project-tiny-context-harness 0.2.60 → 0.2.62

package/assets/skills/plan_acceptance_checklist_compiler/SKILL.md

@@ -21,33 +21,38 @@ The output answers:
 For this exact plan, what must be true before a future executor can honestly say the task is complete?
 ```
 
-This Skill is generic. Do not embed business-specific rules, provider-specific rules, product-domain assumptions, artifact schemas, API names, UI names, status names, or one-off project logic in this Skill. If the user's plan contains a specific domain, derive acceptance items from that plan and the project Context during the current invocation only.
+This Skill is generic. Do not embed business-specific rules, vendor-specific rules, product-domain assumptions, artifact schemas, concrete interface names, UI names, state names, or one-off project logic in this Skill. If the user's plan contains a specific domain, derive acceptance items from that plan and the project Context during the current invocation only.
 
 ## Required Outputs
 
-Every completed invocation must produce:
-
-1. A preserved copy of the plan under `tmp/ty-context/plan-acceptance/`.
-2. A rigorous acceptance checklist derived from the plan and relevant project Context.
-3. A goal/target-mode prompt the user can paste directly into Codex.
+Every completed invocation must produce:
+
+1. A preserved copy of the plan under `tmp/ty-context/plan-acceptance/`. The copied plan is the implementation/source plan, not acceptance proof.
+2. A rigorous full acceptance checklist under a separate `tmp/ty-context/plan-acceptance/<plan-slug>-acceptance-checklist.md` path. If the plan contains an explicit concrete acceptance checklist, reuse that plan-provided checklist verbatim; otherwise derive the checklist from the plan and relevant project Context. The full checklist is the complete acceptance standard.
+3. A goal/target-mode prompt the user can paste directly into Codex. The prompt may include a compact checklist summary for direction, priority and recovery navigation, but the full checklist owns the acceptance details.
+4. When a local audit path is referenced, it is temporary execution/progress state only, not Context and not proof by itself.
 
 Exception: if the Context confirmation gate below triggers, stop after materializing the plan and reading enough Context to explain the uncertainty. Ask the user for confirmation before producing the checklist or goal/target-mode prompt.
 
-The goal/target-mode prompt must be no longer than 3980 characters, including line breaks. This conservative budget keeps the prompt below Codex's 4000-character practical paste boundary even when character counting differs slightly. Keep the prompt information-dense: preserve required paths, core acceptance criteria, evidence rules, blockers and false-completion traps while using compact wording. Use the user's language when practical. For Chinese requests, use this shape:
-
-```text
-实施计划: tmp/ty-context/plan-acceptance/<plan>.md
-可多开agent，agent名额不够了就关掉不用的。
-<验收清单>
-```
-
-For English requests, use this shape:
-
-```text
-Plan: tmp/ty-context/plan-acceptance/<plan>.md
-You may use multiple agents; if agent slots run low, close idle or unnecessary agents.
-<acceptance checklist>
-```
+The goal/target-mode prompt must be no longer than 3850 characters, including line breaks. This conservative budget keeps the prompt below Codex's 4000-character practical paste boundary even when character counting differs slightly. Keep the prompt information-dense: preserve required paths, core acceptance criteria, evidence rules, blockers and false-completion traps while using compact wording. Use the user's language when practical. For Chinese requests, use this shape:
+
+```text
+实施计划: tmp/ty-context/plan-acceptance/<plan>.md（source/implementation plan，非验收证明）
+可多开agent，agent名额不够了就关掉不用的。
+完整验收清单: tmp/ty-context/plan-acceptance/<plan>-acceptance-checklist.md（该文件是完整验收标准，验收以这个为准。完成前必须逐项检查，不满足则继续实现。）
+执行审计: tmp/ty-context/plan-acceptance/<plan>-local-audit.md（临时 progress state，非 Context/proof）
+<验收清单>
+```
+
+For English requests, use this shape:
+
+```text
+Plan: tmp/ty-context/plan-acceptance/<plan>.md (implementation/source plan, not acceptance proof)
+You may use multiple agents; if agent slots run low, close idle or unnecessary agents.
+Full checklist: tmp/ty-context/plan-acceptance/<plan>-acceptance-checklist.md (complete acceptance standard; acceptance is judged against it; every item must be checked before completion)
+Local audit: tmp/ty-context/plan-acceptance/<plan>-local-audit.md (temporary execution/progress state, not Context or proof)
+<acceptance checklist>
+```
 
 This resource lifecycle line is part of the generated execution prompt. It authorizes parallel decomposition for the future executor while requiring unused agents to be closed when slots run low.
 
@@ -121,8 +126,8 @@ Rules:
 - If the user pasted the plan text, write the pasted plan exactly into `tmp/ty-context/plan-acceptance/<safe-plan-name>.md`.
 - Preserve the plan content. Do not summarize, normalize, reorder, translate, or edit it while materializing it.
 - Use a stable readable filename derived from the plan title, source filename, or user topic. Use lowercase letters, digits, hyphens, and `.md`.
-- If the source plan cannot be found or read, stop and report the missing source. Do not invent a plan.
-- The materialized plan is temporary execution input. It is not durable Context and not proof that any acceptance item passed.
+- If the source plan cannot be found or read, stop and report the missing source. Do not invent a plan.
+- The materialized plan is temporary implementation/source input. It is not durable Context, not acceptance proof and not proof that any acceptance item passed.
 
 Recommended paths:
 
@@ -133,8 +138,28 @@ tmp/ty-context/plan-acceptance/<plan-slug>-local-audit.md
 ```
 
 The local audit path is for the future goal/target-mode executor. This compiler may require the prompt to maintain it, but the file is a temporary recovery cache and not proof that any acceptance item passed.
-
-## Step 2: Read Relevant Project Context
+
+## Step 2: Reuse Any Explicit Plan-Provided Checklist
+
+After materializing the plan, inspect it for an explicit concrete acceptance checklist before generating a new checklist.
+
+Plan-provided checklist reuse applies only when the plan contains a clearly labeled checklist or checklist table section, such as `Acceptance Checklist`, `Acceptance Criteria`, `验收清单`, `验收标准`, or equivalent heading, and that section contains concrete acceptance items rather than only saying that acceptance is needed.
+
+When a plan-provided checklist is found:
+
+- Copy the plan-provided acceptance checklist section into `tmp/ty-context/plan-acceptance/<plan-slug>-acceptance-checklist.md` as the full checklist.
+- Preserve the extracted checklist verbatim, including the original language, item wording, order, IDs, Markdown tables, checkboxes, evidence notes, and blocker notes.
+- Do not derive, strengthen, reorder, translate, normalize, merge, split, or add acceptance items.
+- Do not prepend the generated `Acceptance Contract`, checklist table, self-test, or false-completion traps to the full checklist file when reusing a plan-provided checklist.
+- If multiple explicit checklist sections exist, copy all of them into the full checklist file in source order.
+- Keep the copied plan file and full checklist file separate, even if the checklist already appears inside the plan.
+- Continue to read relevant Context only as needed to explain ambiguities, conflicts, the goal/target-mode prompt, and any required local-audit or false-completion guidance. Do not use Context to expand the reused checklist unless the user separately asks for an audit or rewrite.
+- If the plan-provided checklist is too large for the 3850-character prompt budget, keep it intact in the full checklist file and make the prompt reference that file as the acceptance authority; do not invent a compact replacement checklist with new criteria.
+- Skip Steps 5 and 6 for the full checklist file unless the user separately asks for a checklist audit or rewrite.
+
+When no explicit concrete plan-provided checklist exists, continue with the generated-checklist flow below.
+
+## Step 3: Read Relevant Project Context
 
 Read only the Context needed for the plan's impacted surfaces. Use Context to identify what the project says the system should mean.
 
@@ -150,7 +175,7 @@ Extract:
 - Known non-goals and forbidden dependencies.
 - Existing implementation entry points.
 
-## Step 3: Run The Context Confirmation Gate
+## Step 4: Run The Context Confirmation Gate
 
 After reading the plan and relevant Context, decide whether generating an acceptance checklist would require guessing or silently accepting many durable fact changes. If yes, stop and ask the user to confirm details before continuing.
 
@@ -171,11 +196,11 @@ When the gate triggers:
 - Include the materialized plan path if already written.
 - State the specific Context files or Context roles that made confirmation necessary.
 - Offer a concrete default only when it is safe and reversible; otherwise ask for an explicit decision.
-- Resume from Step 2 after the user answers.
+- Resume from Step 3 after the user answers.
 
 Do not trigger this gate merely because the plan is large. If the Context impact is clear, bounded, and the checklist can represent the durable Context updates as acceptance items without guessing, continue.
 
-## Step 4: Compile The Acceptance Contract
+## Step 5: Compile The Acceptance Contract
 
 Before the detailed checklist, write a compact contract:
 
@@ -187,17 +212,22 @@ Before the detailed checklist, write a compact contract:
 - Completion definition: <what must be true>
 - Core surfaces: <code/API/UI/data/runtime/artifact/test/context/etc.>
 - Explicit non-goals: <items>
-- External blockers: <accounts/session/credentials/network/cloud/manual approval/etc.>
-- Evidence standard: <accepted proof types>
-```
+- External blockers: <accounts/session/credentials/network/cloud/manual approval/etc.>
+- Evidence standard: <accepted proof types>
+- Current-state claims: <which "current", "generated", "synced", "tested", "accepted" or runtime claims require current evidence>
+- Evidence ledger required: <whether the checklist or future executor must maintain current evidence by item>
+- Invalid completion evidence: <stale artifacts, code-only edits, partial tests, unexercised runtime, mismatched read paths or other evidence that cannot prove completion>
+```
 
 If the plan uses broad words such as `all`, `complete`, `maximum`, `maximized`, `accepted`, `formal`, `production`, `real`, `current`, or `verified`, convert them into explicit inventory and evidence requirements.
 
-## Step 5: Build The Full Acceptance Checklist
-
-Treat the checklist as the set of falsifiable acceptance items a future executor must satisfy. It is not a progress log.
-
-Create a checklist table with these columns:
+## Step 6: Build The Full Acceptance Checklist
+
+Treat the checklist as the set of falsifiable acceptance items a future executor must satisfy. It is not a progress log.
+
+Use this generated-checklist step only when Step 2 did not find an explicit concrete plan-provided checklist. If Step 2 found one, the full checklist file is the verbatim extracted checklist and this step is skipped.
+
+Create a checklist table with these columns:
 
 ```markdown
 | ID | Acceptance item | Source | Scope | Required evidence | Verification method | Fail / not accepted if |
@@ -214,9 +244,28 @@ Column rules:
 - `Verification method`: concrete command, check, inspection path, API call, UI check, artifact validation, or manual proof.
 - `Fail / not accepted if`: concrete invalidation case.
 
-Each item must be evidence-bound and falsifiable. Split combined requirements into separate rows.
-
-## Hard Blocker Handling
+Each item must be evidence-bound and falsifiable. Split combined requirements into separate rows.
+
+For current-state or evidence-heavy plans, also require the future executor to maintain an Evidence Ledger table:
+
+```markdown
+| AC | Expected state | Current observed state | Current evidence | Evidence location / API / UI / command | Conclusion | Gap / blocker |
+|---|---|---|---|---|---|---|
+```
+
+Allowed `Conclusion` values:
+
+- `proven`
+- `unproven`
+- `stale-evidence`
+- `runtime-disconnected`
+- `implementation-drift`
+- `blocked`
+- `deferred-by-explicit-scope`
+
+Missing ledger evidence means incomplete, not complete. Do not let missing evidence, old evidence, partial evidence or evidence from a different read path satisfy a current-state claim.
+
+## Hard Blocker Handling
 
 Treat any unresolved required blocker as non-completion. A checklist may describe blocked acceptance work, but blocked work is still not accepted until the required evidence exists.
 
@@ -258,7 +307,7 @@ When user input is still required, the blocker request must be the smallest conc
 - Acceptance impact if the blocker remains unresolved.
 - Allowed fallback, deferred or narrowed-scope option, if the plan or Context permits one.
 
-Do not replace this with broad requests such as "provide the token", "send the AppSecret" or "give me the configuration credentials" when a narrower page, field, runtime setup step or delegated user action would satisfy the blocker.
+Do not replace this with broad requests such as "provide the token", "send the secret value" or "give me the configuration credentials" when a narrower page, field, runtime setup step or delegated user action would satisfy the blocker.
 
 ## Generic Acceptance Dimensions
 
@@ -342,18 +391,28 @@ After the checklist, include traps that a future executor must not mistake for c
 
 Use generic wording. Do not add business-specific traps to the Skill itself.
 
-Template:
-
-```markdown
-## False-Completion Traps
-
-- <activity> is not enough unless <acceptance proof> also exists.
-- <partial proof> cannot prove <full acceptance item>.
-- <old/stale/mismatched evidence> cannot prove current completion.
-- <surface A> passing does not prove <surface B> unless the checklist links them.
-```
-
-## Suggested Execution Order
+Template:
+
+```markdown
+## False-Completion Traps
+
+- <activity> is not enough unless <acceptance proof> also exists.
+- <partial proof> cannot prove <full acceptance item>.
+- <old/stale/mismatched evidence> cannot prove current completion.
+- <surface A> passing does not prove <surface B> unless the checklist links them.
+```
+
+For evidence-ledger plans, keep the traps generic and cover these cases when relevant:
+
+- Code-only changes without current execution or acceptance evidence.
+- UI/API shell behavior without the backing data, runtime or artifact evidence required by the checklist.
+- Stale artifacts or stale runtime evidence.
+- Evidence from a mismatched read path, service path, artifact path or runtime instance.
+- Unexercised runtime or unexercised fallback behavior.
+- Partial tests, smoke-only checks or dry runs when the plan requires broader current proof.
+- API/UI/data/test contradictions that remain unresolved.
+
+## Suggested Execution Order
 
 Suggest an execution order that prioritizes the highest-risk proof first:
 
@@ -387,16 +446,18 @@ Every generated checklist must pass this self-test:
 
 ## Goal/Target-Mode Prompt Generation
 
-After compiling the checklist, produce a paste-ready goal/target-mode prompt.
+After reusing a plan-provided checklist or compiling a generated checklist, produce a paste-ready goal/target-mode prompt.
 
-Hard requirements:
-
-- The prompt must be no longer than 3980 characters including line breaks. Treat 3980 as the effective hard budget and preserve information density; do not drop required paths, core acceptance categories, blocker rules, evidence rules or false-completion traps merely to be short.
-- The first line must identify the plan path.
-- Use `实施计划: <path>` for Chinese prompts and `Plan: <path>` for English prompts.
-- The second line must be a resource lifecycle instruction: `可多开agent，agent名额不够了就关掉不用的。` for Chinese prompts or `You may use multiple agents; if agent slots run low, close idle or unnecessary agents.` for English prompts.
-- The remaining content must be the acceptance checklist or a compact version of it.
+Hard requirements:
+
+- The prompt must be no longer than 3850 characters including line breaks. Treat 3850 as the effective hard budget and preserve information density; do not drop required paths, core acceptance categories, blocker rules, evidence rules or false-completion traps merely to be short.
+- The first line must identify the plan path.
+- Use `实施计划: <path>` for Chinese prompts and `Plan: <path>` for English prompts. The line must say the plan is the implementation/source plan and not acceptance proof.
+- The second line must be a resource lifecycle instruction: `可多开agent，agent名额不够了就关掉不用的。` for Chinese prompts or `You may use multiple agents; if agent slots run low, close idle or unnecessary agents.` for English prompts.
+- The remaining content must be the acceptance checklist or a compact version of it.
 - The prompt must be self-contained enough for goal/target-mode execution.
+- The prompt must identify the full checklist path and say it is the complete acceptance standard. Chinese prompts must include this exact sentence: `该文件是完整验收标准，验收以这个为准。完成前必须逐项检查，不满足则继续实现。` English prompts must say the full checklist is the complete acceptance standard, acceptance is judged against it, and every item must be checked before completion.
+- If the prompt uses a compact checklist summary, say the full checklist owns details and acceptance authority; the compact summary owns direction, priority and recovery navigation; overlap is allowed; conflicts are resolved in favor of the full checklist.
 - The prompt must identify a local audit path, normally `tmp/ty-context/plan-acceptance/<plan-slug>-local-audit.md`, and require the future executor to read it before resuming, keep it current during execution, and use it only as target-mode acceptance progress state.
 - The prompt must require the local audit to record overall status (`complete`, `incomplete`, `blocked` or `narrowed-scope-complete`), each core AC status and current evidence, commands with result/time/failure reason, artifact or evidence paths, blockers and missing evidence, acceptance impact, explicit deferred or narrowed scope, and stale/partial/smoke/dry-run/research evidence that cannot prove full completion.
 - The prompt must say that local audit is not Context, not product-quality proof, not a global task manager, and not a replacement for project tests, CI, review, human acceptance, Task Contract or workflow-contract `plan.md`.
@@ -405,15 +466,17 @@ Hard requirements:
 - Do not include Markdown tables inside the prompt if they make it too long.
 - Prefer short numbered items over verbose prose.
 - If the full checklist is too large, write the full checklist to `tmp/ty-context/plan-acceptance/<plan-slug>-acceptance-checklist.md`, then compress the goal/target-mode prompt by increasing information density while preserving all core acceptance categories.
-- The compact prompt may reference the full checklist path, but it must still include the core completion criteria directly.
+- If the full checklist came from a plan-provided checklist and is too large, keep the extracted checklist unchanged in the full checklist file and compress the prompt by referencing the full checklist path, not by rewriting or adding criteria.
+- The compact prompt may reference the full checklist path, but it must still include the core completion criteria directly and state that the summary is direction/priority/recovery navigation, not the acceptance authority.
 
 Recommended compact Chinese prompt shape:
 
 ```text
-实施计划: tmp/ty-context/plan-acceptance/<plan-slug>.md
+实施计划: tmp/ty-context/plan-acceptance/<plan-slug>.md（source/implementation plan，非验收证明）
 可多开agent，agent名额不够了就关掉不用的。
-完整验收清单: tmp/ty-context/plan-acceptance/<plan-slug>-acceptance-checklist.md
-执行审计: tmp/ty-context/plan-acceptance/<plan-slug>-local-audit.md
+完整验收清单: tmp/ty-context/plan-acceptance/<plan-slug>-acceptance-checklist.md（该文件是完整验收标准，验收以这个为准。完成前必须逐项检查，不满足则继续实现。）
+执行审计: tmp/ty-context/plan-acceptance/<plan-slug>-local-audit.md（临时 progress state，非 Context/proof）
+本摘要只负责 direction/priority/recovery navigation；允许与完整 checklist 重叠，冲突时以完整 checklist 为准。
 
 验收清单：
 AC1 <核心完成定义，包含验收证据>
@@ -437,10 +500,11 @@ AC14 完成前审计：逐条对照实施计划和完整 checklist；每个 core
 Recommended compact English prompt shape:
 
 ```text
-Plan: tmp/ty-context/plan-acceptance/<plan-slug>.md
+Plan: tmp/ty-context/plan-acceptance/<plan-slug>.md (implementation/source plan, not acceptance proof)
 You may use multiple agents; if agent slots run low, close idle or unnecessary agents.
-Full checklist: tmp/ty-context/plan-acceptance/<plan-slug>-acceptance-checklist.md
-Local audit: tmp/ty-context/plan-acceptance/<plan-slug>-local-audit.md
+Full checklist: tmp/ty-context/plan-acceptance/<plan-slug>-acceptance-checklist.md (complete acceptance standard; acceptance is judged against it; every item must be checked before completion)
+Local audit: tmp/ty-context/plan-acceptance/<plan-slug>-local-audit.md (temporary progress state, not Context or proof)
+This summary is only direction, priority and recovery navigation; overlap with the full checklist is allowed, and the full checklist wins conflicts.
 
 Acceptance checklist:
 AC1 <core completion definition with required evidence>
@@ -460,17 +524,18 @@ AC14 Final audit: compare every item against the plan and full checklist; every
 
 Do not count these as completion: code-only changes, plan-only updates, partial tests, stale or partial evidence, infrastructure without acceptance proof, runtime not configured/exercised, artifact not accepted by validator, API/UI not reflecting accepted evidence, unexercised fallback, unresolved hard blockers, or contradictions between API/UI/data/tests.
 ```
-
-Before final response, check the prompt length. If it exceeds 3980 characters, compress by tightening wording and referring to the full checklist path while preserving required paths, core AC categories, blocker/evidence rules and false-completion traps; then check again.
+
+Before final response, check the prompt length. If it exceeds 3850 characters, compress by tightening wording and referring to the full checklist path while preserving required paths, core AC categories, blocker/evidence rules and false-completion traps; then check again.
 
 ## Final Response Requirements
 
-For completed checklist runs, the final response must include:
-
-- `tmp/ty-context/plan-acceptance/` plan path.
-- Full checklist path if a full checklist file was written.
-- The paste-ready goal/target-mode prompt in a code block.
-- Any unresolved ambiguity that affects checklist accuracy.
+For completed checklist runs, the final response must include:
+
+- `tmp/ty-context/plan-acceptance/` plan path.
+- Full checklist path if a full checklist file was written.
+- Whether the full checklist was reused from a plan-provided checklist or generated by this Skill.
+- The paste-ready goal/target-mode prompt in a code block.
+- Any unresolved ambiguity that affects checklist accuracy.
 
 If the Context confirmation gate triggers, the response must ask for the needed confirmation instead of including the checklist or goal/target-mode prompt.
 
@@ -488,6 +553,8 @@ Do not use the checklist to mark the task complete.
 
 Do not hide missing source files, ambiguous plan scope, or external blockers.
 
-Do not rewrite the user's plan while copying it into `tmp/ty-context/plan-acceptance/`.
-
-Do not use a short sample, stale artifact, old result, or current implementation convenience to reduce a plan that asked for full completion.
+Do not rewrite the user's plan while copying it into `tmp/ty-context/plan-acceptance/`.
+
+Do not rewrite, strengthen, reorder, translate, normalize, or add items to a plan-provided checklist when the plan already includes an explicit concrete checklist.
+
+Do not use a short sample, stale artifact, old result, or current implementation convenience to reduce a plan that asked for full completion.

package/dist/commands/export-context-args.d.ts

@@ -0,0 +1,21 @@
+import type { SourcePackMode } from "../lib/source-pack-types.js";
+export interface ExportContextArgs {
+    full: boolean;
+    code: boolean;
+    all: boolean;
+    sourceMode?: SourcePackMode;
+    taskName?: string;
+    check: boolean;
+    output?: string;
+    profile?: string;
+    includeContext: string[];
+    includeCode: string[];
+    bundleStrategy?: "auto" | "area" | "topdir" | "config";
+    maxPackFiles?: number;
+    maxBundleCharacters?: number;
+    redactionStrict: boolean;
+    prune?: number;
+    help: boolean;
+}
+export declare function parseArgs(args: string[]): ExportContextArgs;
+export declare function helpText(): string;

package/dist/commands/export-context-args.js

@@ -0,0 +1,149 @@
+export function parseArgs(args) {
+    const parsed = {
+        full: false,
+        code: false,
+        all: false,
+        check: false,
+        includeContext: [],
+        includeCode: [],
+        redactionStrict: false,
+        help: false
+    };
+    for (let index = 0; index < args.length; index += 1) {
+        const arg = args[index];
+        if (arg === "--full")
+            parsed.full = true;
+        else if (arg === "--code")
+            parsed.code = true;
+        else if (arg === "--all")
+            parsed.all = true;
+        else if (arg === "--code-index")
+            parsed.sourceMode = "code-index";
+        else if (arg === "--source-pack")
+            parsed.sourceMode = "source-pack";
+        else if (arg === "--code-bundles")
+            parsed.sourceMode = "code-bundles";
+        else if (arg === "--check")
+            parsed.check = true;
+        else if (arg === "--help" || arg === "-h")
+            parsed.help = true;
+        else if (arg === "--redaction-strict")
+            parsed.redactionStrict = true;
+        else if (arg === "--task-context")
+            index = readValue(args, index, "export-context --task-context requires a name", (value) => {
+                parsed.sourceMode = "task-context";
+                parsed.taskName = value;
+            });
+        else if (arg.startsWith("--task-context=")) {
+            parsed.sourceMode = "task-context";
+            parsed.taskName = inlineValue(arg, "--task-context", "export-context --task-context requires a name");
+        }
+        else if (arg === "--output")
+            index = readValue(args, index, "export-context --output requires a path", (value) => (parsed.output = value));
+        else if (arg.startsWith("--output="))
+            parsed.output = inlineValue(arg, "--output", "export-context --output requires a path");
+        else if (arg === "--profile")
+            index = readValue(args, index, "export-context --profile requires an id", (value) => (parsed.profile = value));
+        else if (arg.startsWith("--profile="))
+            parsed.profile = inlineValue(arg, "--profile", "export-context --profile requires an id");
+        else if (arg === "--include-context")
+            index = readValue(args, index, "export-context --include-context requires a repo-relative path or glob", (value) => parsed.includeContext.push(value));
+        else if (arg.startsWith("--include-context="))
+            parsed.includeContext.push(inlineValue(arg, "--include-context", "export-context --include-context requires a repo-relative path or glob"));
+        else if (arg === "--include-code")
+            index = readValue(args, index, "export-context --include-code requires a repo-relative path or glob", (value) => parsed.includeCode.push(value));
+        else if (arg.startsWith("--include-code="))
+            parsed.includeCode.push(inlineValue(arg, "--include-code", "export-context --include-code requires a repo-relative path or glob"));
+        else if (arg === "--bundle-strategy")
+            index = readValue(args, index, "export-context --bundle-strategy requires auto, area, topdir or config", (value) => (parsed.bundleStrategy = parseBundleStrategy(value)));
+        else if (arg.startsWith("--bundle-strategy="))
+            parsed.bundleStrategy = parseBundleStrategy(inlineValue(arg, "--bundle-strategy", "export-context --bundle-strategy requires auto, area, topdir or config"));
+        else if (arg === "--max-pack-files")
+            index = readValue(args, index, "export-context --max-pack-files requires a positive integer", (value) => (parsed.maxPackFiles = parseInteger(value, "--max-pack-files", false)));
+        else if (arg.startsWith("--max-pack-files="))
+            parsed.maxPackFiles = parseInteger(inlineValue(arg, "--max-pack-files", "export-context --max-pack-files requires a positive integer"), "--max-pack-files", false);
+        else if (arg === "--max-bundle-characters")
+            index = readValue(args, index, "export-context --max-bundle-characters requires a positive integer", (value) => (parsed.maxBundleCharacters = parseInteger(value, "--max-bundle-characters", false)));
+        else if (arg.startsWith("--max-bundle-characters="))
+            parsed.maxBundleCharacters = parseInteger(inlineValue(arg, "--max-bundle-characters", "export-context --max-bundle-characters requires a positive integer"), "--max-bundle-characters", false);
+        else if (arg === "--prune")
+            index = readValue(args, index, "export-context --prune requires a non-negative integer", (value) => (parsed.prune = parseInteger(value, "--prune", true)));
+        else if (arg.startsWith("--prune="))
+            parsed.prune = parseInteger(inlineValue(arg, "--prune", "export-context --prune requires a non-negative integer"), "--prune", true);
+        else
+            throw new Error(`unknown export-context argument: ${arg}`);
+    }
+    validateParsedArgs(parsed);
+    return parsed;
+}
+export function helpText() {
+    return `ty-context export-context:
+  export-context --full [--output tmp/ty-context/context-exports/<name>.md] [--check]
+  export-context --code [--output tmp/ty-context/context-exports/<name>.md] [--check]
+  export-context --all [--check]
+  export-context --code-index [--profile <id>] [--include-code <path-or-glob>] [--check]
+  export-context --source-pack [--profile <id>] [--bundle-strategy auto|area|topdir|config] [--max-pack-files 5] [--max-bundle-characters <n>] [--redaction-strict] [--prune <count>] [--check]
+  export-context --code-bundles [--profile <id>] [--include-code <path-or-glob>] [--max-pack-files 5] [--check]
+  export-context --task-context <name> [--profile <id>] [--include-context <path-or-glob>] [--include-code <path-or-glob>] [--max-pack-files 5] [--redaction-strict] [--check]
+
+Creates temporary Markdown artifacts for copying or external-tool ingestion.
+--full exports the project Context summary as a full-project-context artifact.
+--code exports one current implementation snapshot as a code-level-implementation artifact.
+--all exports both default artifacts in one command.
+Source Pack modes write timestamped directories plus latest/ under tmp/ty-context/context-exports/**.
+--source-pack and --task-context are bounded to at most 5 files; --max-pack-files cannot exceed 5.
+Profiles are export selectors read from <harnessRoot>/config.yaml; verification entries are listed, not executed.
+Secret redaction is always enabled; --redaction-strict fails if redaction was required.
+The artifact must stay under tmp/ty-context/context-exports/** and must not be referenced from project_context/context.toml.`;
+}
+function validateParsedArgs(parsed) {
+    const modeCount = Number(parsed.full) + Number(parsed.code) + Number(parsed.all) + Number(parsed.sourceMode !== undefined);
+    if (modeCount > 1) {
+        throw new Error("export-context accepts exactly one mode: --full, --code, --all, --code-index, --source-pack, --code-bundles or --task-context");
+    }
+    if (parsed.all && parsed.output) {
+        throw new Error("export-context --all writes two default artifacts; --output is only supported with --full or --code");
+    }
+    if (parsed.sourceMode && parsed.output) {
+        throw new Error("export-context --output is only supported with legacy --full or --code single-artifact modes");
+    }
+    if (!parsed.sourceMode && hasSourcePackOnlyOptions(parsed)) {
+        throw new Error("profile/include/bundle/max/prune/redaction-strict options are only supported with Source Pack modes");
+    }
+}
+function readValue(args, index, message, apply) {
+    const value = args[index + 1];
+    if (!value || value.startsWith("--")) {
+        throw new Error(message);
+    }
+    apply(value);
+    return index + 1;
+}
+function inlineValue(arg, flag, message) {
+    const value = arg.slice(`${flag}=`.length).trim();
+    if (!value)
+        throw new Error(message);
+    return value;
+}
+function parseBundleStrategy(value) {
+    if (value === "auto" || value === "area" || value === "topdir" || value === "config")
+        return value;
+    throw new Error("export-context --bundle-strategy must be one of auto, area, topdir or config");
+}
+function parseInteger(value, flag, allowZero) {
+    const parsed = Number.parseInt(value, 10);
+    if (!Number.isInteger(parsed) || String(parsed) !== value.trim() || parsed < 0 || (!allowZero && parsed === 0)) {
+        throw new Error(`export-context ${flag} requires ${allowZero ? "a non-negative" : "a positive"} integer`);
+    }
+    return parsed;
+}
+function hasSourcePackOnlyOptions(parsed) {
+    return Boolean(parsed.profile ||
+        parsed.includeContext.length > 0 ||
+        parsed.includeCode.length > 0 ||
+        parsed.bundleStrategy ||
+        parsed.maxPackFiles ||
+        parsed.maxBundleCharacters ||
+        parsed.redactionStrict ||
+        parsed.prune !== undefined);
+}