bodies surfaced on HTTP failures. Shell, schema
descriptions, and the system prompt steer all HTTP(S) to web_fetch;
curl/wget shell use earns a model-side hint instead of a refusal.

Shell output streams live in a rolling 4-line window for the active
agent only, with an exit line showing return code, elapsed time,
line count, and byte size. Workers, pipes, and capture stay silent.

Fixed step budget replaced by a progress budget: productive steps
(unseen actions, unseen results, user interaction) reset the stall
counter; identical repeats get a loop warning at 3 and a stop at 5;
wider stalls stop at the patience budget; 500-step total cap
backstops everything. 210 + 16 tests green.
2026-10-07 06:17:52 +02:00
retoor 99d7cb21b1 Bots, unified FTS5 search, and sealed memory-only event index (v1.14.0)
Per-profile bots (system plus history, shared vault): create_bot with
nicknames, /bots and /bot with resume, @mention one-turn routing filed
in both histories.

Unified retrieval: one trigger-synced FTS5 index over records, events,
and audit with safe tokenized MATCH, porter stemming, BM25 rank, and
marked snippets. New search tool with kind filters and graph expansion;
recall, record_search, and audit rank through the same index.

Sealed search without weakening the seal: each boot decrypts events
into a :memory: FTS5 index (newest 10000, incrementally synced, never
on disk), so sealed stores rank like plaintext ones. LIKE fallback kept
for partial tokens. Documented in README under Sealed search with the
researched alternatives (SQLCipher, blind indexes, SSE) and rejections.

Also in this batch: sysinfo, create_skill, markdown renderer with
colors, scheduler with subagent rule, --yolo/--auto, denial-loop fix,
read-before-write guard, WAL plus timeouts, records/graph/spillover,
audit time travel, self-backup and releases, lazy skill blueprints,
smart tagging, profile isolation, lazy tool payload, install
subsystem, and multi-profile rotation fix. 176 + 16 tests green.
2026-10-07 05:41:44 +02:00
retoor b1a22cd2dd Initial commit: single-file autonomous agent with sealed storage, sandbox, and telegram bot 2026-10-07 03:24:02 +02:00