diff options
Diffstat (limited to 'help.html')
| -rw-r--r-- | help.html | 44 |
1 files changed, 34 insertions, 10 deletions
@@ -231,7 +231,7 @@ footer .tagline{color:var(--accent2);margin-top:10px;font-weight:500} <h1>WebX11 <span>Docs</span></h1> </div> <div class="header-meta"> - <span class="badge badge-v">v4.5.9</span> + <span class="badge badge-v">v4.5.11</span> <span class="badge badge-new">28 core · 17 ext</span> <span style="color:var(--text2)">160+ commands</span> </div> @@ -522,7 +522,7 @@ diff a.txt b.txt</pre> <tr><td><code>ai-deny</code></td><td>Deny pending destructive action</td><td><code>ai-deny</code></td></tr> <tr><td><code>ai-stop</code></td><td>Cancel running AI request</td><td><code>ai-stop</code></td></tr> <tr><td><code>ai-compress</code></td><td>Manually compress conversation context</td><td><code>ai-compress</code></td></tr> - <tr><td><code>ai-config</code></td><td>View/set AI loop config (max-turns, max-context, max-context-tokens, confirm-timeout, chat-lock-timeout, skill-debounce, trivial-optimization)</td><td><code>ai-config max-turns 12</code></td></tr> + <tr><td><code>ai-config</code></td><td>View/set AI loop config (max-turns, max-context, max-context-tokens, confirm-timeout(0=disabled), chat-lock-timeout, skill-debounce, trivial-optimization)</td><td><code>ai-config max-turns 12</code></td></tr> <tr><td><code>debug</code></td><td>Toggle AI debug mode</td><td><code>debug</code></td></tr> </table></div> @@ -640,7 +640,7 @@ diff a.txt b.txt</pre> <div class="callout callout-warning"> <span class="callout-title">⚠️ Destructive Tools</span> - <code>write_file</code>, <code>delete_file</code>, <code>run_command</code>, <code>make_directory</code>, <code>edit_module</code> all require confirmation before executing. + <code>write_file</code>, <code>delete_file</code>, <code>make_directory</code>, <code>edit_module</code> require confirmation before executing. <code>run_command</code> only requires confirmation for destructive commands (rm, kill, format) — safe-read commands like <code>ls</code>, <code>find</code>, <code>tree</code> are auto-approved. </div> <h3>Available Tools</h3> @@ -655,7 +655,7 @@ diff a.txt b.txt</pre> <tr><td><code>get_help</code></td><td>List commands</td><td>❌</td></tr> <tr><td><code>web_search</code></td><td>SearXNG + DDG</td><td>❌</td></tr> <tr><td><code>web_fetch</code></td><td>Extract URL content</td><td>❌</td></tr> - <tr><td><code>run_command</code></td><td>Execute terminal cmd</td><td>✅</td></tr> + <tr><td><code>run_command</code></td><td>Execute terminal cmd (safe-read auto-approved)</td><td>❌ (only destructive cmds)</td></tr> <tr><td><code>load_skills</code></td><td>Search relevant skills</td><td>❌</td></tr> <tr><td><code>create/patch/list_skills</code></td><td>Skill management</td><td>❌</td></tr> <tr><td><code>view/edit/test/reload</code></td><td>Module operations</td><td>edit ✅</td></tr> @@ -1178,7 +1178,9 @@ vfs-import</pre> <tr><td><code>nvfs-status</code></td><td>Show index stats and last scan time</td></tr> <tr><td><code>nvfs-resolve <concept></code></td><td>Find files related to a concept (exact + fuzzy)</td></tr> <tr><td><code>nvfs-tree [concept]</code></td><td>Show concept-to-file mapping tree</td></tr> - <tr><td><code>nvfs-config [key] [value]</code></td><td>View/set display limits (fuzzy-limit, tree-files, tree-concepts, resolve-files)</td></tr> +<tr><td><code>nvfs-config [key] [value]</code></td><td>View/set config (fuzzy-limit, tree-files, tree-concepts, resolve-files, deep-index, deep-model)</td></tr> + <tr><td><code>nvfs-alias list|add|remove|clear</code></td><td>Manage concept aliases</td></tr> + <tr><td><code>nvfs-sync [--deep]</code></td><td>Incremental background sync dirty files</td></tr> </table></div> </section> @@ -1330,7 +1332,7 @@ listmods</pre> <section id="ref"> <h2>⚡ Quick Reference</h2> <div class="quick-ref"> - <div class="quick-ref-title">WebX11 v4.5.9</div> + <div class="quick-ref-title">WebX11 v4.5.11</div> <div class="quick-ref-grid"> <div class="quick-ref-item"><span class="cmd">help</span><span class="desc">Show all commands</span></div> <div class="quick-ref-item"><span class="cmd">cls</span><span class="desc">Clear terminal</span></div> @@ -1360,6 +1362,7 @@ listmods</pre> <div class="quick-ref-item"><span class="cmd">base64</span><span class="desc">Encode/decode</span></div> <div class="quick-ref-item"><span class="cmd">nvfs-index</span><span class="desc">Build semantic index</span></div> <div class="quick-ref-item"><span class="cmd">nvfs-resolve</span><span class="desc">Find files by concept</span></div> + <div class="quick-ref-item"><span class="cmd">nvfs-sync</span><span class="desc">Sync dirty files</span></div> <div class="quick-ref-item"><span class="cmd">vfs-size</span><span class="desc">VFS size report</span></div> <div class="quick-ref-item"><span class="cmd">vfs-clean</span><span class="desc">Nuke system dirs</span></div> <div class="quick-ref-item"><span class="cmd">mindmap svg</span><span class="desc">Render mindmap as SVG</span></div> @@ -1386,17 +1389,38 @@ listmods</pre> <div class="version-item"> <div class="v-header"><span class="v-num">v4.5 — June 2026</span><span class="v-date">2026-06-06</span></div> <ul> - <li><strong>Security Config CLI</strong> — <code>security-destructive</code>, <code>security-system</code>, <code>security-whitelist</code>, <code>security-flag</code> add|remove|list with localStorage persistence and boot loading</li> +<li><strong>Security Config CLI</strong> — <code>security-destructive</code>, <code>security-system</code>, <code>security-whitelist</code>, <code>security-flag</code> add|remove|list with localStorage persistence and boot loading</li> <li><strong>Enhanced security command</strong> — Shows all sets (destructive, system, whitelist, flags) plus registered command count</li> <li><strong>AI loop config</strong> — <code>ai-config max-turns|max-context|trivial-optimization</code> with persistence across sessions</li> <li><strong>Unified config CLI</strong> — <code>config</code> command with 4 terminal tuning keys (max-lines, history, pipe-buffer), all persisted in localStorage</li> <li><strong>Extended ai-config</strong> — New keys: <code>max-context-tokens</code>, <code>confirm-timeout</code>, <code>chat-lock-timeout</code>, <code>skill-debounce</code> with range validation</li> + <li><strong>Safe-read run_command</strong> — <code>run_command</code> now command-aware: <code>ls</code>, <code>find</code>, <code>tree</code>, <code>cat</code> auto-approved; only mutating commands require confirmation</li> + <li><strong>Whitelist expanded (50+ cmds)</strong> — find, grep, tree, head, tail, wc, sort, du, diff, which, hostname, and all BusyBox read-only utils now whitelisted</li> + <li><strong>Security-bypass fix</strong> — <code>run_command</code> AI tool now routes through <code>checkAndRun()</code> security layer instead of bypassing</li> + <li><strong>list_files root fallback</strong> — relative paths retry from root if cwd-relative lookup fails</li> + <li><strong>Confirm timeout configurable</strong> — <code>ai-config confirm-timeout <seconds></code> accepts 0+ (0 = no confirm / auto-approve all, no upper cap). Dynamic label on confirm bar shows actual timeout.</li> + <li><strong>Auto-sync Neural VFS</strong> — <code>write_file</code>/<code>mkdir</code>/<code>rm</code>/<code>mv</code>/<code>cp</code> automatically mark index dirty; auto-reindexes after 10s debounce. <code>nvfs-alias</code> command for concept aliases. Hybrid discovery fallback in <code>nvfs-resolve</code> (live VFS scan when index empty). Staleness warning in <code>nvfs-status</code> if index >4h old.</li> + <li><strong>5 modules whitelisted</strong> — system-health, server, servers, server-check, monitor run directly</li> <li><strong>OllamaModule consolidated</strong> — Removed duplicate <code>ollamamodels</code> code path (redirects to <code>models</code>), centralized endpoint via <code>ollamaManager.endpoint</code></li> <li><strong>Neural VFS async indexing</strong> — Chunked processing with progress percentage, no UI freeze on large VFS. Improved <code>_summarize</code> (section heading → paragraph → sentence → fallback)</li> <li><strong>Neural VFS display-limit config</strong> — <code>nvfs-config</code> command with 4 keys (fuzzy-limit, tree-files, tree-concepts, resolve-files), persisted</li> <li><strong>Orchestrator event bus</strong> — In-memory pub/sub for instant A2A delivery (VFS polling remains as fallback). Improved <code>_deriveCapabilities</code> with 14 keyword mappings</li> <li><strong>Orchestrator extended config</strong> — 4 new interval keys (a2a-poll-interval, heartbeat-check, idle-sweep-interval, dead-purge-timeout) + all config now persists across sessions</li> - <li>Cache: <code>2026-06-06-v4.5.9</code> — hard refresh required</li> + <li>Cache: <code>2026-06-06-v4.5.11</code> — hard refresh required</li> + </ul> + </div> + + <div class="version-item"> + <div class="v-header"><span class="v-num">v4.5.12 — June 2026</span><span class="v-date">2026-06-06</span></div> + <ul> + <li><strong>Tiered Indexing toggle</strong> — <code>nvfs-config deep-index on|off</code> switches between Fast (metadata-only, instant) and Deep (LLM-assisted, semantic) modes. Off by default. <code>nvfs-index --deep</code> or <code>nvfs-sync --deep</code> forces deep mode per-run.</li> + <li><strong>Configurable deep model</strong> — <code>nvfs-config deep-model <name></code> selects the LLM for deep indexing. Default: <code>ministral-3:3b-cloud</code> for speed. Example: <code>nvfs-config deep-model gemma4:31b-cloud</code> for deeper analysis.</li> + <li><strong>Status bar indicator</strong> — Real-time 🧠 status in terminal bar: concept count + 🌊 wave for deep mode, 🟡 amber for pending auto-sync, 🧠 Deep Indexing progress percentage during LLM processing.</li> + <li><strong>nvfs-sync command</strong> — <code>nvfs-sync [--deep]</code> for incremental background sync of dirty files.</li> + <li><strong>Deep concept extraction</strong> — LLM generates 2-5 semantic concepts per file (configurable model via <code>nvfs-config deep-model</code>, default <code>ministral-3:3b-cloud</code>, 2000 chars, 3-file batches with UI yield). Fast filename-concepts stored immediately, LLM concepts augment in background queue.</li> + <li><strong>nvfs-status mode display</strong> — Shows 🌊 Deep or ⚡ Fast mode.</li> + <li><strong>LLM self-healing</strong> — If Ollama disconnected, deep mode silently falls back to fast metadata-only.</li> + <li>Cache: <code>2026-06-06-v4.5.12</code> — hard refresh required</li> </ul> </div> @@ -1414,13 +1438,13 @@ listmods</pre> </div> <div class="version-item"> - <div class="v-header"><span class="v-num">v4.5.10 — June 2026</span><span class="v-date">2026-06-06</span></div> + <div class="v-header"><span class="v-num">v4.5.11 — June 2026</span><span class="v-date">2026-06-06</span></div> <ul> <li><strong>init(terminal) fix</strong> — <code>loadModuleFromCode</code> and <code>loadModuleFromURL</code> now pass <code>this.terminal</code> to <code>init()</code>, fixing PredictorModule fatal error</li> <li><strong>Save & Test returns value</strong> — <code>saveCodeEditor</code> checks <code>loadModuleFromCode</code> return before printing success</li> <li><strong>StateSyncModule recovered</strong> — Extracted from backup, saved to <code>~/.hermes/scripts/</code></li> <li><strong>PredictorModule hasSync</strong> — Feature detection for sync/recall tasks with tuned duration/turn prediction</li> - <li>Cache: <code>2026-06-06-v4.5.9</code> — hard refresh required</li> + <li>Cache: <code>2026-06-06-v4.5.11</code> — hard refresh required</li> </ul> </div> |