You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -154,6 +163,7 @@ Use the spawn_agents tool to spawn specialized agents to help you complete the u
154
163
'- Spawn context-gathering agents (file pickers, code searchers, and web/docs researchers) before making edits. Use the list_directory and glob tools directly for searching and exploring the codebase.',
155
164
isFree&&
156
165
'Do not spawn the thinker-gpt agent, unless the user asks. Not everyone has connected their ChatGPT subscription to Codebuff to allow for it.',
@@ -340,6 +352,7 @@ function buildImplementationInstructionsPrompt({
340
352
isDefault,
341
353
isMax,
342
354
isFree,
355
+
hasFreeGeminiThinker,
343
356
hasNoValidation,
344
357
noAskUser,
345
358
}: {
@@ -348,6 +361,7 @@ function buildImplementationInstructionsPrompt({
348
361
isDefault: boolean
349
362
isMax: boolean
350
363
isFree: boolean
364
+
hasFreeGeminiThinker: boolean
351
365
hasNoValidation: boolean
352
366
noAskUser: boolean
353
367
}){
@@ -365,6 +379,7 @@ ${buildArray(
365
379
'After getting context on the user request from the codebase or from research, use the ask_user tool to ask the user for important clarifications on their request or alternate implementation strategies. You should skip this step if the choice is obvious -- only ask the user if you need their help making the best choice.',
366
380
(isDefault||isMax||isFree)&&
367
381
`- For any task requiring 3+ steps, use the write_todos tool to write out your step-by-step implementation plan. Include ALL of the applicable tasks in the list.${isFast ? '' : ' You should include a step to review the changes after you have implemented the changes.'}:${hasNoValidation ? '' : ' You should include at least one step to validate/test your changes: be specific about whether to typecheck, run tests, run lints, etc.'} You may be able to do reviewing and validation in parallel in the same step. Skip write_todos for simple tasks like quick edits or answering questions.`,
`- For quick problems, briefly explain your reasoning to the user. If you need to think longer, write your thoughts within the <think> tags. Finally, for complex problems, spawn the thinker agent to help find the best solution. (gpt-5-agent is a last resort for complex problems)`,
370
385
isDefault&&
@@ -395,6 +410,7 @@ function buildImplementationStepPrompt({
395
410
hasNoValidation,
396
411
isSonnet,
397
412
isFree,
413
+
hasFreeGeminiThinker,
398
414
noAskUser,
399
415
}: {
400
416
isDefault: boolean
@@ -403,12 +419,14 @@ function buildImplementationStepPrompt({
403
419
hasNoValidation: boolean
404
420
isSonnet: boolean
405
421
isFree: boolean
422
+
hasFreeGeminiThinker: boolean
406
423
noAskUser: boolean
407
424
}){
408
425
returnbuildArray(
409
426
isMax&&
410
427
`Keep working until the user's request is completely satisfied${!hasNoValidation ? ' and validated' : ''}, or until you require more information from the user.`,
411
428
'Consider loading relevant skills with the skill tool if they might help with the current task. Do not reload skills that were already loaded earlier in this conversation.',
`You must spawn the 'editor-multi-prompt' agent to implement code changes rather than using the str_replace or write_file tools, since it will generate the best code changes.`,
0 commit comments