更新几个 policy.md

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

@@ -14,7 +14,7 @@ For knowledge retrieval tasks, **this policy overrides generic codebase explorat
 
 - **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.
@@ -50,27 +48,35 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 5. Retrieval Breadth (`top_k`)
 
-- Apply `top_k` only to `rag_retrieve`. Use smallest sufficient value, expand if insufficient.
+- Apply `top_k` only to `rag_retrieve`. Choose the appropriate value upfront to maximize first-call success.
-- `30` for simple fact lookup → `50` for moderate synthesis/comparison → `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- Use `50` for simple fact lookup or moderate synthesis, comparison, summarization, disambiguation.
-- Expansion order: `30 → 50 → 100`. If unsure, use `100`.
+- Use `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- If unsure, use `50`. Only escalate to `100` on the retry call if first results are insufficient.
 
 ## 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.
+**Maximum 3 retrieval calls per question.** After each call, evaluate immediately:
+
+### Sufficient — answer now
+- The core entity/topic in the user's question has been hit.
+- There is direct evidence supporting the main intent of the question.
+- Partial but usable coverage is sufficient — you do NOT need exhaustive or perfect coverage to answer.
+- **When results are sufficient, compose the answer immediately. Do NOT call retrieval again to "double-check" or "get more context".**
+
+### Insufficient — retry
+- Empty, `Error:`, off-topic, missing core entity/scope, no usable evidence at all, or claims required by the answer are not explicitly supported.
 
 ## 7. Fallback and Sequential Retry
 
-On insufficient results, follow this sequence:
+On insufficient results, you may retry **up to 2 more times** (3 calls total):
 
-1. Rewrite query, retry same tool (once)
+1. Rewrite query, retry same tool.
-2. Switch to next retrieval source in default order
+2. For `rag_retrieve`, escalate `top_k` to `100` on retry.
-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 retries.
-- 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.
+- Do NOT call any retrieval tool more than 3 times in total.
 
 ## 8. Handling Missing or Partial Evidence
 
@@ -79,13 +85,7 @@ 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.
@@ -94,14 +94,7 @@ 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. Self-Knowledge Prohibition
-
-- 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.
-
-## 12. Self-Knowledge Prohibition
 
 This section applies whenever self-knowledge is disabled or forbidden for the current task.
 
@@ -111,19 +104,18 @@ This section applies whenever self-knowledge is disabled or forbidden for the cu
 - 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
+## 11. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
+- Called retrieval at most 3 times total (not more)?
+- Answered immediately when results were sufficient (did NOT call again unnecessarily)?
 - Did retrieval happen before any factual answer drafting?
 - 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-forbidden-self-knowledge.md

@@ -50,27 +50,38 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 5. Retrieval Breadth (`top_k`)
 
-- Apply `top_k` only to `rag_retrieve`. Use smallest sufficient value, expand if insufficient.
+- Apply `top_k` only to `rag_retrieve`. Choose the appropriate value upfront to maximize first-call success.
-- `30` for simple fact lookup → `50` for moderate synthesis/comparison → `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- Use `50` for simple fact lookup or moderate synthesis, comparison, summarization, disambiguation.
-- Expansion order: `30 → 50 → 100`. If unsure, use `100`.
+- Use `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- If unsure, use `50`. Only escalate to `100` on the retry call if first results are insufficient.
 
 ## 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.
+**Maximum 3 retrieval calls per question.** After each call, evaluate immediately:
+
+### Sufficient — answer now
+- The core entity/topic in the user's question has been hit.
+- There is direct evidence supporting the main intent of the question.
+- Partial but usable coverage is sufficient — you do NOT need exhaustive or perfect coverage to answer.
+- **When results are sufficient, compose the answer immediately. Do NOT call retrieval again to "double-check" or "get more context".**
+
+### Insufficient — retry
+- Empty, `Error:`, `no excel files found`, off-topic, missing core entity/scope, no usable evidence at all, or claims required by the answer are not explicitly supported.
 
 ## 7. Fallback and Sequential Retry
 
-On insufficient results, follow this sequence:
+On insufficient results, you may retry **up to 2 more times** (3 calls total):
 
-1. Rewrite query, retry same tool (once)
+1. Rewrite query, retry same tool.
-2. Switch to next retrieval source in default order
+2. Switch to next retrieval source in default order.
-3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100`
+3. For `rag_retrieve`, escalate `top_k` to `100` on retry.
-4. `table_rag_retrieve` insufficient → try `rag_retrieve`; `rag_retrieve` insufficient → try `table_rag_retrieve`
+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.
+- Say "no relevant information was found" **only after** exhausting all retries.
 - Do NOT switch to local filesystem inspection at any point.
 - Do NOT switch to model self-knowledge at any point.
+- Do NOT call any retrieval tool more than 3 times in total.
 
 ## 8. Handling Missing or Partial Evidence
 
@@ -83,7 +94,6 @@ On insufficient results, follow this sequence:
 
 - 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
 
@@ -94,14 +104,7 @@ 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
+## 11. Self-Knowledge Prohibition
-
-- 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.
-
-## 12. Self-Knowledge Prohibition
 
 This section applies whenever self-knowledge is disabled or forbidden for the current task.
 
@@ -111,19 +114,18 @@ This section applies whenever self-knowledge is disabled or forbidden for the cu
 - 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
+## 12. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
+- Called retrieval at most 3 times total (not more)?
+- Answered immediately when results were sufficient (did NOT call again unnecessarily)?
 - Did retrieval happen before any factual answer drafting?
 - 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/developing/rag-retrieve-no-citation/hooks/retrieval-policy-forbidden-self-knowledge.md

@@ -37,8 +37,8 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 1. **Skill-enabled retrieval tools** (use first when available)
 2. **`rag_retrieve`**
 
-- After each step, evaluate sufficiency before proceeding.
 - Retrieval must happen **before** any factual answer generation.
+- After each step, evaluate sufficiency before proceeding.
 
 ## 4. Query Preparation
 
@@ -48,25 +48,35 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 5. Retrieval Breadth (`top_k`)
 
-- Apply `top_k` only to `rag_retrieve`. Use smallest sufficient value, expand if insufficient.
+- Apply `top_k` only to `rag_retrieve`. Choose the appropriate value upfront to maximize first-call success.
-- `30` for simple fact lookup → `50` for moderate synthesis/comparison → `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- Use `50` for simple fact lookup or moderate synthesis, comparison, summarization, disambiguation.
-- Expansion order: `30 → 50 → 100`. If unsure, use `100`.
+- Use `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- If unsure, use `50`. Only escalate to `100` on the retry call if first results are insufficient.
 
 ## 6. Result Evaluation
 
-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.
+**Maximum 3 retrieval calls per question.** After each call, evaluate immediately:
+
+### Sufficient — answer now
+- The core entity/topic in the user's question has been hit.
+- There is direct evidence supporting the main intent of the question.
+- Partial but usable coverage is sufficient — you do NOT need exhaustive or perfect coverage to answer.
+- **When results are sufficient, compose the answer immediately. Do NOT call retrieval again to "double-check" or "get more context".**
+
+### Insufficient — retry
+- Empty, `Error:`, off-topic, missing core entity/scope, no usable evidence at all, or claims required by the answer are not explicitly supported.
 
 ## 7. Fallback and Sequential Retry
 
-On insufficient results, follow this sequence:
+On insufficient results, you may retry **up to 2 more times** (3 calls total):
 
-1. Rewrite query, retry same tool (once)
+1. Rewrite query, retry same tool.
-2. Switch to next retrieval source in default order
+2. For `rag_retrieve`, escalate `top_k` to `100` on retry.
-3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100`
 
-- Say "no relevant information was found" **only after** exhausting all retrieval sources.
+- Say "no relevant information was found" **only after** exhausting all retries.
 - Do NOT switch to local filesystem inspection at any point.
 - Do NOT switch to model self-knowledge at any point.
+- Do NOT call any retrieval tool more than 3 times in total.
 
 ## 8. Handling Missing or Partial Evidence
 
@@ -84,7 +94,6 @@ 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.
 
-
 ## 10. Self-Knowledge Prohibition
 
 This section applies whenever self-knowledge is disabled or forbidden for the current task.
@@ -103,9 +112,10 @@ This section applies whenever self-knowledge is disabled or forbidden for the cu
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
+- Called retrieval at most 3 times total (not more)?
+- Answered immediately when results were sufficient (did NOT call again unnecessarily)?
 - Did retrieval happen before any factual answer drafting?
 - Did every factual claim come from retrieved evidence rather than model knowledge?
-- Exhausted retrieval flow before concluding "not found"?
 - If any unsupported part remained, was it removed or explicitly marked unavailable?
 
 If any answer is "no", correct the process first.

skills/developing/rag-retrieve-no-citation/hooks/retrieval-policy.md

@@ -35,24 +35,34 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 4. Retrieval Breadth (`top_k`)
 
-- Apply `top_k` only to `rag_retrieve`. Use smallest sufficient value, expand if insufficient.
+- Apply `top_k` only to `rag_retrieve`. Choose the appropriate value upfront to maximize first-call success.
-- `30` for simple fact lookup → `50` for moderate synthesis/comparison → `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- Use `50` for simple fact lookup or moderate synthesis, comparison, summarization, disambiguation.
-- Expansion order: `30 → 50 → 100`. If unsure, use `100`.
+- Use `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- If unsure, use `50`. Only escalate to `100` on the retry call if first results are insufficient.
 
 ## 5. Result Evaluation
 
-Treat as insufficient if: empty, `Error:`, off-topic, missing core entity/scope, no usable evidence, partial coverage, or truncated results.
+**Maximum 3 retrieval calls per question.** After each call, evaluate immediately:
+
+### Sufficient — answer now
+- The core entity/topic in the user's question has been hit.
+- There is direct evidence supporting the main intent of the question.
+- Partial but usable coverage is sufficient — you do NOT need exhaustive or perfect coverage to answer.
+- **When results are sufficient, compose the answer immediately. Do NOT call retrieval again to "double-check" or "get more context".**
+
+### Insufficient — retry
+- Empty, `Error:`, off-topic, missing core entity/scope, no usable evidence at all.
 
 ## 6. Fallback and Sequential Retry
 
-On insufficient results, follow this sequence:
+On insufficient results, you may retry **up to 2 more times** (3 calls total):
 
-1. Rewrite query, retry same tool (once)
+1. Rewrite query, retry same tool.
-2. Switch to next retrieval source in default order
+2. For `rag_retrieve`, escalate `top_k` to `100` on retry.
-3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100`
 
-- Say "no relevant information was found" **only after** exhausting all retrieval sources.
+- Say "no relevant information was found" **only after** exhausting all retries.
 - Do NOT switch to local filesystem inspection at any point.
+- Do NOT call any retrieval tool more than 3 times in total.
 
 ## 7. Image Handling
 
@@ -81,7 +91,8 @@ This section applies only when self-knowledge is enabled.
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
-- Exhausted retrieval flow before concluding "not found"?
+- Called retrieval at most 3 times total (not more)?
+- Answered immediately when results were sufficient (did NOT call again unnecessarily)?
 - 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

@@ -48,25 +48,35 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 5. Retrieval Breadth (`top_k`)
 
-- Apply `top_k` only to `rag_retrieve`. Use smallest sufficient value, expand if insufficient.
+- Apply `top_k` only to `rag_retrieve`. Choose the appropriate value upfront to maximize first-call success.
-- `30` for simple fact lookup → `50` for moderate synthesis/comparison → `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- Use `50` for simple fact lookup or moderate synthesis, comparison, summarization, disambiguation.
-- Expansion order: `30 → 50 → 100`. If unsure, use `100`.
+- Use `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- If unsure, use `50`. Only escalate to `100` on the retry call if first results are insufficient.
 
 ## 6. Result Evaluation
 
-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.
+**Maximum 3 retrieval calls per question.** After each call, evaluate immediately:
+
+### Sufficient — answer now
+- The core entity/topic in the user's question has been hit.
+- There is direct evidence supporting the main intent of the question.
+- Partial but usable coverage is sufficient — you do NOT need exhaustive or perfect coverage to answer.
+- **When results are sufficient, compose the answer immediately. Do NOT call retrieval again to "double-check" or "get more context".**
+
+### Insufficient — retry
+- Empty, `Error:`, off-topic, missing core entity/scope, no usable evidence at all, or claims required by the answer are not explicitly supported.
 
 ## 7. Fallback and Sequential Retry
 
-On insufficient results, follow this sequence:
+On insufficient results, you may retry **up to 2 more times** (3 calls total):
 
-1. Rewrite query, retry same tool (once)
+1. Rewrite query, retry same tool.
-2. Switch to next retrieval source in default order
+2. For `rag_retrieve`, escalate `top_k` to `100` on retry.
-3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100`
 
-- Say "no relevant information was found" **only after** exhausting all retrieval sources.
+- Say "no relevant information was found" **only after** exhausting all retries.
 - Do NOT switch to local filesystem inspection at any point.
 - Do NOT switch to model self-knowledge at any point.
+- Do NOT call any retrieval tool more than 3 times in total.
 
 ## 8. Handling Missing or Partial Evidence
 
@@ -84,14 +94,7 @@ 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.
 
-## 10. Citation Requirements
+## 10. Self-Knowledge Prohibition
-
-- 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.
 
@@ -101,19 +104,18 @@ This section applies whenever self-knowledge is disabled or forbidden for the cu
 - 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
+## 11. Pre-Reply Self-Check
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
+- Called retrieval at most 3 times total (not more)?
+- Answered immediately when results were sufficient (did NOT call again unnecessarily)?
 - Did retrieval happen before any factual answer drafting?
 - 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-forbidden-self-knowledge.md

@@ -14,7 +14,7 @@ For knowledge retrieval tasks, **this policy overrides generic codebase explorat
 
 - **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, `rag_retrieve`. No other source for factual answering.
+- **Allowed tools only**: skill-enabled retrieval tools, `table_rag_retrieve`, `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**.
@@ -35,7 +35,9 @@ 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. **`rag_retrieve`**
+2. **`table_rag_retrieve`** or **`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.
@@ -48,25 +50,38 @@ Execute **sequentially, one at a time**. Do NOT run in parallel. Do NOT probe fi
 
 ## 5. Retrieval Breadth (`top_k`)
 
-- Apply `top_k` only to `rag_retrieve`. Use smallest sufficient value, expand if insufficient.
+- Apply `top_k` only to `rag_retrieve`. Choose the appropriate value upfront to maximize first-call success.
-- `30` for simple fact lookup → `50` for moderate synthesis/comparison → `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- Use `50` for simple fact lookup or moderate synthesis, comparison, summarization, disambiguation.
-- Expansion order: `30 → 50 → 100`. If unsure, use `100`.
+- Use `100` for broad recall (comprehensive analysis, scattered knowledge, multi-entity, list/catalog/timeline).
+- If unsure, use `50`. Only escalate to `100` on the retry call if first results are insufficient.
 
 ## 6. Result Evaluation
 
-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.
+**Maximum 3 retrieval calls per question.** After each call, evaluate immediately:
+
+### Sufficient — answer now
+- The core entity/topic in the user's question has been hit.
+- There is direct evidence supporting the main intent of the question.
+- Partial but usable coverage is sufficient — you do NOT need exhaustive or perfect coverage to answer.
+- **When results are sufficient, compose the answer immediately. Do NOT call retrieval again to "double-check" or "get more context".**
+
+### Insufficient — retry
+- Empty, `Error:`, `no excel files found`, off-topic, missing core entity/scope, no usable evidence at all, or claims required by the answer are not explicitly supported.
 
 ## 7. Fallback and Sequential Retry
 
-On insufficient results, follow this sequence:
+On insufficient results, you may retry **up to 2 more times** (3 calls total):
 
-1. Rewrite query, retry same tool (once)
+1. Rewrite query, retry same tool.
-2. Switch to next retrieval source in default order
+2. Switch to next retrieval source in default order.
-3. For `rag_retrieve`, expand `top_k`: `30 → 50 → 100`
+3. For `rag_retrieve`, escalate `top_k` to `100` on retry.
+4. `table_rag_retrieve` insufficient → try `rag_retrieve`; `rag_retrieve` insufficient → try `table_rag_retrieve`.
 
-- Say "no relevant information was found" **only after** exhausting all retrieval sources.
+- `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 retries.
 - Do NOT switch to local filesystem inspection at any point.
 - Do NOT switch to model self-knowledge at any point.
+- Do NOT call any retrieval tool more than 3 times in total.
 
 ## 8. Handling Missing or Partial Evidence
 
@@ -75,7 +90,12 @@ 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. Image Handling
+## 9. Table RAG Result Handling
+
+- Follow all `[INSTRUCTION]` and `[EXTRA_INSTRUCTION]` in results.
+- If truncated: tell user total (`N+M`), displayed (`N`), omitted (`M`).
+
+## 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.
@@ -84,13 +104,6 @@ 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.
 
-## 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.
@@ -101,7 +114,6 @@ This section applies whenever self-knowledge is disabled or forbidden for the cu
 - 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.
@@ -110,10 +122,10 @@ This section applies whenever self-knowledge is disabled or forbidden for the cu
 
 Before replying to a knowledge retrieval task, verify:
 - Used only whitelisted retrieval tools — no local filesystem inspection?
+- Called retrieval at most 3 times total (not more)?
+- Answered immediately when results were sufficient (did NOT call again unnecessarily)?
 - Did retrieval happen before any factual answer drafting?
 - 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.