更新提示词

skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md

@@ -10,7 +10,7 @@ Classify the request before acting:
 
 ## 1. Critical Enforcement
 
-For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**.
+For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**.
 
 - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference.
 - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful.
@@ -101,7 +101,22 @@ On insufficient results, follow this sequence:
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 - Do NOT cite claims that were not supported by retrieval.
 
-## 12. Pre-Reply Self-Check
+## 12. Self-Knowledge Prohibition
+
+This section applies whenever self-knowledge is disabled or forbidden for the current task.
+
+- Retrieval remains the only usable source for factual answering.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer only the supported parts.
+- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion.
+- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts must include citations.
+- Unsupported parts must be stated as unavailable rather than guessed.
+- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion.
+- If evidence is incomplete, state the limitation explicitly.
+
+## 13. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
@@ -109,5 +124,6 @@ Before replying to a knowledge retrieval task, verify:
 - Did every factual claim come from retrieved evidence rather than model knowledge?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If any unsupported part remained, was it removed or explicitly marked unavailable?
 
 If any answer is "no", correct the process first.

skills/autoload/onprem/rag-retrieve/hooks/retrieval-policy.md

@@ -79,11 +79,29 @@ On insufficient results, follow this sequence:
 - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end.
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 
-## 10. Pre-Reply Self-Check
+## 11. Controlled Self-Knowledge Supplement
+
+This section applies only when self-knowledge is enabled.
+
+- Retrieval remains the primary source.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer the supported parts first.
+- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background.
+- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts and self-knowledge supplements must be clearly separated in the response.
+- Retrieved facts must include citations.
+- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence.
+- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs.
+- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly.
+
+## 12. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope?
 
 If any answer is "no", correct the process first.
+

skills/autoload/support/rag-retrieve/hooks/retrieval-policy-forbidden-self-knowledge.md

@@ -10,7 +10,7 @@ Classify the request before acting:
 
 ## 1. Critical Enforcement
 
-For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**.
+For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**.
 
 - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference.
 - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful.
@@ -101,7 +101,22 @@ On insufficient results, follow this sequence:
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 - Do NOT cite claims that were not supported by retrieval.
 
-## 12. Pre-Reply Self-Check
+## 12. Self-Knowledge Prohibition
+
+This section applies whenever self-knowledge is disabled or forbidden for the current task.
+
+- Retrieval remains the only usable source for factual answering.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer only the supported parts.
+- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion.
+- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts must include citations.
+- Unsupported parts must be stated as unavailable rather than guessed.
+- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion.
+- If evidence is incomplete, state the limitation explicitly.
+
+## 13. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
@@ -109,5 +124,6 @@ Before replying to a knowledge retrieval task, verify:
 - Did every factual claim come from retrieved evidence rather than model knowledge?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If any unsupported part remained, was it removed or explicitly marked unavailable?
 
 If any answer is "no", correct the process first.

skills/autoload/support/rag-retrieve/hooks/retrieval-policy.md

@@ -79,11 +79,29 @@ On insufficient results, follow this sequence:
 - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end.
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 
-## 10. Pre-Reply Self-Check
+## 11. Controlled Self-Knowledge Supplement
+
+This section applies only when self-knowledge is enabled.
+
+- Retrieval remains the primary source.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer the supported parts first.
+- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background.
+- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts and self-knowledge supplements must be clearly separated in the response.
+- Retrieved facts must include citations.
+- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence.
+- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs.
+- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly.
+
+## 12. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope?
 
 If any answer is "no", correct the process first.
+

skills/onprem/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md

@@ -10,11 +10,11 @@ Classify the request before acting:
 
 ## 1. Critical Enforcement
 
-For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**.
+For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**.
 
 - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference.
 - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful.
-- **Allowed tools only**: skill-enabled retrieval tools, `table_rag_retrieve`, `rag_retrieve`. No other source for factual answering.
+- **Allowed tools only**: skill-enabled retrieval tools, `rag_retrieve`. No other source for factual answering.
 - Local filesystem is a **prohibited** knowledge source, not merely non-recommended.
 - Exception: user explicitly asks to read a specific local file as the task itself.
 - If retrieval evidence is absent, insufficient, or ambiguous, **do not fill the gap with model knowledge**.
@@ -35,9 +35,7 @@ For any knowledge retrieval task:
 Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe filesystem first.
 
 1. **Skill-enabled retrieval tools** (use first when available)
-2. **`table_rag_retrieve`** or **`rag_retrieve`**:
+2. **`rag_retrieve`**
-   - Prefer `table_rag_retrieve` for: values, prices, quantities, specs, rankings, comparisons, lists, tables, name lookup, historical coverage, mixed/unclear cases.
-   - Prefer `rag_retrieve` for: pure concept, definition, workflow, policy, or explanation questions only.
 
 - After each step, evaluate sufficiency before proceeding.
 - Retrieval must happen **before** any factual answer generation.
@@ -56,7 +54,7 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 6. Result Evaluation
 
-Treat as insufficient if: empty, `Error:`, `no excel files found`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported.
+Treat as insufficient if: empty, `Error:`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported.
 
 ## 7. Fallback and Sequential Retry
 
@@ -65,9 +63,7 @@ On insufficient results, follow this sequence:
 1. Rewrite query, retry same tool (once)
 2. Switch to next retrieval source in default order
 3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100`
-4. `table_rag_retrieve` insufficient → try `rag_retrieve`; `rag_retrieve` insufficient → try `table_rag_retrieve`
 
-- `table_rag_retrieve` internally falls back to `rag_retrieve` on `no excel files found`, but this does NOT change the higher-level order.
 - Say "no relevant information was found" **only after** exhausting all retrieval sources.
 - Do NOT switch to local filesystem inspection at any point.
 - Do NOT switch to model self-knowledge at any point.
@@ -79,13 +75,7 @@ On insufficient results, follow this sequence:
 - Prefer "the retrieved materials do not provide this information" over speculative completion.
 - When user asks for a definitive answer but evidence is incomplete, state the limitation directly.
 
-## 9. Table RAG Result Handling
+## 9. Image Handling
-
-- Follow all `[INSTRUCTION]` and `[EXTRA_INSTRUCTION]` in results.
-- If truncated: tell user total (`N+M`), displayed (`N`), omitted (`M`).
-- Cite sources using filenames from `file_ref_table`.
-
-## 10. Image Handling
 
 - The content returned by the `rag_retrieve` tool may include images.
 - Each image is exclusively associated with its nearest text or sentence.
@@ -94,13 +84,28 @@ On insufficient results, follow this sequence:
 - Each sentence or key point in the response should be accompanied by relevant images when they meet the established association criteria.
 - Avoid placing all images at the end of the response.
 
-## 11. Citation Requirements
+## 10. Citation Requirements
 
 - MUST generate `<CITATION ... />` tags when using retrieval results.
 - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end.
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 - Do NOT cite claims that were not supported by retrieval.
 
+## 11. Self-Knowledge Prohibition
+
+This section applies whenever self-knowledge is disabled or forbidden for the current task.
+
+- Retrieval remains the only usable source for factual answering.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer only the supported parts.
+- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion.
+- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts must include citations.
+- Unsupported parts must be stated as unavailable rather than guessed.
+- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion.
+- If evidence is incomplete, state the limitation explicitly.
+
 ## 12. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
@@ -109,5 +114,6 @@ Before replying to a knowledge retrieval task, verify:
 - Did every factual claim come from retrieved evidence rather than model knowledge?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If any unsupported part remained, was it removed or explicitly marked unavailable?
 
 If any answer is "no", correct the process first.

skills/onprem/rag-retrieve-only/hooks/retrieval-policy.md

@@ -69,11 +69,28 @@ On insufficient results, follow this sequence:
 - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end.
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 
-## 9. Pre-Reply Self-Check
+## 9. Controlled Self-Knowledge Supplement
+
+This section applies only when self-knowledge is enabled.
+
+- Retrieval remains the primary source.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer the supported parts first.
+- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background.
+- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts and self-knowledge supplements must be clearly separated in the response.
+- Retrieved facts must include citations.
+- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence.
+- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs.
+- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly.
+
+## 10. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope?
 
 If any answer is "no", correct the process first.

skills/support/rag-retrieve-only/hooks/retrieval-policy-forbidden-self-knowledge.md

@@ -10,11 +10,11 @@ Classify the request before acting:
 
 ## 1. Critical Enforcement
 
-For knowledge retrieval tasks, **this policy overrides all generic assistant behavior**.
+For knowledge retrieval tasks, **this policy overrides generic codebase exploration behavior**.
 
 - **Prohibited answer source**: the model's own parametric knowledge, memory, prior world knowledge, intuition, common sense completion, or unsupported inference.
 - **Prohibited tools**: `Glob`, `Read`, `LS`, Bash (`ls`, `find`, `cat`, `head`, `tail`, `grep`, etc.) — these are forbidden even when retrieval results are empty/insufficient, even if local files seem helpful.
-- **Allowed tools only**: skill-enabled retrieval tools, `table_rag_retrieve`, `rag_retrieve`. No other source for factual answering.
+- **Allowed tools only**: skill-enabled retrieval tools, `rag_retrieve`. No other source for factual answering.
 - Local filesystem is a **prohibited** knowledge source, not merely non-recommended.
 - Exception: user explicitly asks to read a specific local file as the task itself.
 - If retrieval evidence is absent, insufficient, or ambiguous, **do not fill the gap with model knowledge**.
@@ -35,9 +35,7 @@ For any knowledge retrieval task:
 Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe filesystem first.
 
 1. **Skill-enabled retrieval tools** (use first when available)
-2. **`table_rag_retrieve`** or **`rag_retrieve`**:
+2. **`rag_retrieve`**
-   - Prefer `table_rag_retrieve` for: values, prices, quantities, specs, rankings, comparisons, lists, tables, name lookup, historical coverage, mixed/unclear cases.
-   - Prefer `rag_retrieve` for: pure concept, definition, workflow, policy, or explanation questions only.
 
 - After each step, evaluate sufficiency before proceeding.
 - Retrieval must happen **before** any factual answer generation.
@@ -56,7 +54,7 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 6. Result Evaluation
 
-Treat as insufficient if: empty, `Error:`, `no excel files found`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported.
+Treat as insufficient if: empty, `Error:`, off-topic, missing core entity/scope, no usable evidence, partial coverage, truncated results, or claims required by the answer are not explicitly supported.
 
 ## 7. Fallback and Sequential Retry
 
@@ -65,9 +63,7 @@ On insufficient results, follow this sequence:
 1. Rewrite query, retry same tool (once)
 2. Switch to next retrieval source in default order
 3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100`
-4. `table_rag_retrieve` insufficient → try `rag_retrieve`; `rag_retrieve` insufficient → try `table_rag_retrieve`
 
-- `table_rag_retrieve` internally falls back to `rag_retrieve` on `no excel files found`, but this does NOT change the higher-level order.
 - Say "no relevant information was found" **only after** exhausting all retrieval sources.
 - Do NOT switch to local filesystem inspection at any point.
 - Do NOT switch to model self-knowledge at any point.
@@ -79,13 +75,7 @@ On insufficient results, follow this sequence:
 - Prefer "the retrieved materials do not provide this information" over speculative completion.
 - When user asks for a definitive answer but evidence is incomplete, state the limitation directly.
 
-## 9. Table RAG Result Handling
+## 9. Image Handling
-
-- Follow all `[INSTRUCTION]` and `[EXTRA_INSTRUCTION]` in results.
-- If truncated: tell user total (`N+M`), displayed (`N`), omitted (`M`).
-- Cite sources using filenames from `file_ref_table`.
-
-## 10. Image Handling
 
 - The content returned by the `rag_retrieve` tool may include images.
 - Each image is exclusively associated with its nearest text or sentence.
@@ -94,13 +84,28 @@ On insufficient results, follow this sequence:
 - Each sentence or key point in the response should be accompanied by relevant images when they meet the established association criteria.
 - Avoid placing all images at the end of the response.
 
-## 11. Citation Requirements
+## 10. Citation Requirements
 
 - MUST generate `<CITATION ... />` tags when using retrieval results.
 - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end.
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 - Do NOT cite claims that were not supported by retrieval.
 
+## 11. Self-Knowledge Prohibition
+
+This section applies whenever self-knowledge is disabled or forbidden for the current task.
+
+- Retrieval remains the only usable source for factual answering.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer only the supported parts.
+- The model must not supplement missing parts with general knowledge, conceptual explanation, common background, intuition, or likely completion.
+- The model must not use self-knowledge to invent or complete private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts must include citations.
+- Unsupported parts must be stated as unavailable rather than guessed.
+- If a paragraph would mix retrieved facts and unsupported completion, remove the unsupported completion.
+- If evidence is incomplete, state the limitation explicitly.
+
 ## 12. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
@@ -109,5 +114,6 @@ Before replying to a knowledge retrieval task, verify:
 - Did every factual claim come from retrieved evidence rather than model knowledge?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If any unsupported part remained, was it removed or explicitly marked unavailable?
 
 If any answer is "no", correct the process first.

skills/support/rag-retrieve-only/hooks/retrieval-policy.md

@@ -69,11 +69,28 @@ On insufficient results, follow this sequence:
 - Place citations immediately after the paragraph or bullet list using the knowledge. Do NOT collect at end.
 - 1-2 citations per paragraph/bullet. At least 1 citation when using retrieved knowledge.
 
-## 9. Pre-Reply Self-Check
+## 9. Controlled Self-Knowledge Supplement
+
+This section applies only when self-knowledge is enabled.
+
+- Retrieval remains the primary source.
+- If retrieval is sufficient, answer from retrieval only.
+- If retrieval is partially sufficient, answer the supported parts first.
+- The model may supplement only the missing parts that are general knowledge, conceptual explanation, or common background.
+- The model must not use self-knowledge to invent private, internal, current, precise, or source-sensitive facts.
+- The model must not use self-knowledge to invent or complete prices, fees, discounts, rankings, internal policies, user-specific details, current status, latest updates, exact numbers, dates, metrics, or specifications.
+- Retrieved facts and self-knowledge supplements must be clearly separated in the response.
+- Retrieved facts must include citations.
+- Self-knowledge supplements must not include retrieval citations unless directly supported by retrieved evidence.
+- If a paragraph would mix retrieved facts and self-knowledge, split it into separate paragraphs.
+- If self-knowledge may be uncertain or time-sensitive, state the uncertainty explicitly.
+
+## 10. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
 - Exhausted retrieval flow before concluding "not found"?
 - Citations placed immediately after each relevant paragraph?
+- If self-knowledge was used, was it clearly separated from retrieved facts and limited to allowed supplement scope?
 
 If any answer is "no", correct the process first.