dankclaw/voiceservice/tts-engine-start.sh

@@ -43,10 +43,15 @@ set -euo pipefail
 : "${QWENTTS_ALIAS:=frank-tts-engine}"
 
 # 0.0.0.0 inside the container is not "public". tts-server defaults to
-# 127.0.0.1, which inside a container netns is reachable by nothing — the
-# façade dials this container by its bridge address. The container publishes
-# 8880 on the host's loopback only (diagnostics and the boot warmer), so the
-# only namespace that can reach 0.0.0.0:8880 here is the private voice bridge.
+# 127.0.0.1 (its own usage prints `--host <ip> Listen address (default:
+# 127.0.0.1)`), and inside a container netns a loopback bind is reachable by
+# nothing outside that namespace — the façade dials this container by its bridge
+# address on the private voice network, which is why the address has to be
+# broad. The unit PUBLISHES NOTHING (see
+# dankclaw/voiceservice/quadlet/frank-tts-engine.container: no PublishPort at
+# all, not even 127.0.0.1:8880), so the only namespaces that can reach
+# 0.0.0.0:8880 are that bridge and this container's own loopback — and its own
+# loopback is exactly where the boot warmer and the health probe speak.
 : "${QWENTTS_HOST:=0.0.0.0}"
 : "${QWENTTS_PORT:=8880}"
 

dankclaw/voiceservice/tts-engine-warm.sh

@@ -78,6 +78,31 @@ set -euo pipefail
 # systemd counts the whole warm pass against the unit's start deadline.
 : "${REQUEST_TIMEOUT:=120}"
 
+# The warm text goes into a JSON string literal by interpolation. Two steps make
+# whatever the two readers of scripts/frank-tts-engine.env deliver arrive as the
+# sentence itself:
+#
+# 1. Unwrap ONE shell-style quoting layer. bash (`set -a; source`) strips the
+#    quotes around a value with spaces; podman's `--env-file` does NOT — measured
+#    2026-10-18 against the image's pinned base, `WARM_TEXT="…"` reaches the
+#    container WITH its quotes. Unwrapped only when the whole value is exactly one
+#    quoted string (starts AND ends with `"` and holds no quote inside), so a
+#    sentence that legitimately contains quotes is never mangled.
+# 2. Escape the two characters that would corrupt or end a JSON string: a
+#    backslash, and a double quote.
+#
+# Without step 1 the body is `{"input":""Warm up…"",…}`, the engine's JSON parser
+# rejects it, every voice stays cold, and the boot still reads healthy. Voice NAMES
+# need neither step: the character class checked below admits no quote, no
+# backslash and no control byte.
+warm_text="$WARM_TEXT"
+if (( ${#warm_text} >= 2 )) && [[ "$warm_text" == \"*\" ]]; then
+    inner="${warm_text:1:${#warm_text}-2}"
+    [[ "$inner" != *'"'* ]] && warm_text="$inner"
+fi
+warm_json="${warm_text//\\/\\\\}"
+warm_json="${warm_json//\"/\\\"}"
+
 fail=0
 log() { printf 'frank-tts-engine-warm: %s\n' "$*"; }
 
@@ -135,7 +160,7 @@ for dir in "$VOICES_DIR"/*/; do
     start=$(date +%s%3N)
     if ! curl -fsS --max-time "$REQUEST_TIMEOUT" -o /dev/null \
             -H 'Content-Type: application/json' \
-            --data-binary "{\"input\":\"${WARM_TEXT}\",\"voice\":\"${name}\",\"response_format\":\"wav\"}" \
+            --data-binary "{\"input\":\"${warm_json}\",\"voice\":\"${name}\",\"response_format\":\"wav\"}" \
             "${ENGINE_URL}/v1/audio/speech"; then
         log "voice '${name}': registered, but the warm synthesis failed — first live request stays cold"
         fail=1
@@ -149,7 +174,7 @@ for dir in "$VOICES_DIR"/*/; do
     start=$(date +%s%3N)
     if ! curl -fsS --max-time "$REQUEST_TIMEOUT" -o /dev/null \
             -H 'Content-Type: application/json' \
-            --data-binary "{\"input\":\"${WARM_TEXT}\",\"voice\":\"${name}\",\"response_format\":\"wav\"}" \
+            --data-binary "{\"input\":\"${warm_json}\",\"voice\":\"${name}\",\"response_format\":\"wav\"}" \
             "${ENGINE_URL}/v1/audio/speech"; then
         log "voice '${name}': warm synthesis failed after a cold one that worked"
         fail=1

scripts/frank-tts-engine.env

@@ -126,8 +126,20 @@ HEALTH_WAIT=300
 # second (warm-timing) pass repeats. Fixed on purpose: the cold=/warm= numbers in
 # the journal are comparable across boots only if the input is the same. Kept
 # short because warming a library is serial — one cold decode per voice, 6-8 s
-# each, inside the unit's start deadline. Quoted because podman's env-file parser
-# and a shell `source` must both read the sentence as ONE value.
+# each, inside the unit's start deadline.
+# QUOTED, and the quoting means two different things to the two readers of this
+# file, which is the trap here:
+#   * bash (`set -a; source`, how the repo's seams and any human read it) needs
+#     the quotes — an unquoted value with spaces is word-split and the second
+#     word is executed as a command.
+#   * podman's `--env-file` (how the unit actually reads it) does NOT strip
+#     quotes: measured 2026-10-18 against the image's pinned base, the value
+#     arrives as `"Warm up, one two three."` WITH them. Interpolated into the
+#     hook's JSON body that is `""Warm up…""`, the engine's parser rejects it,
+#     every voice stays cold and the boot still looks healthy.
+# So the value stays quoted for bash and the hook strips one matched pair before
+# it builds the request, then escapes what is left. Both readers now agree, and a
+# sentence containing a quote or a backslash still arrives verbatim.
 WARM_TEXT="Warm up, one two three."
 
 # Per-request ceiling for the hook. A cold voice measures 6-8 s, so 120 s is

tests/frank_tts_engine.bats

@@ -394,6 +394,51 @@ assert {s["response_format"] for s in speech} == {"wav"}, speech
 PY
 }
 
+@test "the warm sentence survives both readers of the env file intact" {
+    # scripts/frank-tts-engine.env is read two ways and they disagree about
+    # quotes. bash (`set -a; source`, what the seams and a human do) strips the
+    # quotes around a value with spaces. podman's --env-file — how the unit really
+    # reads it — does NOT: measured 2026-10-18 against the image's pinned base,
+    # the value lands in the container WITH its quotes. Interpolated raw into the
+    # hook's JSON body that is `""Warm up…"",` — the engine answers 400, no voice
+    # warms, and the boot still reads healthy. So the hook unwraps one
+    # shell-style layer and then escapes, and BOTH shapes must arrive as the
+    # sentence the operator wrote.
+    start_engine_stub
+
+    # Shape A: what podman delivers for `WARM_TEXT="Warm up, one two three."`.
+    run env ENGINE_URL="http://127.0.0.1:$STUB_PORT" VOICES_DIR="$VOICES" \
+        WARM_TEXT='"Warm up, one two three."' bash "$WARM"
+    [ "$status" -eq 0 ] || { echo "$output"; false; }
+    [[ "$output" == *"voice narrator1 cold="*"ms warm="*"ms"* ]] || { echo "$output"; false; }
+    python3 - "$TEST_TMP/journal.jsonl" <<'PY'
+import json, sys
+entries = [json.loads(l) for l in open(sys.argv[1])]
+assert not [e for e in entries if e.get("invalid_json")], entries
+speech = [e for e in entries if e["path"] == "/v1/audio/speech"]
+assert len(speech) == 2, entries
+assert {s["input"] for s in speech} == {"Warm up, one two three."}, speech
+PY
+
+    # Shape B: a value that starts AND ends with a quote but carries more quotes
+    # INSIDE — exactly the shape an unwrap rule must refuse, because peeling the
+    # outer pair would delete characters the operator wrote. It must arrive
+    # character for character (trailing quote included), which also proves the
+    # escaping does not mangle what it is protecting.
+    : > "$TEST_TMP/journal.jsonl"
+    run env ENGINE_URL="http://127.0.0.1:$STUB_PORT" VOICES_DIR="$VOICES" \
+        WARM_TEXT='"He said "hi"\ once"' bash "$WARM"
+    [ "$status" -eq 0 ] || { echo "$output"; false; }
+    python3 - "$TEST_TMP/journal.jsonl" <<'PY'
+import json, sys
+entries = [json.loads(l) for l in open(sys.argv[1])]
+assert not [e for e in entries if e.get("invalid_json")], entries
+speech = [e for e in entries if e["path"] == "/v1/audio/speech"]
+assert len(speech) == 2, entries
+assert {s["input"] for s in speech} == {'"He said "hi"\\ once"'}, speech
+PY
+}
+
 @test "a directory without reference.wav is not a voice, and a mixed-case name is refused" {
     # `justamanifest` must be invisible; `Narrator2` must be loud. The engine
     # lowercases every voice name (tts_voice_name) while frank-tts matches the