agentvibes 5.2.1 → 5.4.0

package/.claude/hooks-windows/soprano-gradio-synth.py

@@ -1,153 +1,153 @@
-#!/usr/bin/env python3
-#
-# File: .claude/hooks-windows/soprano-gradio-synth.py
-#
-# AgentVibes - Finally, your AI Agents can Talk Back!
-# Website: https://agentvibes.org
-# Repository: https://github.com/paulpreibisch/AgentVibes
-#
-# Co-created by Paul Preibisch with Claude AI
-# Copyright (c) 2025 Paul Preibisch
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-# ---
-#
-# Soprano Gradio WebUI synthesizer helper.
-# Calls the Soprano WebUI's Gradio API and saves the result as a WAV file.
-# Uses only Python stdlib (json, sys, urllib) — no extra dependencies.
-#
-# Usage: python3 soprano-gradio-synth.py "text to speak" output.wav [port]
-#
-"""
-Soprano Gradio WebUI synthesizer helper for AgentVibes.
-
-Calls the Soprano WebUI's Gradio API via the Server-Sent Events (SSE) protocol
-and downloads the generated audio as a WAV file.
-
-Flow:
-  1. Submit generation request -> get event_id
-  2. Poll SSE stream for audio file URL
-  3. Download WAV file to output path
-
-See: https://github.com/ekwek1/soprano
-"""
-import json
-import sys
-import urllib.request
-import urllib.error
-
-
-def synth(text: str, output_path: str, port: int = 7860) -> None:
-    base = f"http://127.0.0.1:{port}"
-
-    # Step 1: Submit generation request
-    # Args: text, temperature, top_p, repetition_penalty, chunk_size, streaming
-    payload = json.dumps({
-        "data": [text, 0.0, 0.95, 1.2, 1, False]
-    }).encode()
-
-    event_id = submit_request(base, payload)
-
-    # Step 2: Poll SSE stream for audio file URL
-    audio_url = poll_for_result(base, event_id)
-
-    # Step 3: Download the audio file (validate localhost to prevent SSRF)
-    download_file(audio_url, output_path, port)
-
-
-def submit_request(base: str, payload: bytes) -> str:
-    """Submit generation request to Gradio API, return event_id."""
-    for api_base in ["/gradio_api/call", "/call"]:
-        url = f"{base}{api_base}/generate_speech"
-        req = urllib.request.Request(
-            url,
-            data=payload,
-            headers={"Content-Type": "application/json"},
-        )
-        try:
-            with urllib.request.urlopen(req, timeout=30) as resp:
-                return json.loads(resp.read())["event_id"]
-        except urllib.error.URLError:
-            continue
-
-    raise RuntimeError("Could not reach Soprano WebUI API")
-
-
-def poll_for_result(base: str, event_id: str) -> str:
-    """Poll SSE endpoint until audio file URL is returned."""
-    for api_base in ["/gradio_api/call", "/call"]:
-        url = f"{base}{api_base}/generate_speech/{event_id}"
-        req = urllib.request.Request(url)
-        try:
-            with urllib.request.urlopen(req, timeout=120) as resp:
-                for raw_line in resp:
-                    line = raw_line.decode("utf-8", errors="replace").strip()
-                    if not line.startswith("data: "):
-                        continue
-                    try:
-                        parsed = json.loads(line[6:])
-                    except json.JSONDecodeError:
-                        continue
-                    # Response format: [{"path": "...", "url": "...", ...}, "status string"]
-                    if isinstance(parsed, list) and len(parsed) >= 1:
-                        audio = parsed[0]
-                        if isinstance(audio, dict) and "url" in audio:
-                            return audio["url"]
-            break
-        except urllib.error.URLError:
-            continue
-
-    raise RuntimeError("No audio URL in Soprano response")
-
-
-def download_file(url: str, output_path: str, port: int = 7860) -> None:
-    """Download audio file from Gradio file server.
-
-    Security: Validates URL points to localhost to prevent SSRF.
-    """
-    # Validate URL is localhost to prevent SSRF via crafted Gradio responses
-    allowed_prefixes = [
-        f"http://127.0.0.1:{port}/",
-        f"http://localhost:{port}/",
-    ]
-    if not any(url.startswith(prefix) for prefix in allowed_prefixes):
-        raise RuntimeError(f"Refused download from non-localhost URL: {url[:80]}")
-
-    req = urllib.request.Request(url)
-    with urllib.request.urlopen(req, timeout=30) as resp:
-        with open(output_path, "wb") as f:
-            while True:
-                chunk = resp.read(8192)
-                if not chunk:
-                    break
-                f.write(chunk)
-
-
-if __name__ == "__main__":
-    if len(sys.argv) < 3:
-        print(f"Usage: {sys.argv[0]} \"text\" output.wav [port]", file=sys.stderr)
-        sys.exit(1)
-
-    text = sys.argv[1]
-    output = sys.argv[2]
-    port = int(sys.argv[3]) if len(sys.argv) > 3 else 7860
-    if not (1 <= port <= 65535):
-        print(f"Error: Invalid port number: {port}", file=sys.stderr)
-        sys.exit(1)
-
-    try:
-        synth(text, output, port)
-    except Exception as e:
-        print(f"Error: {e}", file=sys.stderr)
-        sys.exit(1)
+#!/usr/bin/env python3
+#
+# File: .claude/hooks-windows/soprano-gradio-synth.py
+#
+# AgentVibes - Finally, your AI Agents can Talk Back!
+# Website: https://agentvibes.org
+# Repository: https://github.com/paulpreibisch/AgentVibes
+#
+# Co-created by Paul Preibisch with Claude AI
+# Copyright (c) 2025 Paul Preibisch
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+# ---
+#
+# Soprano Gradio WebUI synthesizer helper.
+# Calls the Soprano WebUI's Gradio API and saves the result as a WAV file.
+# Uses only Python stdlib (json, sys, urllib) — no extra dependencies.
+#
+# Usage: python3 soprano-gradio-synth.py "text to speak" output.wav [port]
+#
+"""
+Soprano Gradio WebUI synthesizer helper for AgentVibes.
+
+Calls the Soprano WebUI's Gradio API via the Server-Sent Events (SSE) protocol
+and downloads the generated audio as a WAV file.
+
+Flow:
+  1. Submit generation request -> get event_id
+  2. Poll SSE stream for audio file URL
+  3. Download WAV file to output path
+
+See: https://github.com/ekwek1/soprano
+"""
+import json
+import sys
+import urllib.request
+import urllib.error
+
+
+def synth(text: str, output_path: str, port: int = 7860) -> None:
+    base = f"http://127.0.0.1:{port}"
+
+    # Step 1: Submit generation request
+    # Args: text, temperature, top_p, repetition_penalty, chunk_size, streaming
+    payload = json.dumps({
+        "data": [text, 0.0, 0.95, 1.2, 1, False]
+    }).encode()
+
+    event_id = submit_request(base, payload)
+
+    # Step 2: Poll SSE stream for audio file URL
+    audio_url = poll_for_result(base, event_id)
+
+    # Step 3: Download the audio file (validate localhost to prevent SSRF)
+    download_file(audio_url, output_path, port)
+
+
+def submit_request(base: str, payload: bytes) -> str:
+    """Submit generation request to Gradio API, return event_id."""
+    for api_base in ["/gradio_api/call", "/call"]:
+        url = f"{base}{api_base}/generate_speech"
+        req = urllib.request.Request(
+            url,
+            data=payload,
+            headers={"Content-Type": "application/json"},
+        )
+        try:
+            with urllib.request.urlopen(req, timeout=30) as resp:
+                return json.loads(resp.read())["event_id"]
+        except urllib.error.URLError:
+            continue
+
+    raise RuntimeError("Could not reach Soprano WebUI API")
+
+
+def poll_for_result(base: str, event_id: str) -> str:
+    """Poll SSE endpoint until audio file URL is returned."""
+    for api_base in ["/gradio_api/call", "/call"]:
+        url = f"{base}{api_base}/generate_speech/{event_id}"
+        req = urllib.request.Request(url)
+        try:
+            with urllib.request.urlopen(req, timeout=120) as resp:
+                for raw_line in resp:
+                    line = raw_line.decode("utf-8", errors="replace").strip()
+                    if not line.startswith("data: "):
+                        continue
+                    try:
+                        parsed = json.loads(line[6:])
+                    except json.JSONDecodeError:
+                        continue
+                    # Response format: [{"path": "...", "url": "...", ...}, "status string"]
+                    if isinstance(parsed, list) and len(parsed) >= 1:
+                        audio = parsed[0]
+                        if isinstance(audio, dict) and "url" in audio:
+                            return audio["url"]
+            break
+        except urllib.error.URLError:
+            continue
+
+    raise RuntimeError("No audio URL in Soprano response")
+
+
+def download_file(url: str, output_path: str, port: int = 7860) -> None:
+    """Download audio file from Gradio file server.
+
+    Security: Validates URL points to localhost to prevent SSRF.
+    """
+    # Validate URL is localhost to prevent SSRF via crafted Gradio responses
+    allowed_prefixes = [
+        f"http://127.0.0.1:{port}/",
+        f"http://localhost:{port}/",
+    ]
+    if not any(url.startswith(prefix) for prefix in allowed_prefixes):
+        raise RuntimeError(f"Refused download from non-localhost URL: {url[:80]}")
+
+    req = urllib.request.Request(url)
+    with urllib.request.urlopen(req, timeout=30) as resp:
+        with open(output_path, "wb") as f:
+            while True:
+                chunk = resp.read(8192)
+                if not chunk:
+                    break
+                f.write(chunk)
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 3:
+        print(f"Usage: {sys.argv[0]} \"text\" output.wav [port]", file=sys.stderr)
+        sys.exit(1)
+
+    text = sys.argv[1]
+    output = sys.argv[2]
+    port = int(sys.argv[3]) if len(sys.argv) > 3 else 7860
+    if not (1 <= port <= 65535):
+        print(f"Error: Invalid port number: {port}", file=sys.stderr)
+        sys.exit(1)
+
+    try:
+        synth(text, output, port)
+    except Exception as e:
+        print(f"Error: {e}", file=sys.stderr)
+        sys.exit(1)

package/.claude/hooks-windows/speed-manager.ps1

@@ -1,166 +1,166 @@
-#
-# File: .claude/hooks-windows/speed-manager.ps1
-#
-# AgentVibes - Finally, your AI Agents can Talk Back!
-# Website: https://agentvibes.org
-# Copyright (c) 2025 Paul Preibisch
-# Licensed under the Apache License, Version 2.0
-
-param(
-    [Parameter(Position=0)]
-    [string]$Command = "help",
-    [Parameter(Position=1)]
-    [string]$Arg1 = ""
-)
-
-$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
-$ClaudeDir = Split-Path -Parent $ScriptDir
-
-# Determine config directory
-if ($env:CLAUDE_PROJECT_DIR -and (Test-Path "$env:CLAUDE_PROJECT_DIR\.claude")) {
-    $ConfigDir = Join-Path $env:CLAUDE_PROJECT_DIR ".claude" "config"
-} else {
-    $ConfigDir = Join-Path $ClaudeDir "config"
-}
-
-if (-not (Test-Path $ConfigDir)) { New-Item -ItemType Directory -Path $ConfigDir -Force | Out-Null }
-
-$MainSpeedFile = Join-Path $ConfigDir "tts-speech-rate.txt"
-$TargetSpeedFile = Join-Path $ConfigDir "tts-target-speech-rate.txt"
-
-# Legacy migration
-$LegacyMain = Join-Path $ConfigDir "piper-speech-rate.txt"
-$LegacyTarget = Join-Path $ConfigDir "piper-target-speech-rate.txt"
-if ((Test-Path $LegacyMain) -and -not (Test-Path $MainSpeedFile)) {
-    Copy-Item $LegacyMain $MainSpeedFile
-}
-if ((Test-Path $LegacyTarget) -and -not (Test-Path $TargetSpeedFile)) {
-    Copy-Item $LegacyTarget $TargetSpeedFile
-}
-
-function Parse-SpeedValue {
-    param([string]$Input)
-
-    switch -Regex ($Input) {
-        '^(normal|1x|1\.0)$' { return "1.0" }
-        '^(slow|slower|0\.5x)$' { return "0.5" }
-        '^(fast|2x|2\.0)$' { return "2.0" }
-        '^(faster|3x|3\.0)$' { return "3.0" }
-    }
-
-    $val = $Input -replace '^[+-]', '' -replace 'x$', ''
-    if ($val -match '^\d+\.?\d*$') { return $val }
-    return "ERROR"
-}
-
-function Set-Speed {
-    param([bool]$IsTarget = $false, [string]$SpeedInput)
-
-    if (-not $SpeedInput) {
-        Write-Output "Error: Speed value required"
-        Write-Output "Usage: speed-manager.ps1 [target] <speed>"
-        exit 1
-    }
-
-    $speedValue = Parse-SpeedValue $SpeedInput
-    if ($speedValue -eq "ERROR") {
-        Write-Output "Invalid speed value: $SpeedInput"
-        Write-Output "Valid values: normal, 0.5x, 1x, 2x, 3x"
-        exit 1
-    }
-
-    if ($IsTarget) {
-        $configFile = $TargetSpeedFile
-        $voiceType = "target language"
-    } else {
-        $configFile = $MainSpeedFile
-        $voiceType = "main voice"
-    }
-
-    Set-Content -Path $configFile -Value $speedValue -NoNewline
-
-    Write-Output "Speech speed set for $voiceType"
-    Write-Output ""
-    Write-Output "Speed: ${speedValue}x"
-
-    switch ($speedValue) {
-        "0.5" { Write-Output "Effect: Half speed (slower)" }
-        "1.0" { Write-Output "Effect: Normal speed" }
-        "2.0" { Write-Output "Effect: Double speed (faster)" }
-        "3.0" { Write-Output "Effect: Triple speed (very fast)" }
-        default {
-            if ([double]$speedValue -gt 1.0) {
-                Write-Output "Effect: Faster speech"
-            } else {
-                Write-Output "Effect: Slower speech"
-            }
-        }
-    }
-}
-
-function Get-Speed {
-    Write-Output "---------------------------------------"
-    Write-Output "   Current Speech Speed Settings"
-    Write-Output "---------------------------------------"
-    Write-Output ""
-
-    if (Test-Path $MainSpeedFile) {
-        $mainSpeed = (Get-Content $MainSpeedFile | Where-Object { $_ -notmatch '^\s*#' -and $_.Trim() -ne '' } | Select-Object -Last 1).Trim()
-        Write-Output "Main voice: ${mainSpeed}x"
-    } else {
-        Write-Output "Main voice: 1.0x (default, normal speed)"
-    }
-
-    if (Test-Path $TargetSpeedFile) {
-        $targetSpeed = (Get-Content $TargetSpeedFile | Where-Object { $_ -notmatch '^\s*#' -and $_.Trim() -ne '' } | Select-Object -Last 1).Trim()
-        Write-Output "Target language: ${targetSpeed}x"
-    } else {
-        Write-Output "Target language: 0.5x (default, slower for learning)"
-    }
-
-    Write-Output ""
-    Write-Output "Scale: 0.5x=slower, 1.0x=normal, 2.0x=faster, 3.0x=very fast"
-    Write-Output "---------------------------------------"
-}
-
-switch -Regex ($Command) {
-    "^target$" {
-        Set-Speed -IsTarget $true -SpeedInput $Arg1
-    }
-    "^(get|status)$" {
-        Get-Speed
-    }
-    "^(normal|fast|slow|slower)$" {
-        Set-Speed -SpeedInput $Command
-    }
-    "^.*x$" {
-        Set-Speed -SpeedInput $Command
-    }
-    "^\d+\.?\d*$" {
-        Set-Speed -SpeedInput $Command
-    }
-    "^[+-]" {
-        Set-Speed -SpeedInput $Command
-    }
-    "^help$" {
-        Write-Output "Speech Speed Manager"
-        Write-Output ""
-        Write-Output "Usage:"
-        Write-Output "  speed-manager.ps1 <speed>          Set main voice speed"
-        Write-Output "  speed-manager.ps1 target <speed>   Set target language speed"
-        Write-Output "  speed-manager.ps1 get              Show current speeds"
-        Write-Output ""
-        Write-Output "Speed values: 0.5x, 1x, 2x, 3x, normal, slow, fast, faster"
-    }
-    default {
-        # Try as speed value
-        $parsed = Parse-SpeedValue $Command
-        if ($parsed -ne "ERROR") {
-            Set-Speed -SpeedInput $Command
-        } else {
-            Write-Output "Unknown command: $Command"
-            Write-Output "Usage: speed-manager.ps1 {get|target|<speed>}"
-            exit 1
-        }
-    }
-}
+#
+# File: .claude/hooks-windows/speed-manager.ps1
+#
+# AgentVibes - Finally, your AI Agents can Talk Back!
+# Website: https://agentvibes.org
+# Copyright (c) 2025 Paul Preibisch
+# Licensed under the Apache License, Version 2.0
+
+param(
+    [Parameter(Position=0)]
+    [string]$Command = "help",
+    [Parameter(Position=1)]
+    [string]$Arg1 = ""
+)
+
+$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
+$ClaudeDir = Split-Path -Parent $ScriptDir
+
+# Determine config directory
+if ($env:CLAUDE_PROJECT_DIR -and (Test-Path "$env:CLAUDE_PROJECT_DIR\.claude")) {
+    $ConfigDir = Join-Path $env:CLAUDE_PROJECT_DIR ".claude" "config"
+} else {
+    $ConfigDir = Join-Path $ClaudeDir "config"
+}
+
+if (-not (Test-Path $ConfigDir)) { New-Item -ItemType Directory -Path $ConfigDir -Force | Out-Null }
+
+$MainSpeedFile = Join-Path $ConfigDir "tts-speech-rate.txt"
+$TargetSpeedFile = Join-Path $ConfigDir "tts-target-speech-rate.txt"
+
+# Legacy migration
+$LegacyMain = Join-Path $ConfigDir "piper-speech-rate.txt"
+$LegacyTarget = Join-Path $ConfigDir "piper-target-speech-rate.txt"
+if ((Test-Path $LegacyMain) -and -not (Test-Path $MainSpeedFile)) {
+    Copy-Item $LegacyMain $MainSpeedFile
+}
+if ((Test-Path $LegacyTarget) -and -not (Test-Path $TargetSpeedFile)) {
+    Copy-Item $LegacyTarget $TargetSpeedFile
+}
+
+function Parse-SpeedValue {
+    param([string]$Input)
+
+    switch -Regex ($Input) {
+        '^(normal|1x|1\.0)$' { return "1.0" }
+        '^(slow|slower|0\.5x)$' { return "0.5" }
+        '^(fast|2x|2\.0)$' { return "2.0" }
+        '^(faster|3x|3\.0)$' { return "3.0" }
+    }
+
+    $val = $Input -replace '^[+-]', '' -replace 'x$', ''
+    if ($val -match '^\d+\.?\d*$') { return $val }
+    return "ERROR"
+}
+
+function Set-Speed {
+    param([bool]$IsTarget = $false, [string]$SpeedInput)
+
+    if (-not $SpeedInput) {
+        Write-Output "Error: Speed value required"
+        Write-Output "Usage: speed-manager.ps1 [target] <speed>"
+        exit 1
+    }
+
+    $speedValue = Parse-SpeedValue $SpeedInput
+    if ($speedValue -eq "ERROR") {
+        Write-Output "Invalid speed value: $SpeedInput"
+        Write-Output "Valid values: normal, 0.5x, 1x, 2x, 3x"
+        exit 1
+    }
+
+    if ($IsTarget) {
+        $configFile = $TargetSpeedFile
+        $voiceType = "target language"
+    } else {
+        $configFile = $MainSpeedFile
+        $voiceType = "main voice"
+    }
+
+    Set-Content -Path $configFile -Value $speedValue -NoNewline
+
+    Write-Output "Speech speed set for $voiceType"
+    Write-Output ""
+    Write-Output "Speed: ${speedValue}x"
+
+    switch ($speedValue) {
+        "0.5" { Write-Output "Effect: Half speed (slower)" }
+        "1.0" { Write-Output "Effect: Normal speed" }
+        "2.0" { Write-Output "Effect: Double speed (faster)" }
+        "3.0" { Write-Output "Effect: Triple speed (very fast)" }
+        default {
+            if ([double]$speedValue -gt 1.0) {
+                Write-Output "Effect: Faster speech"
+            } else {
+                Write-Output "Effect: Slower speech"
+            }
+        }
+    }
+}
+
+function Get-Speed {
+    Write-Output "---------------------------------------"
+    Write-Output "   Current Speech Speed Settings"
+    Write-Output "---------------------------------------"
+    Write-Output ""
+
+    if (Test-Path $MainSpeedFile) {
+        $mainSpeed = (Get-Content $MainSpeedFile | Where-Object { $_ -notmatch '^\s*#' -and $_.Trim() -ne '' } | Select-Object -Last 1).Trim()
+        Write-Output "Main voice: ${mainSpeed}x"
+    } else {
+        Write-Output "Main voice: 1.0x (default, normal speed)"
+    }
+
+    if (Test-Path $TargetSpeedFile) {
+        $targetSpeed = (Get-Content $TargetSpeedFile | Where-Object { $_ -notmatch '^\s*#' -and $_.Trim() -ne '' } | Select-Object -Last 1).Trim()
+        Write-Output "Target language: ${targetSpeed}x"
+    } else {
+        Write-Output "Target language: 0.5x (default, slower for learning)"
+    }
+
+    Write-Output ""
+    Write-Output "Scale: 0.5x=slower, 1.0x=normal, 2.0x=faster, 3.0x=very fast"
+    Write-Output "---------------------------------------"
+}
+
+switch -Regex ($Command) {
+    "^target$" {
+        Set-Speed -IsTarget $true -SpeedInput $Arg1
+    }
+    "^(get|status)$" {
+        Get-Speed
+    }
+    "^(normal|fast|slow|slower)$" {
+        Set-Speed -SpeedInput $Command
+    }
+    "^.*x$" {
+        Set-Speed -SpeedInput $Command
+    }
+    "^\d+\.?\d*$" {
+        Set-Speed -SpeedInput $Command
+    }
+    "^[+-]" {
+        Set-Speed -SpeedInput $Command
+    }
+    "^help$" {
+        Write-Output "Speech Speed Manager"
+        Write-Output ""
+        Write-Output "Usage:"
+        Write-Output "  speed-manager.ps1 <speed>          Set main voice speed"
+        Write-Output "  speed-manager.ps1 target <speed>   Set target language speed"
+        Write-Output "  speed-manager.ps1 get              Show current speeds"
+        Write-Output ""
+        Write-Output "Speed values: 0.5x, 1x, 2x, 3x, normal, slow, fast, faster"
+    }
+    default {
+        # Try as speed value
+        $parsed = Parse-SpeedValue $Command
+        if ($parsed -ne "ERROR") {
+            Set-Speed -SpeedInput $Command
+        } else {
+            Write-Output "Unknown command: $Command"
+            Write-Output "Usage: speed-manager.ps1 {get|target|<speed>}"
+            exit 1
+        }
+    }
+}