@kolbo/mcp 1.81.1 → 1.81.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kolbo/mcp",
-  "version": "1.81.1",
+  "version": "1.81.2",
   "description": "Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code",
   "main": "src/index.js",
   "bin": {

package/skill/GENERATED.md

@@ -1,6 +1,6 @@
 # AUTO-GENERATED — do not edit
 
-This tree is mirrored from kolbo-code@00aade6, the single source of truth.
+This tree is mirrored from kolbo-code@6836af5, the single source of truth.
 Canonical source: packages/opencode/skills/kolbo/
 Distribution: .github/workflows/sync-skill-to-plugin.yml
 

package/skill/SKILL.md

@@ -1,5 +1,5 @@
 ---
-version: 0.9.3
+version: 0.9.6
 name: kolbo
 description: |
   Generate, edit, analyze, and direct creative media through Kolbo AI: images,
@@ -20,7 +20,29 @@ allowed-tools: Bash, Read, Write, Edit
 
 You have direct access to the Kolbo AI creative platform via MCP tools (auto-configured by `kolbo auth login`). Use them to generate and deliver real content — do NOT just describe what you would create.
 
-> 🚫 **Don't dump generated URLs as bare text or markdown links in chat** — the UI already renders artifacts as a gallery tile + canvas. Refer by description ("the rainy scene"), store URLs in `.kolbo/production.md`. INLINE `![](url)` images ARE allowed for catalog-style replies (per-item thumbs in numbered lists).
+> 🚫 **Don't dump generated URLs as bare text or markdown links in chat** — the UI already shows results in **Library** (right panel) and on the generation card. Refer by description ("the rainy scene"), store URLs in `.kolbo/production.md`. INLINE `![](url)` images ARE allowed for catalog-style replies (per-item thumbs in numbered lists).
+
+## ⚠️ Source of truth for generations (HARD RULE — read this)
+
+Agents keep getting confused because three UIs show the same job. Use this map — never invent a fourth:
+
+| Surface | What it is | Trust it for |
+|---|---|---|
+| **Library** (right panel — "This session" / "All media") | User-facing gallery of **completed** media | "Is the user's output there?" Point humans here. Finished clips/images land automatically — do **not** `list_media` / `get_media` just to verify a `generate_*` you just ran. |
+| **Chat generation card** | Progress chrome while a job is in flight | Status badge only (`Generating` / done). A **black / empty preview while Generating is NORMAL** — the iframe has nothing to paint yet. It is **not** failure, not "lost", not a reason to re-fire. |
+| **`get_generation_status`** (MCP) | Agent API for job state | Whether the server job is `completed` / `failed` / still running, and the final `urls`. This is your SoT for in-flight work — **not** the card pixels. |
+| **`.kolbo/production.md`** | Your private log across turns | Ids + URLs after success. Compaction-safe memory — not the user gallery. |
+
+**Do NOT:**
+- Treat an empty/black chat card as "generation failed" or "nothing produced".
+- Re-call `generate_*` because Library still shows a K/logo spinner tile while the job is running — that tile **is** the in-progress placeholder for the same job.
+- Call `list_media` / `get_media` / `list_session_generations` to "check if it worked" after a generate you already submitted — that burns credits/context and can pollute the session.
+- Tell the user to look at chat history for finals — tell them **Library → This session**.
+
+**Do:**
+- After `submitted` / `_timed_out`: end the turn, or one `get_generation_status(..., wait=true)`.
+- When done: say the result is in Library; log URLs to `.kolbo/production.md`.
+- If the user asks "where is it?" → Library (This session). If they ask "is it done?" and you don't have urls yet → `get_generation_status` once.
 
 This file is the **always-loaded core**: tool inventory + universal hard rules + routing index. For any model-specific prompt rules, Visual DNA workflow, production log format, marketing workflow, cost validation, etc., **Read the matching `references/` file from the index below**. Don't try to remember the rules — load the file when you need them.
 
@@ -218,7 +240,7 @@ Do **not** call `generate_*` / `generate_elements` / `generate_image_edit` until
 
 `generate_elements`, Seedance 2 / 2.5, WAN, MiniMax H3, Gemini, and any Visual DNA video share **one** compile shape — the Locked Intro in `references/models/seedance.md`. Load `elements-prompting` first (craft, `@Image N` mapping, eight elements), then compile:
 
-`Total: Xs / N shots / AR` → `[GLOBAL LOOK – LOCKED, APPLIES TO EVERY SHOT]` → `[CAST – IDENTICAL IN EVERY SHOT]` (each person is `@DNAName`) → `[LOCATION]` → `SHOT N — 0:00–0:02 — …`
+`N connected cinematic shots, Xs total, AR, Multishot ON` → `Total: Xs / N shots / AR` → `[GLOBAL LOOK – LOCKED, APPLIES TO EVERY SHOT]` → `[CAST – IDENTICAL IN EVERY SHOT]` (each person is `@DNAName`) → `[LOCATION]` → LOCATION MAP / CONTINUITY / PHYSICS → `SHOT N — 0:00–0:02 — …` (ranges sum to Xs) → closing `Total: Xs / N shots / AR`. Pass MCP `duration: X` matching that Total. Omitting Total / Multishot is a failed compile — same contract as the Kolbo help widget.
 
 Write the beats at FULL DEPTH. The cap is 15,000 characters on Seedance 2.5 (10,000 on 2.0) — a 30s / 8+ shot compile should land around 4k–9k, and every beat carries its own camera move, a performance task for the speaker AND the listeners, prop/hand state, and the sound in that beat. A one-line shot beat is under-written; the structure alone is not the craft. Read `references/models/seedance25.md` before compiling.
 
@@ -268,9 +290,13 @@ A user-named tool — in any language — overrides every other rule. Recognized
    - Auto-select → **only when no model was named on this task**. Then pick from "Auto-selectable" (models with a `summary`). Cheapest fit. Prefer `[RECOMMENDED]` when cost is similar.
    - Never auto-select from "Named-only" section.
 5. **Validate inputs** against model caps — see `references/workflows/cost-and-validation.md`.
-6. **How calls work**: each tool blocks until generation is fully complete. Images: seconds. Video: minutes. Multiple tool calls in one response run concurrently. On hosts with live widgets the tool instead returns `submitted` instantly — the card updates on its own; you only need `get_generation_status` when a follow-up step needs the output URLs.
-7. **Checking status — NEVER poll in a loop**: `get_generation_status` takes `wait=true` (blocks server-side until done, ~3 min) and `generation_ids` (check MANY generations in ONE call — returns `all_done` + which are still running). One `wait=true` call replaces any polling loop. If it comes back with some still processing, call it ONCE more with `wait=true` and the remaining ids.
-8. **Share the URL** after success. Never fabricate URLs.
+6. **How calls work**: each tool blocks until generation is fully complete. Images: seconds. Video: minutes. Multiple tool calls in one response run concurrently. On hosts with live widgets the tool instead returns `submitted` (or `_timed_out`) instantly — the card updates on its own.
+7. **🛑 After `submitted` / `_timed_out` — END THE TURN (credit guard)**: Do **not** keep thinking, writing skills, editing files, or planning "next steps" while a generation is still running. That burns the user's coding/chat credits for nothing. Either:
+   - **Stop immediately** after telling the user it's generating in Library / the card above (preferred when you do not need the output URLs yet), OR
+   - If the **next** required step needs those URLs, call `get_generation_status` **once** with `wait=true` (and `generation_ids` for a batch) as the **only** follow-up — no parallel Write/Edit/Think while it waits.
+   - A black preview on the chat card is expected until URLs exist — not a signal to retry.
+8. **Checking status — NEVER poll in a loop**: `get_generation_status` takes `wait=true` (blocks server-side until done, ~3 min) and `generation_ids` (check MANY generations in ONE call — returns `all_done` + which are still running). One `wait=true` call replaces any polling loop. If it comes back with some still processing, call it ONCE more with `wait=true` and the remaining ids.
+9. **Share the URL** after success. Never fabricate URLs.
 
 Model types for `list_models`: `text_to_img`, `image_editing`, `text_to_video`, `img_to_video`, `draw_to_video`, `video_to_video`, `elements`, `firstlastgenerations`, `lipsync-image`, `lipsync-video`, `music_gen`, `text_to_speech`, `text_to_sound`, `stt`, `text`, `3d_text_to_model`, `3d_image_to_model`, `3d_multi_image_to_model`, `3d_world`.
 
@@ -318,7 +344,8 @@ Full tables + formulas in `references/workflows/cost-and-validation.md`. Quick r
 ## Rate Limiting & Batch Generation
 
 - `generate_image`: 30/min. All other generation tools: 10/min per type. 300/min global. `upload_media`: 300/min, no credit cost.
-- **⚠️ NEVER re-fire a generation you already called.** Aborted / timed-out calls still process server-side. Run `get_generation_status` (with `wait=true`) before retrying.
+- **⚠️ NEVER re-fire a generation you already called.** Aborted / timed-out / `submitted` calls still process server-side. Finish with `get_generation_status` (`wait=true`) — never a second `generate_*`. A black chat card or Library K-tile is not a missing job.
+- **⚠️ NEVER keep working while a generation is in flight.** After `submitted` / `_timed_out`, end the turn or block on one `wait=true` status call. Writing production.md / skills / "merge decisions" while the card spins wastes coding credits.
 - **Tracking a batch**: check ALL in-flight ids in ONE `get_generation_status` call with `generation_ids` + `wait=true`. Read `all_done` / `still_processing` from the response — do not check ids one by one, and never re-call without `wait`.
 - **Batch ≤10 items**: output ALL tool calls in one response — they run concurrently.
 - **Bulk >10 items**: real-world ceilings — `generate_image` 8–10 in-flight, image-edit 5–8, video tools 3–5, `generate_video_from_video` 3, music/speech/sound 5–8. Fire one batch → wait → fire next. Persist every `generation_id` in `.kolbo/production.md`.
@@ -387,9 +414,9 @@ A generation can fail three ways. Treat ALL as failure:
 Chat renders markdown natively. `![alt](url)` = inline image. `[label](url)` = labeled link with preview.
 
 - **Catalog-style replies** (numbered lists of characters / scenes / products): embed `![alt](url)` so each item shows inline.
-- **Conversational replies** ("4 shots ready"): keep prose short; canvas chip already shows gallery.
+- **Conversational replies** ("4 shots ready"): keep prose short; Library already shows the gallery.
 
-Avoid bare URL dumps and HTML `<table>` grids — canvas already provides a gallery.
+Avoid bare URL dumps and HTML `<table>` grids — Library already provides a gallery.
 
 **After `generate_creative_director` completes** — share results as individual URLs, one per scene. Do NOT create an HTML grid artifact.
 

package/skill/VERSION

@@ -1 +1 @@
-0.9.3
+0.9.6

package/skill/references/models/seedance.md

@@ -15,8 +15,15 @@ Load this file when the user wants a **Seedance 2 / Seedance 2.0** (ByteDance) v
 
 - **Visual DNA names are immutable anchors:** when `visual_dna_ids` is passed, every DNA MUST appear in the prompt as the exact literal `@DNA_name` (CAST + every shot it is in). Never "Zohar's", "the left man", "the man on the LEFT", a nickname, or a Visual DNA anchors paragraph without `@tags`.
 - **Rewrites never thin out or rename anchors.** "`@X anchors Odysseus`" is NOT a reference line, and `Odysseus` must never replace `@X` later. Every referenced asset keeps its exact literal tag plus a full role line on every rewrite. Re-use the exact DNA tag in every shot it participates in. A compile that dropped `@gal_suit` / `@yonatan` / `#Board` is a failed turn.
-- **First line ALWAYS declares shot structure**: total duration, shot count, aspect ratio. Example: `Total: 15s / 6 shots / 16:9`. Put it at the BOTTOM of the prompt too. For connected narrative sequences the proven phrasing is `N connected cinematic shots, 15 seconds total, 16:9, Multishot ON` — use it and keep `Multishot ON` for any multi-shot story.
-- **Then the Locked Intro** — `[GLOBAL LOOK]` / `[CAST]` / `[LOCATION]` — before any shot. A one-liner `same character throughout` is not a character lock.
+- **DURATION + SHOT STRUCTURE (HARD — same as help widget):** every text-to-video / Elements prompt MUST open AND close with total duration, shot count, and aspect. Omit only for video-edit tasks (source duration is locked). Required first lines:
+  1. `N connected cinematic shots, Xs total, AR, Multishot ON`
+  2. `Total: Xs / N shots / AR`
+  Then Locked Intro, then `SHOT N — 0:00–0:02 — Size / camera` beats whose ranges **sum exactly to Xs**. Last line repeats `Total: Xs / N shots / AR`.
+  - Example (15s / 6 shots): `6 connected cinematic shots, 15 seconds total, 16:9, Multishot ON` + `Total: 15s / 6 shots / 16:9`
+  - UGC / phone vertical: `N connected phone shots, Xs total, 9:16, Multishot ON` (never the word "cinematic").
+  - A prompt with only shot body and no Total / Multishot header is a **failed turn** — rewrite before calling `generate_*`.
+- **MCP `duration` must match the Total line.** Pass `duration: X` (whole seconds) on `generate_video` / `generate_elements` / `generate_video_from_image` equal to the `Xs` in `Total: Xs / …`. Mismatch = wrong-length clip.
+- **Then the Locked Intro** — `[GLOBAL LOOK]` / `[CAST]` / `[LOCATION]` (+ LOCATION MAP / CONTINUITY / PHYSICS for multi-shot) — before any shot. A one-liner `same character throughout` is not a character lock.
 - **Order inside each shot**: Subject → Action → Camera → Constraints → (Audio/SFX if relevant). Do NOT restack GLOBAL LOOK style inside the shot.
 - **Prompt length**: simple single-idea pieces ~120–280 words. Locked-intro cinematic typically 400–900 words. Shorter than ~120 words = random output. The 8000-char cap below always wins.
 - **Shot count is user-directed.** If the user asks for N shots, deliver exactly N in one prompt unless they ask to split.
@@ -32,11 +39,11 @@ Load this file when the user wants a **Seedance 2 / Seedance 2.0** (ByteDance) v
 
 ## Locked Intro (DEFAULT for any multi-shot cinematic — including Elements)
 
-After the Total line, every multi-shot prompt — and any piece with recurring people or a recurring place — opens with three locked blocks. Skip only for: true single-shot POV/orb, 3×3 grid-panel mode, or video-edit tasks.
+After the Total lines, every multi-shot prompt — and any piece with recurring people or a recurring place — opens with the locked blocks. Skip only for: true single-shot POV/orb, 3×3 grid-panel mode, or video-edit tasks.
 
 ```
-Total: Xs / N shots / AR
 N connected cinematic shots, Xs total, AR, Multishot ON
+Total: Xs / N shots / AR
 
 [GLOBAL LOOK – LOCKED, APPLIES TO EVERY SHOT]
 <body>, <lens family>, <film stock>, <aspect> spherical, <stop>. <DoF, grain, grade as law>. <movement grammar>. <performance + audio law>.
@@ -48,14 +55,37 @@ PROP: recurring object.
 [LOCATION]
 Place in materials + light + color field. Blocking. Background LIFE.
 
+[LOCATION MAP]
+Named seats / sides in SCREEN language (screen-left armchair, center couch, door camera-left).
+
+[CONTINUITY – LOCKED ACROSS EVERY CUT]
+Axis / camera side of the line. Screen direction. Eyelines. Floor props stay. Which hand holds what. No teleport.
+
+[PHYSICS]
+Weight into furniture, props resting, cloth/hair settle, no float.
+
 SHOT 1 — 0:00–0:02 — Medium / camera position
 (physical verbs, timed acting, quoted dialogue)
-…
+SHOT 2 — 0:02–0:05 — …
+… (ranges MUST sum to Xs)
 Total: Xs / N shots / AR
+POSITIVE LOCKS: <2–4 sentences restating positions / mouth / optical signature>
 ```
 
 When a Visual DNA exists, its exact `@DNA_name` IS the cast name — never place a nickname before it or substitute one later. For plain image refs use `@ImageN`.
 
+## OUTPUT CONTRACT (WINS — same as help widget)
+
+ONE fenced prompt. Required shape or the turn failed:
+1. `N connected cinematic shots, Xs total, AR, Multishot ON`
+2. `Total: Xs / N shots / AR`
+3. GLOBAL LOOK → CAST → LOCATION → LOCATION MAP → CONTINUITY → PHYSICS (dense, before any shot)
+4. `SHOT 1 — 0:00–0:02 — …` through SHOT N; timecodes sum to Xs; continuity bridge after SHOT 1
+5. Closing `Total: Xs / N shots / AR` + short POSITIVE LOCKS
+6. Tool call `duration` = Xs
+
+FORBIDDEN: omitting Total / Multishot; "same character throughout" as the only lock; one fence per shot; `[0s]`/`[3s]` stubs; splitting a ≤15s story into multiple generations unless the user asks.
+
 ## The 5 Formats
 
 ### 1. Transformations (highest-performing format)

package/skill/references/models/seedance25.md

@@ -23,21 +23,45 @@ Load this file when the user wants a **Seedance 2.5** video (they said "2.5" / "
 - **Up to 50 reference medias / Visual DNA mentions** (`@Name`, `@ImageN`, `#Moodboard`). Every referenced asset must be tagged in the prompt text. A rewrite that drops or renames a tag ( `@doron_fauda_1` → `DORON` / `the hero` ) is a failed turn — put the exact tag back.
 - **Multimodal refs:** images + video clips + audio can all anchor one generation.
 
-## Locked Intro (DEFAULT — same shape as Seedance 2)
+## Universal Rules (HARD — same as help widget OUTPUT CONTRACT)
+
+- **First lines ALWAYS declare shot structure** (text-to-video / Elements / reference gen — NOT video-edit):
+  1. `N connected cinematic shots, Xs total, AR, Multishot ON`
+  2. `Total: Xs / N shots / AR`
+  Example: `12 connected cinematic shots, 30 seconds total, 16:9, Multishot ON` + `Total: 30s / 12 shots / 16:9`
+  UGC phone: `N connected phone shots, Xs total, 9:16, Multishot ON` — never the word "cinematic"; restate `9:16 vertical phone frame` in every shot.
+- **Last line repeats** `Total: Xs / N shots / AR` + short POSITIVE LOCKS.
+- **Shot timecodes MUST sum to Xs.** `SHOT 1 — 0:00–0:02` … through SHOT N ending at Xs. Never `[0s]` / `[3s]` stubs.
+- **MCP `duration` = Xs** on the generate call. Mismatch is a failed turn.
+- Duration range **4–30s**; shot count **≤30** in one generation. Do not split a ≤30s story into multiple 10s clips unless the user asks.
+- Omit Total / Multishot / shot-count headers only for **video editing** (source duration locked) — use Edit Goal blocks instead.
 
-After the Total line, every multi-shot cinematic opens with:
+## Locked Intro (DEFAULT — same shape as Seedance 2)
 
 ```
+N connected cinematic shots, Xs total, AR, Multishot ON
+Total: Xs / N shots / AR
+
 [GLOBAL LOOK – LOCKED, APPLIES TO EVERY SHOT]
 [CAST – IDENTICAL IN EVERY SHOT]
 [LOCATION]
+[LOCATION MAP]
+[CONTINUITY – LOCKED ACROSS EVERY CUT]
+[PHYSICS]
+
+SHOT 1 — 0:00–0:02 — Medium / camera position
+…
+Total: Xs / N shots / AR
 ```
 
-then timecoded `SHOT N — 0:00–0:02 — Medium / camera position` beats. Full skeleton, acting rules, and optical craft: `models/seedance.md`.
+Full acting / continuity craft: `models/seedance.md`. Do not skip the Total lines or the three look/cast/location blocks. Do not restack GLOBAL LOOK inside shots.
+
+2.5 is where this format earns its keep: 15 shots timed to 30s, ~5k characters, one locked look so every cut matches camera / grade / cast.
 
-2.5 is where this format earns its keep: 15 shots timed to 30s, ~5k characters, one locked look so every cut matches camera / grade / cast. Do not skip the three blocks. Do not restack GLOBAL LOOK inside shots.
+## OUTPUT CONTRACT (WINS — mirror of help widget)
 
-UGC / phone vertical (full craft: `workflows/ugc-smartphone.md`): NEVER write "cinematic". GLOBAL LOOK is phone-native. Use `N connected phone shots, Xs total, 9:16, Multishot ON` and restate `9:16 vertical phone frame` inside every shot.
+ONE fenced prompt. Missing Total / Multishot / summing timecodes / matching `duration` = failed skill turn.
+FORBIDDEN: "same character throughout" as the only lock; one fence per shot; claiming you followed the skill while omitting GLOBAL LOOK / CAST / LOCATION / Multishot ON.
 
 ## Prompt length
 

package/skill/references/workflows/production-log.md

@@ -4,7 +4,9 @@ Load this file when starting a multi-step production, or before any continuation
 
 ## Why It Exists
 
-Every URL, id, and brief produced by a Kolbo MCP tool MUST be recorded in `.kolbo/production.md` in the user's workspace. This file — not chat history — is your source of truth for prior artifacts: URLs scattered across `tool_result` blobs are unreliable to re-scan and disappear entirely on context compaction. If the user named a model, write that name into `## 🎯 Now` and keep using that family on every follow-up — compaction is not permission to cheapest-swap.
+Every URL, id, and brief produced by a Kolbo MCP tool MUST be recorded in `.kolbo/production.md` in the user's workspace. This file is **your** (agent) source of truth for prior artifacts across turns — not chat history (unreliable / compacted) and not a substitute for the user's **Library** gallery. URLs scattered across `tool_result` blobs are unreliable to re-scan and disappear entirely on context compaction. If the user named a model, write that name into `## 🎯 Now` and keep using that family on every follow-up — compaction is not permission to cheapest-swap.
+
+**User vs agent SoT:** finished media for the human → **Library → This session**. Job state while in flight → `get_generation_status`. Your memory → this file. Chat cards are progress UI only.
 
 ## When to READ it
 

package/skill/references/workflows/troubleshooting.md

@@ -26,6 +26,10 @@ If Kolbo tools timeout or aren't listed, the MCP server may not be wired. Tell t
 ```
 This re-wires the MCP configuration automatically. Then restart the session.
 
+## Black / empty chat card while "Generating"
+
+**Not a bug and not a failure.** The chat generation card's preview stays dark until the job has media. Library shows a K/logo placeholder tile for the same in-flight job. Do **not** re-fire `generate_*`, do **not** `list_media` to "find" it. Wait, or call `get_generation_status` once with `wait=true`. When complete, the result appears in Library (This session) — that is the user-facing source of truth.
+
 ## "Rate limited" (429 errors)
 
 Wait 60s for the window to reset, retry only the failed calls. For batch image work prefer `generate_creative_director` over multiple `generate_image` calls. Full rate-limit details + retry sequence: see SKILL.md "Rate Limiting & Batch Generation".
@@ -47,6 +51,8 @@ prompt loses.
 
 `get_generation_status` supports `wait=true` (blocks server-side until the generation reaches a final state, up to ~3 min) and `generation_ids` (many ids in one call → returns `all_done`, `still_processing`, and per-generation results). **Never call it repeatedly in a loop** — one `wait=true` call replaces the loop. If some generations are still running after the wait window, call it ONCE more with `wait=true` and only the `still_processing` ids.
 
+**Credit guard:** after a generate tool returns `submitted` / `_timed_out`, do not keep thinking or editing files while the card spins — that burns coding credits. End the turn, or make **one** `wait=true` status call if you need the URLs next.
+
 ## Failure envelope from `get_generation_status`
 
 When a generation fails, `get_generation_status` returns a structured `failure` field alongside `error`:

package/skill/references/workflows/visual-dna.md

@@ -63,11 +63,12 @@ When the user says "use the model אסתר" but you've only created a DNA for "
 
 ## ⚠️ Don't re-fetch / re-list your own outputs (CRITICAL)
 
-After a generation tool returns its URLs, those URLs are **already** in the canvas (the desktop app's gallery panel) and in `.kolbo/production.md`. Do **NOT** call `list_media`, `get_media`, `get_media_stats`, `list_visual_dnas`, or `chat_send_message` with `media_urls` on those URLs just to "verify" or "fetch thumbnails of the results":
+After a generation tool returns its URLs, those URLs are **already** in **Library** (right panel — This session) and in `.kolbo/production.md`. Do **NOT** call `list_media`, `get_media`, `get_media_stats`, `list_visual_dnas`, or `chat_send_message` with `media_urls` on those URLs just to "verify" or "fetch thumbnails of the results":
 
 - It burns credits and time for zero new information.
-- Every such tool call streams partial output into the session, which forces the desktop canvas to re-evaluate (visible flicker on the gallery tiles).
+- Every such tool call streams partial output into the session, which forces Library to re-evaluate (visible flicker on the gallery tiles).
 - The thumbnails returned by `list_media` / `get_media` are the SAME asset you just generated.
+- A black chat generation card while `Generating` is normal — do not treat it as missing output.
 
 **Only call list/get media tools when:**
 - The user explicitly asks ("what do I have in my library?", "show me my old DNAs").