Fix Gradio 6 Textbox error and add SEO keyword-density controls

- Remove show_copy_button (unsupported by Textbox in Gradio 6.x) that crashed startup
- Add three keyword + density% inputs; instruct the tutorial LLM to weave them in at the
target keyword density, leaning toward under-use rather than keyword stuffing

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app.py

@@ -65,8 +65,24 @@ def _safe_name(text: str) -> str:
     return re.sub(r"[^A-Za-z0-9._-]+", "_", text).strip("_")[:60] or "tutorial"
 
 
+def _collect_keywords(kw1, d1, kw2, d2, kw3, d3) -> list[dict]:
+    """Build the [{keyword, density}] list from the three UI keyword/density pairs."""
+    keywords = []
+    for kw, dens in ((kw1, d1), (kw2, d2), (kw3, d3)):
+        kw = (kw or "").strip()
+        if not kw:
+            continue
+        try:
+            dval = float(dens or 0)
+        except (TypeError, ValueError):
+            dval = 0.0
+        keywords.append({"keyword": kw, "density": max(0.0, dval)})
+    return keywords
+
+
 def run_pipeline(topic, hf_token, llm_model, vlm_model, w_llm, w_whisper, lead,
-                 max_minutes, max_shots, progress=gr.Progress()):
+                 max_minutes, max_shots, kw1, d1, kw2, d2, kw3, d3,
+                 progress=gr.Progress()):
     """Generator that yields (status_md, ranking_df, transcript, docx_file)."""
     log: list[str] = []
 
@@ -126,8 +142,11 @@ def run_pipeline(topic, hf_token, llm_model, vlm_model, w_llm, w_whisper, lead,
 
         # 6. Tutorial text -----------------------------------------------------------
         progress(0.72, desc="Writing tutorial")
-        yield status(f"🤖 Generating tutorial with `{llm_model}`…"), ranking, gr.update(value=transcript), gr.update()
-        tut = tutorial_mod.generate_tutorial(transcript, hf_token.strip(), llm_model)
+        keywords = _collect_keywords(kw1, d1, kw2, d2, kw3, d3)
+        kw_note = (" with keywords " + ", ".join(f"{k['keyword']} (~{k['density']:.1f}%)"
+                                                 for k in keywords)) if keywords else ""
+        yield status(f"🤖 Generating tutorial with `{llm_model}`{kw_note}…"), ranking, gr.update(value=transcript), gr.update()
+        tut = tutorial_mod.generate_tutorial(transcript, hf_token.strip(), llm_model, keywords)
 
         # 7. Weighted screenshot selection ------------------------------------------
         selected = frames_mod.select_screenshots(
@@ -182,6 +201,22 @@ def build_ui():
                 vlm_model = gr.Dropdown(VLM_CHOICES, value=VLM_CHOICES[0],
                                         label="Vision model (captions)", allow_custom_value=True)
 
+        with gr.Accordion("SEO keywords (optional)", open=False):
+            gr.Markdown(
+                "Weave up to three keywords into the tutorial at a target **keyword "
+                "density** (% of total words). The writer aims for these but stays "
+                "natural — it may use a keyword somewhat less often than requested."
+            )
+            with gr.Row():
+                kw1 = gr.Textbox(label="Keyword 1", scale=3)
+                d1 = gr.Number(label="Density % 1", value=0, minimum=0, maximum=100, scale=1)
+            with gr.Row():
+                kw2 = gr.Textbox(label="Keyword 2", scale=3)
+                d2 = gr.Number(label="Density % 2", value=0, minimum=0, maximum=100, scale=1)
+            with gr.Row():
+                kw3 = gr.Textbox(label="Keyword 3", scale=3)
+                d3 = gr.Number(label="Density % 3", value=0, minimum=0, maximum=100, scale=1)
+
         with gr.Accordion("Advanced settings", open=False):
             with gr.Row():
                 w_llm = gr.Slider(0.0, 1.0, value=0.4, step=0.05, label="Weight: LLM timestamp")
@@ -198,12 +233,13 @@ def build_ui():
             headers=["#", "Title", "Positive", "Comments", "Note", "URL"],
             label="Sentiment ranking", interactive=False, wrap=True,
         )
-        transcript_box = gr.Textbox(label="Transcript preview", lines=10, max_lines=20, show_copy_button=True)
+        transcript_box = gr.Textbox(label="Transcript preview", lines=10, max_lines=20)
         docx_file = gr.File(label="Download tutorial (.docx)")
 
         run_btn.click(
             run_pipeline,
-            inputs=[topic, hf_token, llm_model, vlm_model, w_llm, w_whisper, lead, max_minutes, max_shots],
+            inputs=[topic, hf_token, llm_model, vlm_model, w_llm, w_whisper, lead,
+                    max_minutes, max_shots, kw1, d1, kw2, d2, kw3, d3],
             outputs=[status_md, ranking_df, transcript_box, docx_file],
         )
     return demo

pipeline/tutorial.py

@@ -46,6 +46,8 @@ Rules:
 - t_llm must be within the transcript's time range.
 - Output valid JSON only. No markdown, no comments in the actual output.
 
+{keyword_block}
+
 Transcript (each line is "[mm:ss] text"):
 ---
 {transcript}
@@ -53,6 +55,27 @@ Transcript (each line is "[mm:ss] text"):
 """
 
 
+def _keyword_block(keywords: list[dict] | None) -> str:
+    """Render the SEO-keyword guidance injected into the prompt."""
+    keywords = [k for k in (keywords or []) if k.get("keyword")]
+    if not keywords:
+        return "SEO keywords: none specified."
+    lines = [
+        "SEO keywords: naturally weave the following keywords into the title, intro and "
+        "step bodies, aiming for roughly the target keyword density (share of total "
+        "words). Treat each target as an upper guide: keep the writing natural and "
+        "readable, and prefer using a keyword somewhat LESS often than the target over "
+        "forcing awkward, repetitive phrasing (no keyword stuffing):",
+    ]
+    for k in keywords:
+        try:
+            dens = float(k.get("density", 0) or 0)
+        except (TypeError, ValueError):
+            dens = 0.0
+        lines.append(f'  - "{k["keyword"]}": target ~{dens:.1f}% of total words')
+    return "\n".join(lines)
+
+
 def _extract_json(text: str) -> dict:
     """Parse the model output into a dict, tolerating code fences / stray prose."""
     text = text.strip()
@@ -95,15 +118,22 @@ def _normalize(data: dict) -> dict:
     }
 
 
-def generate_tutorial(transcript: str, hf_token: str, model: str = DEFAULT_LLM) -> dict:
-    """Call the chat model and return a normalized ``{title, intro, steps}`` dict."""
+def generate_tutorial(transcript: str, hf_token: str, model: str = DEFAULT_LLM,
+                      keywords: list[dict] | None = None) -> dict:
+    """Call the chat model and return a normalized ``{title, intro, steps}`` dict.
+
+    ``keywords`` is an optional list of ``{"keyword", "density"}`` SEO targets the model
+    is asked to weave in at roughly the given keyword density.
+    """
     if not hf_token:
         raise ValueError("An HF token is required for the tutorial LLM (billed to your key).")
 
     truncated = transcript[:MAX_TRANSCRIPT_CHARS]
     if len(transcript) > MAX_TRANSCRIPT_CHARS:
         truncated += "\n[... transcript truncated for length ...]"
-    prompt = _INSTRUCTIONS.replace("{transcript}", truncated)
+    prompt = (_INSTRUCTIONS
+              .replace("{keyword_block}", _keyword_block(keywords))
+              .replace("{transcript}", truncated))
 
     client = InferenceClient(token=hf_token)
     try: