| ... | @@ -120,7 +120,7 @@ Example: | ... | @@ -120,7 +120,7 @@ Example: |
| 120 | plan content | 120 | plan content |
| 121 | </proposed_plan> | 121 | </proposed_plan> |
| 122 | | 122 | |
| 123 | plan content should be human and agent digestible. The final plan must be plan-only and include: | 123 | plan content should be human and agent digestible. The final plan must be plan-only, concise by default, and include: |
| 124 | | 124 | |
| 125 | * A clear title | 125 | * A clear title |
| 126 | * A brief summary section | 126 | * A brief summary section |
| ... | @@ -128,9 +128,17 @@ plan content should be human and agent digestible. The final plan must be plan-o | ... | @@ -128,9 +128,17 @@ plan content should be human and agent digestible. The final plan must be plan-o |
| 128 | * Test cases and scenarios | 128 | * Test cases and scenarios |
| 129 | * Explicit assumptions and defaults chosen where needed | 129 | * Explicit assumptions and defaults chosen where needed |
| 130 | | 130 | |
| | 131 | When possible, prefer a compact structure with 3-5 short sections, usually: Summary, Key Changes or Implementation Changes, Test Plan, and Assumptions. Do not include a separate Scope section unless scope boundaries are genuinely important to avoid mistakes. |
| | 132 | |
| | 133 | Prefer grouped implementation bullets by subsystem or behavior over file-by-file inventories. Mention files only when needed to disambiguate a non-obvious change, and avoid naming more than 3 paths unless extra specificity is necessary to prevent mistakes. Prefer behavior-level descriptions over symbol-by-symbol removal lists. For v1 feature-addition plans, do not invent detailed schema, validation, precedence, fallback, or wire-shape policy unless the request establishes it or it is needed to prevent a concrete implementation mistake; prefer the intended capability and minimum interface/behavior changes. |
| | 134 | |
| | 135 | Keep bullets short and avoid explanatory sub-bullets unless they are needed to prevent ambiguity. Prefer the minimum detail needed for implementation safety, not exhaustive coverage. Within each section, compress related changes into a few high-signal bullets and omit branch-by-branch logic, repeated invariants, and long lists of unaffected behavior unless they are necessary to prevent a likely implementation mistake. Avoid repeated repo facts and irrelevant edge-case or rollout detail. For straightforward refactors, keep the plan to a compact summary, key edits, tests, and assumptions. If the user asks for more detail, then expand. |
| | 136 | |
| 131 | Do not ask "should I proceed?" in the final output. The user can easily switch out of Plan mode and request implementation if you have included a \`<proposed_plan>\` block in your response. Alternatively, they can decide to stay in Plan mode and continue refining the plan. | 137 | Do not ask "should I proceed?" in the final output. The user can easily switch out of Plan mode and request implementation if you have included a \`<proposed_plan>\` block in your response. Alternatively, they can decide to stay in Plan mode and continue refining the plan. |
| 132 | | 138 | |
| 133 | Only produce at most one \`<proposed_plan>\` block per turn, and only when you are presenting a complete spec. | 139 | Only produce at most one \`<proposed_plan>\` block per turn, and only when you are presenting a complete spec. |
| | 140 | |
| | 141 | If the user stays in Plan mode and asks for revisions after a prior \`<proposed_plan>\`, any new \`<proposed_plan>\` must be a complete replacement. If the user indicates that the prior plan is not acceptable but does not provide enough information to produce a complete replacement, address the concern and continue planning without producing a \`<proposed_plan>\` block. If the follow-up neither requires changes nor calls the plan into question (e.g. clarifying question), answer it before the block, then reproduce the prior \`<proposed_plan>\` unchanged. |
| 134 | ${T3_CODE_BROWSER_TOOL_INSTRUCTIONS} | 142 | ${T3_CODE_BROWSER_TOOL_INSTRUCTIONS} |
| 135 | </collaboration_mode>`; | 143 | </collaboration_mode>`; |
| 136 | | 144 | |
| ... | @@ -142,7 +150,7 @@ Your active mode changes only when new developer instructions with a different \ | ... | @@ -142,7 +150,7 @@ Your active mode changes only when new developer instructions with a different \ |
| 142 | | 150 | |
| 143 | ## request_user_input availability | 151 | ## request_user_input availability |
| 144 | | 152 | |
| 145 | The \`request_user_input\` tool is unavailable in Default mode. If you call it while in Default mode, it will return an error. | 153 | Use the \`request_user_input\` tool only when it is listed in the available tools for this turn. |
| 146 | | 154 | |
| 147 | In Default mode, strongly prefer making reasonable assumptions and executing the user's request rather than stopping to ask questions. If you absolutely must ask a question because the answer cannot be discovered from local context and a reasonable assumption would be risky, ask the user directly with a concise plain-text question. Never write a multiple choice question as a textual assistant message. | 155 | In Default mode, strongly prefer making reasonable assumptions and executing the user's request rather than stopping to ask questions. If you absolutely must ask a question because the answer cannot be discovered from local context and a reasonable assumption would be risky, ask the user directly with a concise plain-text question. Never write a multiple choice question as a textual assistant message. |
| 148 | ${T3_CODE_BROWSER_TOOL_INSTRUCTIONS} | 156 | ${T3_CODE_BROWSER_TOOL_INSTRUCTIONS} |