adeelahmad · Oct 17, 2026 · Oct 16, 2026 · Oct 17, 2026 · Oct 17, 2026 · Oct 17, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,14 @@ The backend (`fastapi_backend`) and the frontend (`nextjs-frontend`) are version
 
 ## Unreleased
 
+- **Export a conversation.** `GET /api/v1/chats/<id>/export.md`, `.pdf` or `.json` gives the version showing, one
+  message (`?message=`) or, as JSON, every version (`?all=true`). The Markdown has each question and answer, its
+  citations as footnotes linking back to the moment in Lens and the tools it used; the PDF is that Markdown printed by
+  Chromium, else anytopdf, else LibreOffice (409 when none can run); the JSON is OpenAI's chat message format in a tree
+  with Dublin Core terms, or `?format=messages` for one `{"messages": [...]}` line, checked against a published schema.
+  Agents use `list_chats`, `read_chat` and `export_chat` over MCP. The web app's copy and export buttons are in
+  progress ([Copy and export](docs/assistant.md#copy-and-export)).
+
 ## 0.14.0 <small>October 17, 2026</small> {id="0.14.0"}
 
 - **Dates read as days, for agents.** With Settings → Analysis → Read dates on (off by default), analysis reads the

diff --git a/docs/assistant.md b/docs/assistant.md
@@ -95,6 +95,64 @@ An app's chat completions keep no messages, so their record comes back in the re
 cost ([Chat completions](api.md#chat-completions-for-any-app)). Answers from before Lens kept records have none; Details
 shows what they have and says the rest wasn't recorded.
 
+### Copy and export
+
+A conversation, or one message of it, comes out as a file to keep or hand on: `GET
+/api/v1/chats/<id>/export.md`, `export.pdf` or `export.json`. They hold the version showing; `?message=<mid>` holds
+one message (an answer comes with the question it answers), and the JSON export's `?all=true` holds every version.
+Citations follow the reader's access now, as `GET /api/v1/chats/<id>` does, and no model is called.
+
+- **Markdown:** the title, a short header (the conversation's address in Lens, when it started, what it draws on in
+  words, and the Lens version that exported it), then each question and answer with its time, the model that wrote
+  it and its version (version 2 of 3). An answer's citations become numbered footnotes naming the asset, its time or
+  page and speaker, a short quote and a link back to that moment in Lens; a web page's citation links the page. The
+  tools an answer used are a "Looked up" list with each one's summary.
+- **PDF:** that Markdown on a page, printed by Chromium where it's installed, else by anytopdf (installed, on a
+  conversion node, or fetched on first use, [anytopdf](configuration.md#anytopdf)), else by LibreOffice. When none
+  can run here (Settings › Documents says never to use anytopdf, and nothing else is installed), or printing fails,
+  it answers 409 with the reason; the web app can still print the conversation.
+- **JSON:** the conversation in OpenAI's chat message format, as other tools and trainers read it, with Dublin Core
+  terms (`dc:title`, `dc:created`, `dc:modified`, `dc:creator`, `dc:identifier`, `dc:publisher`). `mapping` holds each
+  message by id with its `parent` and `children` (more than one child where there are versions), and `current_node`
+  is the last message of the version showing. Each node's `message` is `{role, content}`; an answer that used tools
+  has them before it in `tool_messages`: an assistant message with `tool_calls`, then a `tool` message per call
+  carrying the step's summary. What only Lens knows is under `lens`: the citations (`[n]` in the text is `n` there,
+  with a `url` back to Lens or the web page), the answer's record (`meta`, [above](#what-each-answer-records)),
+  `versions`, attached files, and the page a question was asked from. `?format=messages` gives the version showing
+  as one `{"messages": [...]}` line instead, the shape fine-tuning reads. The schema is
+  [chat-export.schema.json](schemas/chat-export.schema.json).
+
+```json
+{
+  "@context": {"dc": "http://purl.org/dc/terms/"},
+  "format": "lens.chat-export/1",
+  "dc:title": "Are ships slow?",
+  "dc:identifier": "https://lens.example/chat/4",
+  "current_node": "2",
+  "mapping": {
+    "1": {"id": "1", "parent": null, "children": ["2"], "message": {"role": "user", "content": "Are ships slow?"}, "lens": {}},
+    "2": {
+      "id": "2", "parent": "1", "children": [],
+      "tool_messages": [
+        {"role": "assistant", "content": null, "tool_calls": [{"id": "call_2_1", "type": "function",
+          "function": {"name": "search_transcripts", "arguments": "{\"query\": \"ships\"}"}}]},
+        {"role": "tool", "tool_call_id": "call_2_1", "content": "2 moments"}
+      ],
+      "message": {"role": "assistant", "content": "Yes, said Ana [1]."},
+      "lens": {"citations": [{"n": 1, "source": "said", "recording_id": 5, "title": "Ep 1", "time": "1:15",
+        "speaker": "Ana", "text": "They are slow.", "url": "https://lens.example/resources/5?t=75"}]}
+    }
+  }
+}
+```
+
+Exports carry each tool call's arguments and summary, never its raw result, which Lens doesn't keep. Agents read and
+export the same way over MCP: `list_chats`, `read_chat` and `export_chat` ([MCP](mcp.md)) work on the person's own
+conversations.
+
+The web app's copy buttons and Export menus are in progress. Planned: importing a conversation from its JSON,
+exporting one to a note, and a styled PDF without Chromium.
+
 ### Picking the namespace for a conversation over everything
 
 When a conversation has no scope (the assistant home starts it over everything), its first question goes to the

diff --git a/docs/mcp.md b/docs/mcp.md
@@ -46,8 +46,8 @@ that should see that namespace and nothing else: a family assistant, a project's
 has the same tools, but sees only that namespace, whatever else the person who signs the agent in can read. Tools
 that take a namespace use this one when none is named, `list_namespaces` and `list_files` show only it, and the tools
 about the server itself (`file_storage`, `monitoring`, `sandbox_gateway`, `install_settings` and the ones that change
-them) aren't there,
-even for admins. An admin counts as an owner of the namespace there.
+them) aren't there, even for admins. Nor are the person's own conversations (`list_chats`, `read_chat`,
+`export_chat`), which belong to no namespace. An admin counts as an owner of the namespace there.
 
 It is off until an owner of the namespace turns it on: **Admin → Namespaces →** the namespace **→ Connect apps**, which
 also copies its address, or `PATCH /api/v1/namespaces/<namespace>/integrations` with `{"mcp": true}`, or an agent's
@@ -94,6 +94,9 @@ For an app that speaks OpenAI's API rather than MCP, the namespace can also answ
 | `find_notes` | [notes](notes.md) by words in their title, summary or text, or by where they're filed (PARA), with the words around the match and links |
 | `read_note` | a note's Markdown with its links and backlinks, by id or as the page of a thing (`recording:12`) |
 | `write_note` | write a note or a thing's page, marked as written by an assistant. Needs a write-scope token and editor access |
+| `list_chats` | the person's conversations with Lens's [assistant](assistant.md#chat), newest first, by words in their title, each with its link |
+| `read_chat` | one of them: what it draws on, and the version showing (or the one ending at a `message`), each message with its versions, the tools an answer used, its citations with links and its record; `tree` adds every message's parent and role |
+| `export_chat` | one of them as Markdown or JSON ([Copy and export](assistant.md#copy-and-export)): the version showing, one `message`, every version (`all_versions`) or OpenAI's `{"messages": [...]}` shape (`as_messages`) |
 | `create_podcast` | make a two-host learning [episode](podcasts.md) about assets or lines in them, with an angle, a length and a style; it's made in the background. Needs a write-scope token and editor access where it goes |
 | `get_podcast` | an episode: how far it has got, its script with each line's speaker and the sources it cites (links), and what the fact-check changed |
 | `nsfw_settings` | how [NSFW classification](nsfw.md) works in a namespace: on or off, the threshold, how flagged resources show, and how many are classified, flagged and not classified yet |

diff --git a/docs/schemas/chat-export.schema.json b/docs/schemas/chat-export.schema.json
@@ -0,0 +1,145 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://github.com/adeelahmad/lense/blob/main/docs/schemas/chat-export.schema.json",
+  "title": "Lens conversation export",
+  "description": "GET /api/v1/chats/{id}/export.json (docs/assistant.md, Copy and export): a conversation as a tree of OpenAI chat messages with Dublin Core terms, or with format=messages one version as {\"messages\": [...]}.",
+  "oneOf": [{ "$ref": "#/$defs/document" }, { "$ref": "#/$defs/messages" }],
+  "$defs": {
+    "document": {
+      "type": "object",
+      "required": ["@context", "format", "dc:title", "dc:identifier", "dc:format", "id", "title", "current_node", "mapping"],
+      "properties": {
+        "@context": {
+          "type": "object",
+          "required": ["dc"],
+          "properties": { "dc": { "const": "http://purl.org/dc/terms/" } }
+        },
+        "format": { "const": "lens.chat-export/1" },
+        "dc:title": { "type": "string" },
+        "dc:created": { "type": ["string", "null"], "description": "when the conversation started (ISO 8601, UTC)" },
+        "dc:modified": { "type": ["string", "null"], "description": "when it was last added to" },
+        "dc:creator": { "type": "string", "description": "the person whose conversation it is" },
+        "dc:identifier": { "type": "string", "description": "its address in Lens" },
+        "dc:format": { "const": "application/json" },
+        "dc:publisher": { "type": "string", "description": "the Lens and version that exported it" },
+        "id": { "type": "string" },
+        "title": { "type": "string" },
+        "scope": { "type": "object", "description": "what the conversation draws on (namespaces, recordings, collections, speakers, from, to)" },
+        "model": { "type": ["string", "null"], "description": "the model picked for it; null: the configured one" },
+        "exported_at": { "type": "string" },
+        "current_node": { "type": ["string", "null"], "description": "the last message of the version showing" },
+        "mapping": {
+          "type": "object",
+          "additionalProperties": { "$ref": "#/$defs/node" }
+        }
+      }
+    },
+    "node": {
+      "type": "object",
+      "required": ["id", "parent", "children", "message", "lens"],
+      "properties": {
+        "id": { "type": "string" },
+        "parent": { "type": ["string", "null"], "description": "the message it follows, among those exported" },
+        "children": { "type": "array", "items": { "type": "string" }, "description": "the messages that follow it: more than one where there are versions" },
+        "created_at": { "type": ["string", "null"] },
+        "message": { "$ref": "#/$defs/chatMessage" },
+        "tool_messages": {
+          "type": "array",
+          "description": "an answer's tool calls, before it: an assistant message calling them, then a tool message for each carrying its summary (raw results aren't kept)",
+          "items": { "$ref": "#/$defs/openaiMessage" }
+        },
+        "lens": { "$ref": "#/$defs/lens" }
+      }
+    },
+    "chatMessage": {
+      "type": "object",
+      "required": ["role", "content"],
+      "properties": {
+        "role": { "enum": ["user", "assistant"] },
+        "content": { "type": "string", "description": "the text; an answer cites with [n], the n of lens.citations" }
+      }
+    },
+    "openaiMessage": {
+      "type": "object",
+      "required": ["role"],
+      "properties": {
+        "role": { "enum": ["system", "user", "assistant", "tool"] },
+        "content": { "type": ["string", "null"] },
+        "tool_call_id": { "type": "string" },
+        "tool_calls": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "required": ["id", "type", "function"],
+            "properties": {
+              "id": { "type": "string" },
+              "type": { "const": "function" },
+              "function": {
+                "type": "object",
+                "required": ["name", "arguments"],
+                "properties": {
+                  "name": { "type": "string" },
+                  "arguments": { "type": "string", "description": "the arguments, as JSON text" }
+                }
+              }
+            }
+          }
+        }
+      },
+      "allOf": [
+        { "if": { "properties": { "role": { "const": "tool" } } }, "then": { "required": ["tool_call_id", "content"] } }
+      ]
+    },
+    "citation": {
+      "type": "object",
+      "required": ["n", "source", "text"],
+      "properties": {
+        "n": { "type": "integer" },
+        "source": { "enum": ["said", "page", "screen", "memory", "web"], "description": "where it is: said in a recording, on a document's page, shown on screen, from memory, or a web page" },
+        "url": { "type": ["string", "null"], "description": "the web page, or the asset's page in Lens at that moment" },
+        "recording_id": { "type": "integer" },
+        "title": { "type": ["string", "null"] },
+        "namespace": { "type": ["string", "null"] },
+        "recorded_at": { "type": ["string", "null"] },
+        "time": { "type": ["string", "null"] },
+        "page": { "type": ["integer", "null"] },
+        "speaker": { "type": ["string", "null"] },
+        "site": { "type": ["string", "null"] },
+        "fetched_at": { "type": ["string", "null"] },
+        "text": { "type": "string" },
+        "used": { "type": ["boolean", "null"], "description": "cited in the answer" }
+      }
+    },
+    "lens": {
+      "type": "object",
+      "description": "what only Lens knows of a message",
+      "properties"
92CB
: {
+        "model": { "type": "string" },
+        "stopped": { "type": "boolean" },
+        "notice": { "type": "string" },
+        "error": { "type": "string" },
+        "check": { "type": "object" },
+        "context": { "type": "object", "description": "a question asked from a page: the page and any highlighted text" },
+        "versions": {
+          "type": "object",
+          "required": ["index", "count", "ids"],
+          "properties": { "index": { "type": "integer" }, "count": { "type": "integer" }, "ids": { "type": "array", "items": { "type": "integer" } } }
+        },
+        "attachments": {
+          "type": "array",
+          "items": { "type": "object", "properties": { "filename": { "type": "string" }, "size": { "type": "integer" }, "recording": { "type": "integer" } } }
+        },
+        "citations": { "type": "array", "items": { "$ref": "#/$defs/citation" } },
+        "meta": { "type": "object", "description": "what produced it (GET /chats/{cid}/messages/{mid} meta): model, provider, tools, scope, limits, use, outcome, tokens, cost, time" }
+      }
+    },
+    "messages": {
+      "type": "object",
+      "required": ["messages"],
+      "additionalProperties": false,
+      "properties": {
+        "messages": { "type": "array", "items": { "$ref": "#/$defs/openaiMessage" } }
+      }
+    }
+  }
+}