From c5d92a24ab79d823816156a85d7c2d468e6495fd Mon Sep 17 00:00:00 2001 From: jinliyl <6469360+jinliyl@users.noreply.github.com> Date: Thu, 6 Aug 2026 17:40:01 +0800 Subject: [PATCH] feat: weave dream wikilinks into contextual prose (#428) --- reme/steps/evolve/dream/integrate.yaml | 118 ++++++++++++++++--------- tests/unit/test_auto_dream.py | 16 ++++ 2 files changed, 91 insertions(+), 43 deletions(-) diff --git a/reme/steps/evolve/dream/integrate.yaml b/reme/steps/evolve/dream/integrate.yaml index 6b52cb46..25d66250 100644 --- a/reme/steps/evolve/dream/integrate.yaml +++ b/reme/steps/evolve/dream/integrate.yaml @@ -18,8 +18,8 @@ integrate_system_prompt_procedure: | genuinely needs more. - If the draft starts copying paragraphs or narrating the event, it belongs in the source material, not digest. - - The Sources section carries details: cite every relevant unit_paths entry - as `- [[]]`. + - The Sources section carries provenance: cite every relevant unit_paths + entry inside a complete sentence that explains what the material supports. - Digest-to-digest wikilinks carry the conceptual graph. ## Procedure Body Shape @@ -30,9 +30,10 @@ integrate_system_prompt_procedure: | - Steps: numbered or terse bullets; each step is verb-led. - Pre-conditions / inputs: short list, not prose. - Failure modes / caveats: brief. - - `## Sources`: at least one `- [[]]` item, and normally one - for every relevant path in unit_paths. Plain-prose provenance does NOT - count; only wikilinks survive future updates. + - `## Sources`: at least one sentence containing `[[]]`, and + normally one for every relevant path in unit_paths. A bare wikilink does + not count; every link must have surrounding prose that explains what the + source supports. ## Workflow @@ -60,12 +61,18 @@ integrate_system_prompt_procedure: | UPDATE. UPDATE must be additive: never remove existing wikilinks or source links. Default to weaving more, not less; this is the only chance to attach recalled related nodes. + 5. Before returning, read the target and rewrite any standalone relation + field or bare-link line into a contextual sentence. ## Wikilink Graph - - A `## Sources` section points from digest back to material with bare list - items such as `- [[daily//.md]]` and - `- [[resource/]]`. + - A `## Sources` section points from digest back to material. Each entry must + be a complete contextual sentence, for example `- This workflow was + observed in [[daily//.md|the session record]].` + - Never emit standalone relation fields or bare-link lines such as + `relates_to:: [[...]]`, `derived_from:: [[...]]`, or `- [[...]]`. + Digest links belong inside the sentence that explains the relationship; + source links belong inside the sentence that explains the evidence. - Procedure nodes may link to any digest bucket: `[[{digest_dir}/procedure/.md]]`, `[[{digest_dir}/personal/.md]]`, or @@ -98,7 +105,7 @@ integrate_system_prompt_procedure_zh: | - 正文短且抽象，通常 50-200 words；只有流程本身确实需要时才更长。 - 如果草稿开始复制段落或叙述事件，说明细节放错层了。 - - Sources 章节承载细节：用 `- [[]]` 引用 unit_paths 中每个相关来源。 + - Sources 章节承载 provenance：在完整句子中引用 unit_paths 中每个相关来源，并说明材料支持什么。 - Digest 之间的 wikilink 承载概念图。 ## Procedure 正文形态 @@ -109,8 +116,8 @@ integrate_system_prompt_procedure_zh: | - Steps：编号或短 bullet；每步以动词开头。 - Pre-conditions / inputs：短列表，不写长 prose。 - Failure modes / caveats：简短。 - - `## Sources`：至少一条 `- [[]]`，通常覆盖 unit_paths 中每个相关 path。 - 纯文本 provenance 不算；只有 wikilink 会在未来更新中保留下来。 + - `## Sources`：至少一个包含 `[[]]` 的完整句子，通常覆盖 unit_paths 中每个相关 path。 + 裸 Wikilink 不算；每个链接周围都必须有自然语言，说明该来源支持什么。 ## 工作流 @@ -129,11 +136,14 @@ integrate_system_prompt_procedure_zh: | `> note: contradicted by [[]] - ` 内联标注。 4. CREATE 和 UPDATE 都要把 related digest 节点织入正文 wikilink。UPDATE 必须只增不删：不要删除已有 wikilink 或来源链接。默认多织，而不是少织；这是挂接召回到的相关节点的唯一机会。 + 5. 返回前读取目标文件，把任何独立关系字段或裸链接行改写成有上下文的自然句子。 ## Wikilink 图 - - `## Sources` 章节用普通列表 Wikilink 从 digest 指回材料，例如 - `- [[daily//.md]]` 和 `- [[resource/]]`。 + - `## Sources` 章节从 digest 指回材料。每一项必须是有上下文的完整句子，例如 + `- 这一流程见于 [[daily//.md|该会话记录]]。` + - 禁止生成 `relates_to:: [[...]]`、`derived_from:: [[...]]` 或 `- [[...]]` 这类独立关系字段和裸链接行。 + Digest 链接必须融入解释关系的句子；来源链接必须融入解释证据的句子。 - Procedure 节点可以链接任意 digest bucket： `[[{digest_dir}/procedure/.md]]`、`[[{digest_dir}/personal/.md]]`、 `[[{digest_dir}/wiki/.md]]`。 @@ -166,8 +176,8 @@ integrate_system_prompt_personal: | - Body is short and operational, usually 50-200 words. - Do not narrate what the user said in detail; cite source material instead. - - The Sources section carries details: cite every relevant unit_paths entry - as `- [[]]`. + - The Sources section carries provenance: cite every relevant unit_paths + entry inside a complete sentence that explains what the material supports. - Digest-to-digest wikilinks carry the conceptual graph. ## Personal Body Shape @@ -180,9 +190,10 @@ integrate_system_prompt_personal: | - `How to apply:` contexts, tasks, boundaries, or exceptions. - Do not invent exceptions or soften a hard preference unless the source material explicitly supports that exception. - - `## Sources`: at least one `- [[]]` item, and normally one - for every relevant path in unit_paths. Plain-prose provenance does NOT - count; only wikilinks survive future updates. + - `## Sources`: at least one sentence containing `[[]]`, and + normally one for every relevant path in unit_paths. A bare wikilink does + not count; every link must have surrounding prose that explains what the + source supports. For preferences, prefer one node per preference rather than one large person node; that is the granularity downstream search will hit. @@ -213,12 +224,18 @@ integrate_system_prompt_personal: | UPDATE. UPDATE must be additive: never remove existing wikilinks or source links. Default to weaving more, not less; this is the only chance to attach recalled related nodes. + 5. Before returning, read the target and rewrite any standalone relation + field or bare-link line into a contextual sentence. ## Wikilink Graph - - A `## Sources` section points from digest back to material with bare list - items such as `- [[daily//.md]]` and - `- [[resource/]]`. + - A `## Sources` section points from digest back to material. Each entry must + be a complete contextual sentence, for example `- This preference was + observed in [[daily//.md|the session record]].` + - Never emit standalone relation fields or bare-link lines such as + `relates_to:: [[...]]`, `derived_from:: [[...]]`, or `- [[...]]`. + Digest links belong inside the sentence that explains the relationship; + source links belong inside the sentence that explains the evidence. - Personal nodes may link to any digest bucket: `[[{digest_dir}/personal/.md]]`, `[[{digest_dir}/procedure/.md]]`, or @@ -252,7 +269,7 @@ integrate_system_prompt_personal_zh: | - 正文短且可操作，通常 50-200 words。 - 不要详细复述用户说了什么；用来源材料承载细节。 - - Sources 章节承载细节：用 `- [[]]` 引用 unit_paths 中每个相关来源。 + - Sources 章节承载 provenance：在完整句子中引用 unit_paths 中每个相关来源，并说明材料支持什么。 - Digest 之间的 wikilink 承载概念图。 ## Personal 正文形态 @@ -263,8 +280,8 @@ integrate_system_prompt_personal_zh: | - `Why:` 原因或上下文，帮助未来判断边界情况。 - `How to apply:` 适用上下文、任务、边界或例外。 - 不要凭空添加例外，也不要软化明确偏好；只有来源材料明确支持时才写例外。 - - `## Sources`：至少一条 `- [[]]`，通常覆盖 unit_paths 中每个相关 path。 - 纯文本 provenance 不算；只有 wikilink 会在未来更新中保留下来。 + - `## Sources`：至少一个包含 `[[]]` 的完整句子，通常覆盖 unit_paths 中每个相关 path。 + 裸 Wikilink 不算；每个链接周围都必须有自然语言，说明该来源支持什么。 偏好类内容优先一条偏好一个 node，而不是一个人一个大 node；这是下游搜索更容易命中的粒度。 @@ -285,11 +302,14 @@ integrate_system_prompt_personal_zh: | `> note: contradicted by [[]] - ` 内联标注。 4. CREATE 和 UPDATE 都要把 related digest 节点织入正文 wikilink。UPDATE 必须只增不删：不要删除已有 wikilink 或来源链接。默认多织，而不是少织；这是挂接召回到的相关节点的唯一机会。 + 5. 返回前读取目标文件，把任何独立关系字段或裸链接行改写成有上下文的自然句子。 ## Wikilink 图 - - `## Sources` 章节用普通列表 Wikilink 从 digest 指回材料，例如 - `- [[daily//.md]]` 和 `- [[resource/]]`。 + - `## Sources` 章节从 digest 指回材料。每一项必须是有上下文的完整句子，例如 + `- 这一偏好见于 [[daily//.md|该会话记录]]。` + - 禁止生成 `relates_to:: [[...]]`、`derived_from:: [[...]]` 或 `- [[...]]` 这类独立关系字段和裸链接行。 + Digest 链接必须融入解释关系的句子；来源链接必须融入解释证据的句子。 - Personal 节点可以链接任意 digest bucket： `[[{digest_dir}/personal/.md]]`、`[[{digest_dir}/procedure/.md]]`、 `[[{digest_dir}/wiki/.md]]`。 @@ -325,8 +345,8 @@ integrate_system_prompt_wiki: | genuinely needs more. - If the draft starts copying paragraphs or narrating the event, it belongs in the source material, not digest. - - The Sources section carries details: cite every relevant unit_paths entry - as `- [[]]`. + - The Sources section carries provenance: cite every relevant unit_paths + entry inside a complete sentence that explains what the material supports. - Digest-to-digest wikilinks carry the conceptual graph. ## Wiki Body Shape @@ -337,9 +357,10 @@ integrate_system_prompt_wiki: | - Body: short paragraphs or tight bullets with properties, sub-claims, distinctions, and one-line examples. - Relations: weave related nodes into natural prose with ordinary wikilinks. - - `## Sources`: at least one `- [[]]` item, and normally one - for every relevant path in unit_paths. Plain-prose provenance does NOT - count; only wikilinks survive future updates. + - `## Sources`: at least one sentence containing `[[]]`, and + normally one for every relevant path in unit_paths. A bare wikilink does + not count; every link must have surrounding prose that explains what the + source supports. ## Workflow @@ -368,12 +389,18 @@ integrate_system_prompt_wiki: | UPDATE. UPDATE must be additive: never remove existing wikilinks or source links. Default to weaving more, not less; this is the only chance to attach recalled related nodes. + 5. Before returning, read the target and rewrite any standalone relation + field or bare-link line into a contextual sentence. ## Wikilink Graph - - A `## Sources` section points from digest back to material with bare list - items such as `- [[daily//.md]]` and - `- [[resource/]]`. + - A `## Sources` section points from digest back to material. Each entry must + be a complete contextual sentence, for example `- This claim is supported + by [[daily//.md|the session record]].` + - Never emit standalone relation fields or bare-link lines such as + `relates_to:: [[...]]`, `derived_from:: [[...]]`, or `- [[...]]`. + Digest links belong inside the sentence that explains the relationship; + source links belong inside the sentence that explains the evidence. - Wiki nodes may link to any digest bucket: `[[{digest_dir}/wiki/.md]]`, `[[{digest_dir}/procedure/.md]]`, or @@ -407,7 +434,7 @@ integrate_system_prompt_wiki_zh: | - 正文短且抽象，通常 50-200 words；只有概念本身确实需要时才更长。 - 如果草稿开始复制段落或叙述事件，说明细节放错层了。 - - Sources 章节承载细节：用 `- [[]]` 引用 unit_paths 中每个相关来源。 + - Sources 章节承载 provenance：在完整句子中引用 unit_paths 中每个相关来源，并说明材料支持什么。 - Digest 之间的 wikilink 承载概念图。 ## Wiki 正文形态 @@ -417,8 +444,8 @@ integrate_system_prompt_wiki_zh: | - First line：一句话定义或主张。 - Body：短段落或紧凑 bullets，写属性、子主张、区分和一行例子。 - Relations：在自然语言中用普通 Wikilink 织入相关节点。 - - `## Sources`：至少一条 `- [[]]`，通常覆盖 unit_paths 中每个相关 path。 - 纯文本 provenance 不算；只有 wikilink 会在未来更新中保留下来。 + - `## Sources`：至少一个包含 `[[]]` 的完整句子，通常覆盖 unit_paths 中每个相关 path。 + 裸 Wikilink 不算；每个链接周围都必须有自然语言，说明该来源支持什么。 ## 工作流 @@ -437,11 +464,14 @@ integrate_system_prompt_wiki_zh: | `> note: contradicted by [[]] - ` 内联标注。 4. CREATE 和 UPDATE 都要把 related digest 节点织入正文 wikilink。UPDATE 必须只增不删：不要删除已有 wikilink 或来源链接。默认多织，而不是少织；这是挂接召回到的相关节点的唯一机会。 + 5. 返回前读取目标文件，把任何独立关系字段或裸链接行改写成有上下文的自然句子。 ## Wikilink 图 - - `## Sources` 章节用普通列表 Wikilink 从 digest 指回材料，例如 - `- [[daily//.md]]` 和 `- [[resource/]]`。 + - `## Sources` 章节从 digest 指回材料。每一项必须是有上下文的完整句子，例如 + `- 这一主张由 [[daily//.md|该会话记录]] 支持。` + - 禁止生成 `relates_to:: [[...]]`、`derived_from:: [[...]]` 或 `- [[...]]` 这类独立关系字段和裸链接行。 + Digest 链接必须融入解释关系的句子；来源链接必须融入解释证据的句子。 - Wiki 节点可以链接任意 digest bucket： `[[{digest_dir}/wiki/.md]]`、`[[{digest_dir}/procedure/.md]]`、 `[[{digest_dir}/personal/.md]]`。 @@ -471,8 +501,9 @@ integrate_user_message: | {material_blob} Integrate this single unit into digest memory. Cite every relevant unit_paths - entry as `- [[]]` under `## Sources`, recall related digest nodes, and - weave useful digest wikilinks into the target node. + entry in a contextual sentence under `## Sources`, recall related digest + nodes, and weave useful digest wikilinks into natural body prose. Never emit + standalone relation fields or bare-link lines. integrate_user_message_zh: | 提示：{hint} @@ -488,5 +519,6 @@ integrate_user_message_zh: | {material_blob} - 将这个单独的 unit 整合进 digest memory。在 `## Sources` 下用 `- [[]]` 引用 unit_paths 中每个 - 相关来源，召回相关 digest 节点，并把有用的 digest wikilink 织入目标节点。 + 将这个单独的 unit 整合进 digest memory。在 `## Sources` 下用有上下文的完整句子引用 unit_paths 中每个 + 相关来源，召回相关 digest 节点，并把有用的 digest Wikilink 融入正文的自然表达。禁止生成独立关系字段 + 或裸链接行。 diff --git a/tests/unit/test_auto_dream.py b/tests/unit/test_auto_dream.py index 9577d999..9509d67d 100644 --- a/tests/unit/test_auto_dream.py +++ b/tests/unit/test_auto_dream.py @@ -156,6 +156,22 @@ def test_parse_structured_reply_handles_fenced_yaml_and_scalar_fallback(): assert data["note"].startswith("Extended node") +def test_integrate_prompts_require_wikilinks_in_contextual_prose(): + """Every digest bucket rejects standalone relation fields and bare links.""" + prompt_path = Path(__file__).parents[2] / "reme" / "steps" / "evolve" / "dream" / "integrate.yaml" + prompts = yaml.safe_load(prompt_path.read_text(encoding="utf-8")) + + for bucket in ("procedure", "personal", "wiki"): + english = prompts[f"integrate_system_prompt_{bucket}"] + chinese = prompts[f"integrate_system_prompt_{bucket}_zh"] + assert "Never emit standalone relation fields or bare-link lines" in english + assert "Digest links belong inside the sentence" in english + assert "Before returning, read the target" in english + assert "禁止生成 `relates_to:: [[...]]`" in chinese + assert "Digest 链接必须融入解释关系的句子" in chinese + assert "返回前读取目标文件" in chinese + + def test_extract_clean_output_respects_max_units(): """Extract cleaning caps valid units at max_units.""" state = DreamState(changed_paths=["daily/a.md"])