@starreel/mcp 0.1.202 → 0.1.207

package/SKILL.md

@@ -543,6 +543,12 @@ content that will be rejected.
    `review_frames` flags the two actionable states as `seam_unchained` / `seam_broken`
    (warnings — they do not block `generate_videos`, but this is the cheapest point to fix
    them: the video is generated from the first frame).
+   Joined seams can still jump when the same subject sits on opposite sides of the frame,
+   moves in opposite directions, or the shot size leaps several steps. Optional, before videos:
+   `audit_seam_directions` (`dry_run` first — quote, billed by text tokens; advisory,
+   never blocks) compares each previous last frame with the next first frame; read the
+   results with `get_seam_directions` (also summarised in `review_frames` as
+   `seam_direction_advisory`) and let the customer pick which seams to fix.
    **Image model**: images use a drama-level model (default **ChatGPT Image 2.5
    Flare** = `gpt-image-2.5-flare`), set via `create_drama` /
    `update_project_settings` field `image_model` for one consistent look across
@@ -1566,7 +1572,12 @@ to close") tells the vendor to fit that entire sequence into each 3-second shot.
   `applicable=false`) → `trim_shot`; ④ `audit_seams(episode_id)` for continuity
   between adjacent shots — the default `dry_run` is free, running it is billed by
   text tokens, so only pass `dry_run:false` + `confirm_usage_billing:true` after the
-  customer accepts; ⑤ `compose_episode`. When the cut shows a problem, come back to
+  customer accepts; ⑤ `preview_seams` → `get_seam_previews` (free: one 2-second
+  clip per seam — 1 s before the out point + 1 s after the in point, current trims
+  and transitions applied through the same build/render path as the final cut —
+  plus an edge-frame comparison image and the `audit_seams` verdict; re-run it on
+  the seam you changed, since crossfades / inserts / overlays used as patches often
+  create new problems); ⑥ `compose_episode`. When the cut shows a problem, come back to
   these tools to find the shot instead of re-exporting. Advisory only, not a gate;
   trims and seam audits don't invalidate the `review_videos` token.
 

package/dist/i18n/tools.en.json

@@ -42,7 +42,7 @@
   "get_health_report": "(★Recommended · free diagnosis) Read storyboards and output a health report: overlong duration / insufficient motif coverage / problematic shots. Read-only, free. Check before image generation; identify issues, fix first, and avoid discovering them only after the film is produced.",
   "review_script": "【Hard Gate ① · Free】Review the AI rewritten script: dialogue line length, completeness of emotional turns, opening hook, final-scene cliffhanger. ★Before extract_assets and generate_storyboards, this tool must run first—character profiles and storyboards are derived from the rewritten script; issues in the script will be amplified layer by layer into character sheets / image generation / video generation, and discovering them at final cut means redoing the whole episode. Tell the client each item in findings one by one, fix by action (use edit_rewritten_script for script edits), then re-review and proceed with the review_token.\n★【Agent manual QC · Free】The returned agent_qc contains this-layer checklist and the episode materials to inspect (materials, each with a ref; images/videos include links). The platform only judges “exists / present / rejected”; “looks alike / correct / good” must be checked by you: download and open images, sample at least beginning/middle/end frames for videos, read text through with tools. Answer each checklist item (ok / issue / na; for issue, specify which item and what problem), list every inspected ref in inspected, and call submit_qc_report to submit; relay the QC conclusion to the client verbatim. If agent_qc.required=true and no report is submitted, this review_token cannot enter the next step (400 agent_qc_required); a problematic report blocks by default just like a platform error.\n★【Script evaluation and suggestions】materials contains the client original script (script:original) and the rewritten script (script): first evaluate the client’s script itself (mainline, motivation, conflict, pacing, plot holes, filmability), then check the rewritten script; for each issue, provide concrete fixes in submit_qc_report suggestions (if wording can be directly changed, provide before/after). After submission, tell the client the evaluation and suggestions item by item and let the client choose: adopt some / execute all directly / continue without changes (which path to take follows the execution mode: professional mode / unconfirmed plan / this stage controlled by client → tell the client and proceed only after client approval; do not decide for the client; if this stage is autopiloted → do not ask the client, execute according to get_production_plan autopilot.default_decisions, and the platform records it in get_autopilot_log); autopiloted stages by default execute only priority=must items that do not change the client’s original dialogue; all others go into the delivery report. ★[Customer acceptance items] review_frames / review_videos append the customer's registered specific requirements (add_acceptance_criteria) to the checklist (ids start with req:) together with acceptance_criteria: the platform's generic review does not know these requirements, so passing it does not mean they are met. Check each one with your own eyes, answer it in submit_qc_report, tell the customer the result, and let the customer confirm via confirm_acceptance_criterion.",
   "review_storyboards": "【Hard gate ② · free】Review storyboards: forbidden terms (will be rejected by vendors and waste credits), shot duration distribution, repeated adjacent composition, character blocking drift in the same scene, emotional curve peaks/valleys, key-shot markers. ★Must run this tool before generate_frames—storyboard issues become a whole episode of wasted images once generated and cannot be fixed shot by shot. Fix per findings.action using update_shot/split_shot, then review again. ★A finding with code=forbidden_term includes `terms` (specific matched terms, e.g. \"background music\", \"strong light\") and `shots` (shot numbers); use those two to update_shot and remove them, no need to guess word by word. ★Forbidden terms are judged with **negative semantics**: writing \"no background music\" or \"do not add music\" is not a violation (it is obeying the constraint), so no edit is needed. ★\"Action overload\" in warnings (action_overload, advisory only, non-blocking): one shot contains more independent actions than its duration can support; before video generation, use split_shot to split it or delete actions—slow motion/dissolves cannot rescue it after final cut. Ignore if multiple people each do one thing or it is a naturally continuous action chain.\n★【Agent hands-on QC · free】Returned agent_qc contains this layer's checklist and materials to inspect for this episode (materials, each with a ref; images/videos include links). The platform only checks \"exists / present / rejected\"; \"looks like / is correct / is good\" must be judged by you: download and open images, sample at least beginning/middle/end frames for videos, read text fully with tools. Answer checklist items one by one (ok / issue / na; for issue, state which item has what problem), list every inspected ref in inspected, and call submit_qc_report; tell the customer the QC conclusion verbatim. When agent_qc.required=true, without a submitted report this review_token cannot proceed to the next step (400 agent_qc_required); issues in the report block by default just like platform errors. ★[Customer acceptance items] review_frames / review_videos append the customer's registered specific requirements (add_acceptance_criteria) to the checklist (ids start with req:) together with acceptance_criteria: the platform's generic review does not know these requirements, so passing it does not mean they are met. Check each one with your own eyes, answer it in submit_qc_report, tell the customer the result, and let the customer confirm via confirm_acceptance_criterion.",
-  "review_frames": "【Hard gate ③ · free】Review the shot image layer: character identity-anchor coverage (characters without character sheets will drift in shots), image-generation failure rate, orphan character variants, scene images polluted by people. ★Must run this tool before generate_videos—video generation is the most expensive step in the whole chain, and generating a whole episode of video from drifting first frames is the most typical wasted-film failure. Fix per findings.action (mostly generate_character_portraits / generate_shot_frame single-shot regeneration), then review again. ★Also reports **inter-shot seams** (warning, non-blocking): code=seam_unchained (marked continuous but never did first/last-frame chaining, or initiated chained regeneration never landed / first frame was regenerated again after chaining) / seam_broken (chained but not connected, or previous shot's last frame was regenerated after chaining); shots is the shot whose \"seam with previous shot\" has the issue. Cheapest to fix before video generation—videos are generated from first frames; if a first frame does not match the previous shot's last frame, the final cut has a jump cut. See action for fixes (whole episode chain_frames dry_run first; single seam chain_shot_from_prev / chain_shot_from).\n★【Agent hands-on QC · free】Returned agent_qc contains this layer's checklist and materials to inspect for this episode (materials, each with a ref; images/videos include links). The platform only checks \"exists / present / rejected\"; \"looks like / is correct / is good\" must be judged by you: download and open images, sample at least beginning/middle/end frames for videos, read text fully with tools. Answer checklist items one by one (ok / issue / na; for issue, state which item has what problem), list every inspected ref in inspected, and call submit_qc_report; tell the customer the QC conclusion verbatim. When agent_qc.required=true, without a submitted report this review_token cannot proceed to the next step (400 agent_qc_required); issues in the report block by default just like platform errors. ★[Customer acceptance items] review_frames / review_videos append the customer's registered specific requirements (add_acceptance_criteria) to the checklist (ids start with req:) together with acceptance_criteria: the platform's generic review does not know these requirements, so passing it does not mean they are met. Check each one with your own eyes, answer it in submit_qc_report, tell the customer the result, and let the customer confirm via confirm_acceptance_criterion.",
+  "review_frames": "【Hard gate ③ · free】Review the shot image layer: character identity-anchor coverage (characters without character sheets will drift in shots), image-generation failure rate, orphan character variants, scene images polluted by people. ★Must run this tool before generate_videos—video generation is the most expensive step in the whole chain, and generating a whole episode of video from drifting first frames is the most typical wasted-film failure. Fix per findings.action (mostly generate_character_portraits / generate_shot_frame single-shot regeneration), then review again. ★Also reports **inter-shot seams** (warning, non-blocking): code=seam_unchained (marked continuous but never did first/last-frame chaining, or initiated chained regeneration never landed / first frame was regenerated again after chaining) / seam_broken (chained but not connected, or previous shot's last frame was regenerated after chaining); shots is the shot whose \"seam with previous shot\" has the issue. Cheapest to fix before video generation—videos are generated from first frames; if a first frame does not match the previous shot's last frame, the final cut has a jump cut. See action for fixes (whole episode chain_frames dry_run first; single seam chain_shot_from_prev / chain_shot_from).\n★【Agent hands-on QC · free】Returned agent_qc contains this layer's checklist and materials to inspect for this episode (materials, each with a ref; images/videos include links). The platform only checks \"exists / present / rejected\"; \"looks like / is correct / is good\" must be judged by you: download and open images, sample at least beginning/middle/end frames for videos, read text fully with tools. Answer checklist items one by one (ok / issue / na; for issue, state which item has what problem), list every inspected ref in inspected, and call submit_qc_report; tell the customer the QC conclusion verbatim. When agent_qc.required=true, without a submitted report this review_token cannot proceed to the next step (400 agent_qc_required); issues in the report block by default just like platform errors. ★[Customer acceptance items] review_frames / review_videos append the customer's registered specific requirements (add_acceptance_criteria) to the checklist (ids start with req:) together with acceptance_criteria: the platform's generic review does not know these requirements, so passing it does not mean they are met. Check each one with your own eyes, answer it in submit_qc_report, tell the customer the result, and let the customer confirm via confirm_acceptance_criterion. ★When there are adjacent shots, the response also carries seam_direction_advisory (advisory, does not affect review_token): existing results of the adjacent-shot direction check (subject side jump/reversed motion/shot-size jump); seams not yet observed need audit_seam_directions dry_run for a quote first, and run only after the client agrees.",
   "review_assets": "【Asset-layer hard gate · free】Review character appearance images, scene images, and prop images used **on screen** in this episode—coverage and quality: on-screen character missing character sheet / missing reference image / still generating / generation failed / reference image rejected by consistency gate (hint includes rejection reason); scene missing empty-scene base plate; prop referenced by storyboard missing prop image / rejected; prop image conflicts with this shot's era/form; missing color script (warning). ★Call once after producing character sheets, reference images, scene images, and prop images; must review before generate_frames / generate_shot_frame—pass the returned review_token as **asset_review_token**, together with the storyboard-layer review_token (both are required). Only checks the assets themselves: generating shot images later will not invalidate it; changing character sheets / scene images / prop images will invalidate it, just review again (free, seconds). Explain findings to the customer one by one (code=issue type, names=which character/scene/prop, shots=affected shot numbers, action=which tool to call to fix).\n★【Agent hands-on QC · free】Returned agent_qc contains this layer's checklist and materials to inspect for this episode (materials, each with a ref; images/videos include links). The platform only checks \"exists / present / rejected\"; \"looks like / is correct / is good\" must be judged by you: download and open images, sample at least beginning/middle/end frames for videos, read text fully with tools. Answer checklist items one by one (ok / issue / na; for issue, state which item has what problem), list every inspected ref in inspected, and call submit_qc_report; tell the customer the QC conclusion verbatim. When agent_qc.required=true, without a submitted report this review_token cannot proceed to the next step (400 agent_qc_required); issues in the report block by default just like platform errors. ★[Customer acceptance items] review_frames / review_videos append the customer's registered specific requirements (add_acceptance_criteria) to the checklist (ids start with req:) together with acceptance_criteria: the platform's generic review does not know these requirements, so passing it does not mean they are met. Check each one with your own eyes, answer it in submit_qc_report, tell the customer the result, and let the customer confirm via confirm_acceptance_criterion.",
   "review_videos": "【Video and dubbing-layer hard gate · free】Review this episode's videos and dubbing—coverage and quality: missing video / still generating / generation failed / vendor rejected; first frame changed but video was generated from an old frame (video_stale); suspected hard cut at clip end, unexpected human voice in no-dialogue shots (warning); dubbed drama: dialogue shot missing dubbing, speaking character has no voice, missing narrator role; original-audio drama: shots not attached to current voice line at export time, characters without locked voice lines; missing music (warning). ★Call once after video, dubbing (generate_tts), and music are produced; must review before compose_episode, passing the returned review_token. Finer checks (requiring decoding picture/audio tracks) are available via scan_intra_shot_cuts / scan_dialogue_coverage / audit_silent_shot_audio; after assembling the final cut, run review_final_cut.\n★★【Pre-compose checks · after review_videos passes, before compose_episode】Don't hunt for problems by repeatedly exporting the whole cut and trying transitions by hand — per-shot and seam problems have dedicated tools; run them in order before stitching: ① portraits / turnarounds / scene images / shot frames were changed in this episode → first get_stale_portrait_frames(episode_id, free) to see which shots' in-use frames are still based on old assets; for shots where it is unclear which version to use, get_asset_versions(storyboard_id, free) shows each shot's versions and dependencies (unknown means insufficient evidence, not stale; regenerating is paid, so give the list to the customer and let them decide); ② scan_intra_shot_cuts(episode_id, free) finds shots where the vendor hard-cut inside a single shot; ③ per shot, recommend_trim_window(storyboard_id, free) shows a frozen tail and the effective action window (shots inside a scene group return applicable=false — skip them); apply a recommendation with trim_shot (free); ④ audit_seams(episode_id) checks editing continuity at seams between adjacent shots: by default dry_run only lists what would be audited (free); actually running it is billed by real text-token usage — tell the customer, and only after they explicitly accept pass dry_run:false + confirm_usage_billing:true; read the result from seam_review in get_storyboards; ⑤ then compose_episode. If the final cut shows jump cuts / dragging tails / seams that don't match, go back to these tools to locate the shots and fix only those — don't keep re-exporting the whole cut by trial and error. These checks are advisory, not gates; trimming and seam audits don't invalidate the review_videos token. The response's pre_compose_checks carries the same list in structured form (tool/scope/when/cost per item).\n★【Agent hands-on QC · free】Returned agent_qc contains this layer's checklist and materials to inspect for this episode (materials, each with a ref; images/videos include links). The platform only checks \"exists / present / rejected\"; \"looks like / is correct / is good\" must be judged by you: download and open images, sample at least beginning/middle/end frames for videos, read text fully with tools. Answer checklist items one by one (ok / issue / na; for issue, state which item has what problem), list every inspected ref in inspected, and call submit_qc_report; tell the customer the QC conclusion verbatim. When agent_qc.required=true, without a submitted report this review_token cannot proceed to the next step (400 agent_qc_required); issues in the report block by default just like platform errors. ★If the response includes post_production_advisory = narrative-required effects that the script marks as post-production are still unhandled (the platform will not composite them): tell the client verbatim and use get_post_production_checklist to see the list. ★[Customer acceptance items] review_frames / review_videos append the customer's registered specific requirements (add_acceptance_criteria) to the checklist (ids start with req:) together with acceptance_criteria: the platform's generic review does not know these requirements, so passing it does not mean they are met. Check each one with your own eyes, answer it in submit_qc_report, tell the customer the result, and let the customer confirm via confirm_acceptance_criterion.",
   "submit_qc_report": "Submit the QC report made by you (agent) after personally inspecting materials. Free. First call the corresponding review_* layer (script / storyboards / assets / frames / videos), open each returned agent_qc material in materials, answer every checklist item, then call this tool. ★The platform only verifies the report is **complete**, not whether your conclusions are correct: every checklist id must be answered (ok / issue / na; issue must include note explaining which item has what problem); every ref in materials must be listed in inspected (omit one and it is rejected with the missing refs named); if there are issues, set verdict=issues and list them in issues; reporting pass when issues exist will be rejected. ★Do not go through the motions: listing something in inspected without opening it means you signed off for the customer—wasted output will still be charged. ★When verdict=issues, this token cannot proceed to the next step by default: explain the problems to the customer, fix, then review + QC again; only if the customer is clearly informed and insists on proceeding as-is should the next step include acknowledge_review:true. ★suggestions (change suggestions): required at script layer when agent_qc.suggestions_required=true and issues were reported; optional for other layers. Each item includes problem + proposal; if text can be directly changed, also provide before/after; the response assigns each suggestion an id (s1…). Explain suggestions to the customer; the customer chooses accept some / execute all directly / proceed without changes (which route; autopilot = only execute priority=must suggestions that do not change the customer's original lines per execution mode: professional mode / unconfirmed plan / this step customer-controlled → explain to customer and only proceed after approval; do not decide for the customer. This step autopilot → do not ask customer; follow get_production_plan autopilot.default_decisions, recorded by the platform in get_autopilot_log). If content changes after the review, the report will be rejected; review again and QC against the new agent_qc.",
@@ -203,6 +203,8 @@
   "get_motion_templates": "Read existing motion templates for this drama (camera/action presets). Generated by generate_motion_templates; read with this tool. Free.",
   "record_product_text_review": "Free: record the user's manual verification result for current original product text. Call only after the user explicitly opens the file, checks it word by word, and confirms the result; do not substitute model judgment as manual verification. From get_storyboards product_text, take the current contract_hash and the frame position, file, generation_id in reviews; for uploaded assets generation_id is null, and media_version from the same response must be passed. Any change invalidates old reviews. Does not regenerate, does not switch the adopted version, and does not represent client acceptance of the entire film.",
   "audit_seams": "Audit edit continuity of current bilateral frames; checks only, does not regenerate or replace assets. Default dry_run=true returns the scope to audit and is free. Insert details only check object identity and state, not composition copying. Existing current valid conclusions are not re-audited. Execution is billed by actual text token usage; estimated_points=null means the amount is not quoted, not free. First show the plan and billing method; only pass dry_run=false and confirm_usage_billing=true after explicit client acceptance. After execution, use get_storyboards seam_review to inspect actual results; attempted does not mean passed.",
+  "preview_seams": "★Run this first when checking transition/seam problems instead of repeatedly exporting the whole episode. Free, zero charge (pure ffmpeg; no vendor calls and no on-the-fly TTS synthesis). Renders one short clip for every seam between adjacent shots in the episode: the last 1 second before the outgoing shot's out point + the first 1 second after the incoming shot's in point (for transitions longer than 0.5 s each side takes 2× the transition), applying the current trim windows and transition settings with the same timeline-building and rendering logic as the final compose (only the canvas is scaled down; no BGM and no subtitles). Also returns an edge-frame comparison image for both sides, plus the existing audit_seams conclusion. Async: this tool only starts the job; poll get_seam_previews until status=done. seams is optional: re-render only the listed seam indexes (use it to re-check after changing a trim/transition). ★Decide the fix after watching: if the action does not connect, run recommend_trim_window → trim_shot; if the transition is wrong, change the transition. Patch-up tricks such as crossfade ghosting, zoom-in inserts or occluding overlays often introduce new problems themselves — after changing anything, run this tool again on that seam.",
+  "get_seam_previews": "Check progress and results of preview_seams. Free. While status=running, read progress.done/total; when status=done, each entry of result.seams[] gives: from_shot_id/to_shot_id, transition (effective transition), left/right (in/out points on the source video, src_in_ms/src_out_ms, trim already applied), preview_url (the short clip), compare_image_url (left = last frame of the outgoing shot before the transition starts, right = first frame of the incoming shot after the transition ends), audit (audit_seams conclusion; not_enabled = not enabled for this drama). A non-empty result.synth_skipped_shot_ids means those shots have no synthesized voice-over yet and the preview treats them as silent. A single-shot episode returns seam_count=0.",
   "chain_frames": "Whole-episode first/last-frame relay chain: make each shot's first frame inherit the previous shot's last frame so inter-shot visuals are continuous (smoother than generating each shot independently). ★When to call: after first frames are done and any last frames required by tail_frame_plan are also filled, before review_frames / generate_videos. The platform only auto-runs this once when batch frame generation on the official site finishes; episodes generated shot by shot (generate_frames / generate_shot_frame) often have never been chained — get_storyboards seam_state=unchained means this kind of seam.\n★First use dry_run:true (free, does not write DB or generate images): returns planned_copy / planned_reframe / estimated_points / needs_last_frame. copy = directly replace this shot's first frame with the previous shot's last frame (free, but this shot's shot size becomes the same as the previous shot); reframe = use the previous shot's last frame as an anchor to regenerate this shot's first frame according to this shot's visual description (one image per seam, preserves shot size). Tell the client the plan and estimated_points; after confirmation, call again **without dry_run** to execute (postpaid by usage).\n★The platform decides which seams to chain: intentional cuts (scene/time jump/costume change/insert shot), shots with existing video, and already-chained seams are skipped — “already chained” = the first frame is the previous shot's last frame, or reframe is chained to the previous shot's **current** last frame, so repeated execution will not charge again. If the previous shot's last frame is later regenerated, that seam will reappear in the plan; that seam is indeed broken. To fill individual seams, use chain_shot_from_prev / chain_shot_from. Shots whose first frame is changed by execution and already have video will be marked pending regeneration. ★Execution only dispatches reframe and does not wait for image generation: use get_jobs to view first_frame generation rows for these shots; wait until all pending/processing are finished (for failed, check error_msg; for a single seam use chain_shot_from to reconnect; while the old first frame still exists, get_storyboards frame_status remains ready and failure is not visible), then use get_storyboards to verify seam_state and review_frames — auditing too early will audit the old first frame, and the token will be invalidated later.",
   "chain_shot_from_prev": "(Free) Directly set the previous shot's last frame as this shot's first frame: visuals connect 100%, zero cost, no image generation. ★Use when: the two shots are a continuation from the same camera position and same shot size (seam_state=unchained/broken and this shot should already share the previous shot's composition). ★Do not use for seams with shot-size changes (wide → close-up, etc.): it will overwrite this shot's shot-size design, and later image generation may be judged “inconsistent with design” — for such seams use chain_shot_from with mode=reframe. If this shot already has video, it will be marked pending regeneration. If this shot's first frame is already client-locked (first_frame_pinned), the call is rejected; pass force:true only to overwrite it (any execution mode requires explicit client consent, including managed mode).",
   "quote_chain_shot_from": "(Free quote) chain_shot_from with mode=reframe deducts **one image** (regenerate this shot's first frame anchored on the source frame); quote before execution (quote confirmation follows execution mode: professional mode / unconfirmed plan / this step is customer-controlled → explain to the customer and proceed only after customer approval; do not decide for them; this step is autopiloted → do not ask the customer, execute per get_production_plan autopilot.default_decisions, and the platform records it in get_autopilot_log). Returns quote_id / estimated_points; quote_id is one-time and valid only for this shot. mode=copy needs no quote.",
@@ -248,5 +250,7 @@
   "add_acceptance_criteria": "Register customer acceptance items (free): when the customer states a **specific requirement** for a shot or the whole episode (identity, wardrobe, prop color, lip sync, visual artifacts, etc.), record it in the customer's own words. review_frames / review_videos will then append it to agent_qc.checklist (ids start with req:) for you to check item by item, and the result is recorded separately. ★One requirement per item; for a shot use shot_number (current shot number) or storyboard_id, omit both for the whole episode. Registering invalidates review_tokens already issued for that stage — re-review. ★Only register what the customer actually said; never invent requirements.",
   "update_acceptance_criterion": "Edit a customer acceptance item (free). Changing the text / category / shot / stages resets all three states of that item (the requirement changed, old conclusions no longer count); re-run the review to check it. To delete, use delete_acceptance_criterion. item_id comes from get_acceptance_criteria. (Editing customer acceptance items requires explicit client consent in every execution mode, including autopilot.)",
   "confirm_acceptance_criterion": "Record the **customer's own** confirmation of an acceptance item (free): accepted / rejected / pending (undo). Only the client state is written; the platform auto review and your QC conclusion are untouched. ★Call it only after the customer has explicitly stated their decision, with confirm_client_statement:true; you must never confirm on the customer's behalf, autopilot included.",
-  "delete_acceptance_criterion": "Delete a customer acceptance item (free; its three states go with it). item_id comes from get_acceptance_criteria. (Deleting customer acceptance items requires explicit client consent in every execution mode, including autopilot.)"
+  "delete_acceptance_criterion": "Delete a customer acceptance item (free; its three states go with it). item_id comes from get_acceptance_criteria. (Deleting customer acceptance items requires explicit client consent in every execution mode, including autopilot.)",
+  "audit_seam_directions": "Pre-video seam direction check (advisory, never blocks any step): for every pair of adjacent shots, compares \"previous shot's last frame (or first frame if none) ↔ this shot's first frame\" for the same subject jumping left/right sides of the frame (a reversed eyeline is noted with it), reversed motion direction, and shot-size jumps (same subject, extreme long ↔ close-up). Eyeline alone and key-light direction are observed but not reported: production replay showed too many false positives on those (better to miss than to nag). Shots that look fine alone but jump when cut together usually fail on these. Complements audit_seams, which checks identity/wardrobe/props/object state but not direction or position. ★When: after first frames (and needed last frames) are done and chain_frames has run, before review_frames / generate_videos. Scene changes, declared jump cuts, insert shots and title/black cards are skipped automatically. ★dry_run first (default, free): returns the seams to observe plus estimated_points (upper bound) and typical_points (usual cost); tell the client both — billed by actual text tokens. After the client agrees, pass dry_run=false + confirm_usage_billing=true. Execution is asynchronous and returns immediately; read results with get_seam_directions a minute or two later. Seams already observed with unchanged frames are not billed again.",
+  "get_seam_directions": "(Free) Read audit_seam_directions results: each issue gives the seam shot numbers, the problem (subject jumps sides, reversed motion, shot-size jump) and fixes (chain_shot_from mode=reframe to regenerate this shot's first frame anchored on the previous last frame / update_shot to state facing then generate_shot_frame / align_prev_shot when the previous shot already has video / split_shot to insert an intermediate shot size). Results are advisory: explain them to the client and let the client pick which to fix; intentional reverse shots, turns or impact cuts can be ignored. not_audited>0 = seams not observed yet or frames changed since; running=true = still running. review_frames' seam_direction_advisory is a summary of the same results. This tool only looks at pre-video still frames; after videos are generated, check seams with preview_seams (free short-clip previews)."
 }