From ba5770931016ac8cc25c2cc994cc99b008f051f2 Mon Sep 17 00:00:00 2001 From: Aishanee Shah Date: Wed, 1 Apr 2026 19:13:22 +0000 Subject: [PATCH 1/3] feat(core): add Strategic Re-evaluation guidance to system prompt --- .../core/__snapshots__/prompts.test.ts.snap | 96 +++++++++++++++++++ packages/core/src/prompts/snippets.ts | 6 ++ 2 files changed, 102 insertions(+) diff --git a/packages/core/src/core/__snapshots__/prompts.test.ts.snap b/packages/core/src/core/__snapshots__/prompts.test.ts.snap index 1506e56a456..9b7a5f7a05d 100644 --- a/packages/core/src/core/__snapshots__/prompts.test.ts.snap +++ b/packages/core/src/core/__snapshots__/prompts.test.ts.snap @@ -762,6 +762,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -908,6 +914,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -1036,6 +1048,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -1688,6 +1706,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -1847,6 +1871,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -2010,6 +2040,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -2173,6 +2209,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -2332,6 +2374,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -2493,6 +2541,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -2613,6 +2667,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -2771,6 +2831,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -3057,6 +3123,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -3473,6 +3545,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -3632,6 +3710,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -3905,6 +3989,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. @@ -4064,6 +4154,12 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. diff --git a/packages/core/src/prompts/snippets.ts b/packages/core/src/prompts/snippets.ts index d75a6545e74..e99d93a9940 100644 --- a/packages/core/src/prompts/snippets.ts +++ b/packages/core/src/prompts/snippets.ts @@ -347,6 +347,12 @@ ${workflowStepStrategy(options)} **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +1. Stop and remind yourself of the original task description. +2. List your current assumptions and identify which ones might be wrong. +3. Propose a different architectural approach rather than continuing to patch the current one. +4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. + ## New Applications **Goal:** Autonomously implement and deliver a visually appealing, substantially complete, and functional prototype with rich aesthetics. Users judge applications by their visual impact; ensure they feel modern, "alive," and polished through consistent spacing, interactive feedback, and platform-appropriate design. From 1514414b640d7febb7d4031173231fea387e70f2 Mon Sep 17 00:00:00 2001 From: Aishanee Shah Date: Wed, 8 Apr 2026 14:46:00 +0000 Subject: [PATCH 2/3] chore: refine strategic re-evaluation guidance --- packages/core/src/prompts/snippets.ts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/packages/core/src/prompts/snippets.ts b/packages/core/src/prompts/snippets.ts index e99d93a9940..a2853c89645 100644 --- a/packages/core/src/prompts/snippets.ts +++ b/packages/core/src/prompts/snippets.ts @@ -347,11 +347,10 @@ ${workflowStepStrategy(options)} **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications From c880debcde0557e7301c2b9832fc05c88413c10e Mon Sep 17 00:00:00 2001 From: Aishanee Shah Date: Wed, 8 Apr 2026 14:54:49 +0000 Subject: [PATCH 3/3] test(core): update prompt snapshots --- .../core/__snapshots__/prompts.test.ts.snap | 48 +++++++------------ 1 file changed, 16 insertions(+), 32 deletions(-) diff --git a/packages/core/src/core/__snapshots__/prompts.test.ts.snap b/packages/core/src/core/__snapshots__/prompts.test.ts.snap index 9b7a5f7a05d..0e9cc591d13 100644 --- a/packages/core/src/core/__snapshots__/prompts.test.ts.snap +++ b/packages/core/src/core/__snapshots__/prompts.test.ts.snap @@ -762,11 +762,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -914,11 +913,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -1048,11 +1046,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -1706,11 +1703,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -1871,11 +1867,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -2040,11 +2035,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -2209,11 +2203,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -2374,11 +2367,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -2541,11 +2533,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -2667,11 +2658,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -2831,11 +2821,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -3123,11 +3112,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -3545,11 +3533,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -3710,11 +3697,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -3989,11 +3975,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications @@ -4154,11 +4139,10 @@ Operate using a **Research -> Strategy -> Execution** lifecycle. For the Executi **Validation is the only path to finality.** Never assume success or settle for unverified changes. Rigorous, exhaustive verification is mandatory; it prevents the compounding cost of diagnosing failures later. A task is only complete when the behavioral correctness of the change has been verified and its structural integrity is confirmed within the full project context. Prioritize comprehensive validation above all else, utilizing redirection and focused analysis to manage high-output tasks without sacrificing depth. Never sacrifice validation rigor for the sake of brevity or to minimize tool-call overhead; partial or isolated checks are insufficient when more comprehensive validation is possible. -**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 5 times without success, you must: +**Strategic Re-evaluation:** If you have attempted to fix a failing implementation more than 3 times without success, you must: 1. Stop and remind yourself of the original task description. 2. List your current assumptions and identify which ones might be wrong. 3. Propose a different architectural approach rather than continuing to patch the current one. -4. If the environment constraints (e.g., single-process shell) fundamentally prevent success, explain the limitation clearly and terminate. ## New Applications