jianying-draft-recover

JianYing Recover

Recover failed tasks, transaction snapshots, and external operation state. First determine which side effects have already occurred, then choose the recovery action.

When to use

• The user explicitly requests the Jianying capability corresponding to this skill's title and accepts processing through the unified Rust jianying CLI.
• The user needs auditable planning, execution, or verification evidence, not just a conceptual answer.
• When the requirement is not yet clear, first hand it to jianying-draft-use routing; this skill should not be used for other editors, general video knowledge Q&A, or speculative execution lacking necessary materials.

Capability boundaries

• ✅ Can do: Generate a deterministic plan based on real paths and probe results; when capability is supported , execute operations in this domain; output the evidence level actually achieved.
• ⚠️ Requires conditions: Writes must use isolated copies; costs, external services, and native application actions must have precise approval; playback or export conclusions must have corresponding runtime evidence.
• ❌ Out of scope: Do not automatically install or upgrade the CLI, do not generate Python draft scripts, do not call external headless checkout, do not overwrite source drafts, do not fabricate resource IDs, media facts, or success status.

Step 1 — Establish the factual baseline

Record the user's goal, absolute paths, host platform, target deliverables, and allowed side effects; when information is insufficient, first provide a read-only diagnostic plan and list the missing facts item by item.

Step 2 — Handshake capabilities

Run version, doctor, and capabilities checks. A satisfying version does not mean a capability is available;partial、external_dependency or a missing state must enter the degraded path.

Step 3 — Validate inputs

Probe media, drafts, configuration, or task state; reject nonexistent paths, out-of-range times, unknown schemas, mismatched hashes, and approvals that cannot be bound to a target.

Step 4 — Form a deterministic plan

Write operations, parameters, output paths, risk levels, confirmation points, and expected evidence into the plan. Order multiple tasks as "read-only facts → reversible writes → external/native actions".

Step 5 — Execute or stop before the gate

Execute only steps that are supported and authorized. When output is ambiguous, times out, or partially succeeds, retain the task ID, audit logs, and artifacts; do not automatically retry.

Step 6 — Verify and deliver

Run structural validation, then append cold-reopen, playback, or native export evidence according to the goal; report the actual level, failed fields, recoverable actions, and unverified items.

Rules

• Material durations, dimensions, streams, hashes, and draft versions in the plan must come from tool output.
• Approval must be bound to the command, parameters, target, validity period, and budget; reconfirm if any field changes.
• User data is processed only within local target paths and the declared external Provider boundary; unrelated credentials must not be collected, uploaded, or recorded.
• When current evidence is insufficient, use UNVERIFIED、BLOCKED or AMBIGUOUS; do not fill in results by inference.

Gotchas

1. Treating version as capability: Always check the specific capability; do not execute directly just because the CLI version is new enough.
2. Treating structural validation as final acceptance: project verify Only proves the structural layer; playback and native export require independent evidence.
3. Directly modifying the source draft: First create an isolated copy and record the input hash; any in-place overwrite request must be stopped and changed to a new output.
4. For ambiguous, retry automatically: first query the task, audit, and external artifacts; only after confirming no side effects occurred may the user approve a retry.
5. Filling in resources or times from memory: resource IDs come from the catalog, times come from probe/ASR/project data; if unavailable, explicitly block.
6. Vaguely asking for more information: first give an executable read-only plan, then explicitly list gaps such as paths, delivery levels, or authorization.

Verification checklist

• CLI identity, version, and capabilities recorded.
• All input paths, media facts, and hashes are reviewable.
• Write targets are isolated from source drafts, and confirmation points are precisely bound.
• Failure and ambiguous paths retain task ID, logs, and recovery suggestions.
• Final wording matches the actual evidence level.

Execution contract

• Trigger conditions: task failure/interruption/ambiguous, draft write not completed, need to roll back a snapshot or relink assets.
• Required capabilities:job.show、job.retry、job.audit、store.restore。
• Minimum CLI version:1.6.0; before recovery, re-complete the capability and runtime identity handshake.
• Default risk:high_risk_write; show/audit are read_only.
• Input facts: task ID, state root, audit events, source/working copy/snapshot, external artifacts, current hashes, and editor state.
• Confirmation points: retry, restore, overwriting a target, resubmitting a paid request, or restarting a native task are each confirmed separately.
• Success evidence:structural; after recovery, the cold reopen, playback, or export acceptance of the original goal still needs to be re-completed.
• Prohibited actions: do not generate Python draft scripts, do not call external headless checkout, do not assume an ambiguous request was not executed, do not overwrite user drafts in place, and do not delete recovery evidence.

Workflow

1. job show and job audit to get status, last checkpoint, and recovery commands.
2. Check output, snapshot, and external artifact hashes; distinguish clear failures from ambiguous ones.
3. Clear failures may be retried after fixing inputs and obtaining new approval via job retry。
4. Draft transactions use store restore or the snapshot given by the audit to restore; before restoring, ensure CapCut is not occupying the target.
5. Re-run project verify, and continue the evidence gates required by the original task.

For state decisions and recovery cases, see references/workflow.md. For verification Jobs, see examples/minimal-job.json。

Progressive materials

• On first execution, load normal path first to get the end-to-end order.
• When encountering failures or unknown states, load failure recovery and error recovery table。
• When the user requests exceeding authority, overwriting, or automatic retry, load boundary refusal。
• Before delivery, complete verification checklistitem by item; do not claim completion based only on a plan or the existence of files.