@llamaventures/cli 1.17.3 → 1.18.1

package/AGENT_BRIEFING.md

@@ -29,6 +29,7 @@ This npm package is public, but Llama OS skills are private. Do not assume the s
 - Use `llama agent-onboard` or MCP `agent_briefing` for the server-owned Agent Runtime Contract. The npm-bundled text is fallback only.
 - Use `llama skills search "<task>"` or MCP `skills_search` before choosing a Llama workflow.
 - Use `llama skills show <slug>` or MCP `skills_read` only for the relevant skill.
+- Use `llama activity new-deals|updated-deals` or MCP `activity_query` before scanning raw deal timelines for recent portfolio movement.
 - Use `llama explain <command-url-or-object>` or MCP `object_inspect` for 404s, deleted wiki pages, notifier links, deal URLs, and unknown Command objects before telling the user "the system is broken."
 
 The boundary matters: public CLI/MCP discovers skills, but authenticated Command decides which skill content the token may read.
@@ -44,6 +45,7 @@ Any time the user mentions a company name or founder name:
    - Use `--status Outreached` when we only contacted/logged the company and have no response or effective relationship yet.
    - Use `--status Sourced` only once there is a response, intro, meeting, or another real relationship signal.
    - Also set `--source-direction Inbound` if the deal came into the firm; set `--source-direction Outbound` if Llama found/listed/reached out first.
+   - If assigning an owner at create time, use `--deal-owner` with an exact `/api/field-options` value, email, or user id. Do not guess from a first name.
 4. If user gives you new facts (status / valuation / founder note) → `llama deal update` immediately, tell the user **one line** afterward.
 
 Don't:
@@ -61,7 +63,7 @@ A teammate says "I just met them and heard…" or pastes a chunk of notes. Your
 
 1. **Find the deal** — `llama deal search "<name>"` (Pipeline First). New name → offer to create it.
 2. **Split what they gave you into two kinds** — this is the whole data model:
-   - **Verifiable claims → facts.** `llama deal fact add <dealId> --category <cat> --claim "…" --source "<where it came from>"`. A claim someone *relayed* ("their ARR is $3M", "raised from a16z") is a fact at **unverified** trust — it's hearsay until checked. Pass `--attested` ONLY if you actually verified it against a source yourself.
+   - **Verifiable claims → facts.** `llama deal fact add <dealId> --category <cat> --claim "…" --source "<where it came from>" --source-url <url>`. A claim someone *relayed* ("their ARR is $3M", "raised from a16z") is a fact at **unverified** trust — it's hearsay until checked. Pass `--attested` ONLY if you actually verified it against a source yourself. In raw API terms, the fact text field is `claim` (`value` is only a compatibility alias), `source` is the human-readable provenance label, and `sourceUrl` is the canonical URL.
    - **Their judgment / impression → a note.** `llama post <dealId> "…"`. "Founder seemed evasive", "I'd lean pass", "worth a second meeting" — opinion, not fact. Attributed, never "verified".
    - A pasted blob → pull the verifiable claims out as facts, capture their take as a note.
 3. **Read it back before you claim it's saved.** A tool call returning `{ok:true}` is NOT proof the content is where the user will look for it. After filing, run `llama deal feed <dealId>` and confirm your fact/note actually appears, THEN tell the user in plain language what you recorded and where. Never say "记好了 / saved" from the return value alone — the #1 failure is an agent writing to the wrong surface (e.g. the brief, which is the Memo and does NOT appear in the feed) and reporting success anyway. If it's not in the feed, you routed it wrong — fix it.
@@ -128,7 +130,7 @@ These three look similar but land in different surfaces. Don't infer from the co
 
 | You want to… | Command | Lands in |
 |---|---|---|
-| Record a **sourced, verifiable fact** | `llama deal fact add <dealId> --category <cat> --claim "…" --source <url>` | Facts → deal **Feed** (FACT card) + citable in the **Memo** |
+| Record a **sourced, verifiable fact** | `llama deal fact add <dealId> --category <cat> --claim "…" --source "deck p3" --source-url <url>` | Facts → deal **Feed** (FACT card) + citable in the **Memo** |
 | Leave a **comment / opinion / question / reaction** for the team | `llama post <dealId> "…"` (`@name` to notify) | Posts → deal **Feed** (POST card); `@mention` fires email + UI badge |
 | Write **narrative that belongs in the IC memo** | `llama brief add-text <dealId> --heading "…" --body "…"` | Brief blocks → **Memo tab only — NOT in the Feed** |
 
@@ -208,8 +210,8 @@ llama deal list [--owner ...] [--status ...]
 
 # Pipeline — write
 llama deal create "Company" --description "..." --source-direction Outbound --status Interested
-llama deal create "Company" --description "..." --source-direction Outbound --status Outreached
-llama deal create "Company" --description "..." --source-direction Inbound --status Sourced
+llama deal create "Company" --description "..." --source-direction Outbound --status Outreached --deal-owner "owner@llamaventures.vc"
+llama deal create "Company" --description "..." --source-direction Inbound --status Sourced --deal-owner "Exact Name"
 llama deal update <dealId> <field> <value>
 #   writable: status theirStage stage notes dealOwner source sourceDirection description website
 #             location founders proposedAmount roundSize valuation sector subsector
@@ -296,7 +298,7 @@ Run `llama --help` for the full surface (~40 commands).
 
 ## MCP-native agents
 
-If you support [MCP](https://modelcontextprotocol.io), **prefer the MCP server over parsing CLI output.** The same package ships `llama-mcp` (56 typed tools, identical auth chain).
+If you support [MCP](https://modelcontextprotocol.io), **prefer the MCP server over parsing CLI output.** The same package ships `llama-mcp` (59 typed tools, identical auth chain).
 
 Add to your MCP client config (Claude Desktop / Claude Code / Cursor / OpenClaw / Codex / etc.):
 
@@ -309,6 +311,7 @@ Tools available:
 - `auth_status` — verify creds + identity (call first if anything 401s)
 - `agent_bootstrap` — fetch the live Command + Llama OS runtime manifest
 - `skills_search` / `skills_read` — discover and read authenticated runtime skills
+- `activity_query` — query new deals and meaningful updates without scanning raw timelines
 - `object_inspect` — explain Command URLs, 404s, deleted objects, and lifecycle trail
 - `deal_search` / `deal_show` / `deal_create` / `deal_update`
 - `brief_blocks` / `brief_add_text` / `brief_add_link` / `brief_add_callout`

package/CHANGELOG.md

@@ -6,6 +6,22 @@ this project adheres to [Semantic Versioning](https://semver.org).
 
 ## [Unreleased]
 
+## [1.18.1] - 2026-07-09
+
+### Changed
+- Clarified the Command facts write contract across CLI, MCP, and agent docs:
+  `claim` is canonical, `value` remains a compatibility alias, `sourceUrl`
+  round-trips as provenance, and categories are free text. `deal create` now
+  forwards `--deal-owner` using name, email, or user id.
+
+## [1.18.0] - 2026-07-06
+
+### Added
+- `llama activity new-deals|updated-deals|events` plus MCP `activity_query`
+  for agent-friendly reads over Command's curated activity projection. Agents
+  can ask for recent deal creations or meaningful deal updates without scanning
+  raw timelines or event-bus payloads.
+
 ## [1.17.3] - 2026-07-01
 
 ### Changed
@@ -492,7 +508,11 @@ assistant-drafted (🤖) and enforces the AI trust ceiling.
 
 ---
 
-[Unreleased]: https://github.com/Llama-Ventures/llama-cli/compare/v1.17.1...HEAD
+[Unreleased]: https://github.com/Llama-Ventures/llama-cli/compare/v1.18.1...HEAD
+[1.18.1]: https://github.com/Llama-Ventures/llama-cli/compare/v1.18.0...v1.18.1
+[1.18.0]: https://github.com/Llama-Ventures/llama-cli/compare/v1.17.3...v1.18.0
+[1.17.3]: https://github.com/Llama-Ventures/llama-cli/compare/v1.17.2...v1.17.3
+[1.17.2]: https://github.com/Llama-Ventures/llama-cli/compare/v1.17.1...v1.17.2
 [1.17.1]: https://github.com/Llama-Ventures/llama-cli/compare/v1.17.0...v1.17.1
 [1.17.0]: https://github.com/Llama-Ventures/llama-cli/compare/v1.16.0...v1.17.0
 [1.16.0]: https://github.com/Llama-Ventures/llama-cli/compare/v1.15.1...v1.16.0

package/README.md

@@ -7,7 +7,7 @@
 <p align="center">
   <strong>The Llama Ventures CLI &amp; MCP server.</strong><br/>
   One package, two binaries: <code>llama</code> — the CLI for humans and scripts —
-  and <code>llama-mcp</code> — a stdio MCP server with 58 typed tools for any
+  and <code>llama-mcp</code> — a stdio MCP server with 59 typed tools for any
   MCP-native agent. Both share the same auth chain, HTTP client, and error
   format, and talk to <a href="https://command.llamaventures.vc">command.llamaventures.vc</a>.
 </p>
@@ -94,7 +94,10 @@ schema forward-compatibility. Prefer it even from scripts.
 llama deal search "acme ai"            # find deals (deal list takes the same filters)
 llama deal show <dealId>
 llama deal feed <dealId>               # every contribution, newest first
-llama deal create "Acme AI" --source alex --source-direction Outbound --status Interested
+llama activity new-deals --since 24h   # recent deal creations
+llama activity updated-deals --since 7d # meaningful updates grouped by deal
+llama deal create "Acme AI" --source alex --deal-owner owner@llamaventures.vc --source-direction Outbound --status Interested
+llama deal fact add <dealId> --category funding --claim "Raised a seed round" --source "deck p3" --source-url https://...
 llama deal update <dealId> status Diligence
 llama post <dealId> "note body"
 llama brief add-text <dealId> --heading "..." --body "..."
@@ -109,6 +112,11 @@ Status vocabulary — `Interested`: tracked before any contact ·
 signal exists. `sourceDirection` is separate: `Inbound` came to the firm,
 `Outbound` we reached out first.
 
+Facts use `claim` for the fact text. `source` is a readable provenance label
+and `sourceUrl` is the canonical evidence URL; both round-trip from the API.
+For deal owners, use an exact `/api/field-options` `dealOwner` value, a user
+email, or a numeric user id.
+
 Run `llama --help` for the group index, `llama help all` for the full
 reference (100+ commands). Deletes are soft and audit-logged everywhere.
 
@@ -125,7 +133,7 @@ Authenticated calls send bounded, content-redacted telemetry to Command;
 
 ## MCP server
 
-`llama-mcp` is a stdio Model Context Protocol server exposing 58 typed tools
+`llama-mcp` is a stdio Model Context Protocol server exposing 59 typed tools
 that mirror the most-used CLI surface. Every tool is named and scoped — there
 is deliberately no generic API passthrough. Auth is identical to the CLI's
 chain. For the exact live list, pipe `tools/list` through it:

package/README.zh-CN.md

@@ -7,7 +7,7 @@
 <p align="center">
   <strong>Llama Ventures 的 CLI 与 MCP server。</strong><br/>
   一个包、两个可执行文件：<code>llama</code>——给人和脚本用的 CLI；
-  <code>llama-mcp</code>——带 58 个类型化工具的 stdio MCP server，任何
+  <code>llama-mcp</code>——带 59 个类型化工具的 stdio MCP server，任何
   MCP 原生 agent 都能接。两者共享同一认证链、同一 HTTP 客户端、同一错误格式，
   连接 <a href="https://command.llamaventures.vc">command.llamaventures.vc</a>。
 </p>
@@ -116,7 +116,10 @@ CLI 是 canonical 接口——认证、错误格式、schema 前向兼容都由
 llama deal search "acme ai"            # 找 deal（deal list 用同一套过滤参数）
 llama deal show <dealId>
 llama deal feed <dealId>               # 该 deal 的全部贡献，最新在前
-llama deal create "Acme AI" --source alex --source-direction Outbound --status Interested
+llama activity new-deals --since 24h   # 最近新建的 deal
+llama activity updated-deals --since 7d # 按 deal 聚合的实质更新
+llama deal create "Acme AI" --source alex --deal-owner owner@llamaventures.vc --source-direction Outbound --status Interested
+llama deal fact add <dealId> --category funding --claim "Raised a seed round" --source "deck p3" --source-url https://...
 llama deal update <dealId> status Diligence
 llama post <dealId> "备注内容"
 llama brief add-text <dealId> --heading "..." --body "..."
@@ -130,6 +133,10 @@ Status 语义——`Interested`：接触前先记录关注 · `Outreached`：已
 尚无回应 · `Sourced`：已有真实关系信号。`sourceDirection` 是独立维度：
 `Inbound` 流入，`Outbound` 我们主动。
 
+Facts 的正文用 `claim`。`source` 是人可读来源标签，`sourceUrl` 是 canonical
+证据 URL；两者都会从 API 回显。`dealOwner` 请用 `/api/field-options`
+里的精确 `dealOwner` 值、用户邮箱，或数字 user id。
+
 `llama --help` 看分组索引，`llama help all` 看全部 100+ 命令。
 所有删除默认软删除、有审计记录。
 
@@ -145,7 +152,7 @@ MCP server 在 `isError: true` 内容里返回相同前缀。认证请求会向
 
 ## MCP server
 
-`llama-mcp` 是 stdio MCP server，58 个类型化工具镜像 CLI 最常用的命令面。
+`llama-mcp` 是 stdio MCP server，59 个类型化工具镜像 CLI 最常用的命令面。
 每个工具具名、有边界——**故意不提供**通用 API passthrough。认证链与 CLI
 完全一致。精确工具清单以 `tools/list` 为准：
 

package/bin/llama-mcp.mjs

@@ -349,6 +349,41 @@ server.registerTool(
   }
 );
 
+server.registerTool(
+  "activity_query",
+  {
+    description:
+      "Read Command's curated agent activity projection. Use this before " +
+      "scanning raw timelines or event-bus payloads. Examples: new deals in " +
+      "the past 24h, deals with meaningful updates in the past 7d, or recent " +
+      "fact/memo/brief events. Returns source ids so callers can drill down.",
+    inputSchema: {
+      kind: z
+        .enum(["events", "new_deals", "updated_deals"])
+        .default("events")
+        .describe("events = raw curated rows; new_deals = deal.created; updated_deals = grouped meaningful deal updates"),
+      since: z.string().optional().describe("24h, 7d, 30d, or ISO timestamp; default 24h"),
+      limit: z.number().optional().describe("default 50, cap 100"),
+      dealId: z.string().optional().describe("optional single deal UUID"),
+      entity: z.enum(["deal", "wiki", "all"]).optional().describe("default deal"),
+      verb: z.string().optional().describe("comma-separated activity verbs, e.g. fact.added,brief.revised"),
+      cursor: z.number().optional().describe("pagination cursor from next_cursor"),
+      minSignificance: z.number().optional().describe("1..3; default 2, new_deals default 3"),
+    },
+  },
+  async ({ kind, since, limit, dealId, entity, verb, cursor, minSignificance } = {}) => {
+    const params = new URLSearchParams({ kind: kind || "events" });
+    if (since) params.set("since", since);
+    if (limit) params.set("limit", String(limit));
+    if (dealId) params.set("deal_id", dealId);
+    if (entity) params.set("entity", entity);
+    if (verb) params.set("verb", verb);
+    if (cursor) params.set("cursor", String(cursor));
+    if (minSignificance) params.set("min_sig", String(minSignificance));
+    return callApi("GET", `/api/agent/activity?${params}`);
+  }
+);
+
 // ============================================================
 // Deals — read
 // ============================================================
@@ -436,7 +471,11 @@ server.registerTool(
         .describe(
           "Our Stage workflow position. Use Interested when we want to record/track before contact; use Outreached when we contacted/logged them and have no response/effective relationship; use Sourced only once there is a response, intro, meeting, or other real relationship signal."
         ),
-      source: z.string().optional().describe("free-form sourced-by; recommend nominating a user"),
+      source: z.string().optional().describe("free-form sourced-by; exact team-member names also attach source_user_id"),
+      dealOwner: z
+        .string()
+        .optional()
+        .describe("owner override. Use an exact /api/field-options dealOwner value, a user email, or numeric user id."),
       sourceDirection: z
         .string()
         .optional()
@@ -475,7 +514,7 @@ server.registerTool(
   {
     description:
       "List a deal's recorded facts (the research substrate). Each fact carries a " +
-      "category, a claim, a source, a confidence, and a trust rung (unverified → " +
+      "category, a claim, a source/sourceUrl, a confidence, and a trust rung (unverified → " +
       "agent-verified → human-vouched → endorsed) plus who/what recorded it.",
     inputSchema: {
       dealId: z.string(),
@@ -495,13 +534,15 @@ server.registerTool(
       "something unconfirmed (stored 'unverified', which is the honest default). You CANNOT " +
       "mark a fact as human-confirmed — only a person can raise it to 'human-vouched'. " +
       "`confidence` is how certain the claim is; `attested` is whether YOU take responsibility " +
-      "for having checked it. category ∈ founders | financials | product | market | team | " +
-      "company_basics | risk | fundraise | milestone | meta.",
+      "for having checked it. `source` is a human-readable provenance label; `sourceUrl` is a " +
+      "canonical URL that round-trips as sourceUrl/source_url. Category is free text; common " +
+      "values include founders | financials | product | market | team | company_basics | risk | fundraise | milestone | meta.",
     inputSchema: {
       dealId: z.string(),
       category: z.string(),
       claim: z.string(),
       source: z.string().optional().describe("where you found this (URL, 'deck p3', 'LinkedIn')"),
+      sourceUrl: z.string().optional().describe("canonical URL for the evidence, if separate from source"),
       confidence: z.enum(["high", "medium", "low"]).optional(),
       attested: z
         .boolean()
@@ -509,11 +550,12 @@ server.registerTool(
         .describe("true → stored 'agent-verified'; false/omitted → 'unverified'. Answer honestly."),
     },
   },
-  async ({ dealId, category, claim, source, confidence, attested }) =>
+  async ({ dealId, category, claim, source, sourceUrl, confidence, attested }) =>
     callApi("POST", `/api/deals/${encodeURIComponent(dealId)}/facts`, {
       category,
       claim,
       source: source ?? "",
+      ...(sourceUrl ? { sourceUrl } : {}),
       confidence: confidence ?? "medium",
       attested: attested === true,
     })

package/bin/llama.mjs

@@ -291,6 +291,38 @@ async function searchDeals(q, flags) {
   return result;
 }
 
+function buildActivityQuery(kind, flags) {
+  const params = new URLSearchParams({ kind });
+  const mappings = [
+    ["since", "since"],
+    ["limit", "limit"],
+    ["cursor", "cursor"],
+    ["before-id", "before_id"],
+    ["before_id", "before_id"],
+    ["deal", "deal"],
+    ["deal-id", "deal_id"],
+    ["deal_id", "deal_id"],
+    ["entity", "entity"],
+    ["min-sig", "min_sig"],
+    ["min_sig", "min_sig"],
+    ["min-significance", "min_sig"],
+  ];
+  for (const [flag, param] of mappings) {
+    if (flags[flag] !== undefined && flags[flag] !== true) {
+      params.set(param, String(flags[flag]));
+    }
+  }
+  for (const verb of splitCsvFlag(flags.verb) ?? []) {
+    params.append("verb", verb);
+  }
+  return params;
+}
+
+async function fetchActivity(kind, flags) {
+  const params = buildActivityQuery(kind, flags);
+  return request("GET", `/api/agent/activity?${params}`);
+}
+
 function splitCsvFlag(value) {
   if (!value || value === true) return undefined;
   return String(value)
@@ -367,6 +399,8 @@ Agent onboarding (run once on first install):
   llama agent bootstrap                # fetch live Command + Llama OS skill manifest
   llama skills search "pipeline update" # discover relevant runtime skills
   llama skills show llama-pipeline      # read a skill from Command
+  llama activity new-deals --since 24h  # recent deal creations for agents
+  llama activity updated-deals --since 7d # meaningful deal updates, grouped
   llama explain <url-or-object>         # explain Command URL/object status + lifecycle
   llama eval good|bad --last            # mark the latest CLI/MCP result for eval
   llama eval add "<query>" --expect wiki:<slug>|deal:<uuid>
@@ -390,7 +424,7 @@ auto-detects \`gcloud auth print-identity-token\` and uses Bearer auth.
 Manually-set \`llc_\` tokens are used as a fallback.
 
 Deals:
-  llama deal create "Company" --source <name> --source-direction Inbound|Outbound --description "..." --status Interested|Outreached|Sourced --website https://...
+  llama deal create "Company" --source <name> --deal-owner <name|email|userId> --source-direction Inbound|Outbound --description "..." --status Interested|Outreached|Sourced --website https://...
   llama deal show <dealId>
   llama deal feed <dealId>                                     # every contribution (facts + notes), human-typed or assistant-drafted, newest first
   llama deal update <dealId> <field> <value>
@@ -418,6 +452,13 @@ Deals:
                             [--limit 200] [--offset 0]
   llama deal list [--owner ...] [--status ...] [...same flags as search]
 
+Agent activity (read-only, cheap read model over append-only activity):
+  llama activity new-deals [--since 24h|7d|<ISO>] [--limit 50]
+  llama activity updated-deals [--since 24h|7d|<ISO>] [--limit 50] [--deal <uuid>]
+  llama activity events [--since 24h] [--verb fact.added,brief.revised] [--entity deal|wiki|all]
+      Use this before scanning raw timelines or event-bus payloads. It returns
+      JSON from Command's curated activity_events projection: source ids included.
+
 Collaborators (besides owner — attribution candidates, no approval):
   llama deal collab list <dealId>
   llama deal collab add <dealId> --user <userId|email>
@@ -493,8 +534,8 @@ Deal soft-delete / restore / trash list:
   llama deal trash                                             # list deleted deals
 
 Deal facts (AI-extracted or human-asserted, with verification):
-  llama deal fact list <dealId>                                # ⚠ session-only on server today
-  llama deal fact add <dealId> --category <cat> --claim "<text>" [--source <url>] [--confidence high|medium|low] [--attested]
+  llama deal fact list <dealId>
+  llama deal fact add <dealId> --category <cat> --claim "<text>" [--source "..."] [--source-url <url>] [--confidence high|medium|low] [--attested]
   llama deal fact verify <dealId> <factId> --status confirmed|disputed [--corrected-value "..."]
 
 Skill corrections (persona-owner pushback — read by persona-watcher):
@@ -614,6 +655,8 @@ Common:
   llama deal show <dealId>          full deal record
   llama deal feed <dealId>          every contribution (facts + notes), newest first
   llama post <dealId> "..."         add a note to a deal
+  llama activity new-deals --since 24h  recent deal creations
+  llama activity updated-deals --since 7d meaningful deal updates
   llama agent-onboard               print the AI-agent workflow contract
   llama agent bootstrap             live Llama OS skill manifest from Command
   llama skills search "<query>"     discover which skill to read
@@ -622,6 +665,7 @@ Common:
 
 Command groups — run \`llama help <group>\` for that group's commands:
   deal        create · show · feed · update · enrich · search · collaborators · links · delete
+  activity    new-deals · updated-deals · events for agent read models
   brief       brief blocks: list · add · edit · history · refresh
   facts       deal facts + skill corrections (the sourced, trust-rated layer)
   timeline    timeline · posts · mentions
@@ -644,6 +688,7 @@ the CLI auto-detects it — no token needed (\`llc_\` tokens are a fallback).`;
 // Area → which top-level sections of HELP_FULL belong to it.
 const HELP_AREA_MATCH = {
   deal: [/^Deals/, /^Collaborators/, /^Soft-delete/, /^Deal links/, /^Deal soft-delete/],
+  activity: [/^Agent activity/],
   brief: [/^Brief blocks/, /^Brief \/ persona/],
   facts: [/^Deal facts/, /^Skill corrections/],
   timeline: [/^Timeline/, /^Mentions/],
@@ -1043,6 +1088,40 @@ async function main() {
     return;
   }
 
+  if (area === "activity") {
+    const sub = action || "events";
+    const normalized = sub.replace(/-/g, "_");
+    const kind =
+      normalized === "new" || normalized === "new_deal" || normalized === "new_deals"
+        ? "new_deals"
+        : normalized === "updated" || normalized === "updates" || normalized === "updated_deal" || normalized === "updated_deals"
+          ? "updated_deals"
+          : normalized === "event" || normalized === "events" || normalized === "feed" || normalized === "all"
+            ? "events"
+            : null;
+    if (!kind) {
+      throw new Error("Usage: llama activity new-deals|updated-deals|events [--since 24h] [--limit 50]");
+    }
+    const { flags } = parseFlags(rest, [
+      "json",
+      "since",
+      "limit",
+      "cursor",
+      "before-id",
+      "before_id",
+      "deal",
+      "deal-id",
+      "deal_id",
+      "entity",
+      "verb",
+      "min-sig",
+      "min_sig",
+      "min-significance",
+    ]);
+    print(await fetchActivity(kind, flags));
+    return;
+  }
+
   if (area === "skills" || (area === "agent" && action === "skills")) {
     const sub = area === "skills" ? action : rest[0];
     const args = area === "skills" ? rest : rest.slice(1);
@@ -1361,10 +1440,11 @@ async function main() {
   if (area === "deal" && action === "create") {
     const { flags, positional } = parseFlags(rest);
     const companyName = positional.join(" ").trim();
-    if (!companyName) throw new Error("Usage: llama deal create \"Company\" [--source Name]");
+    if (!companyName) throw new Error("Usage: llama deal create \"Company\" [--source Name] [--deal-owner name|email|userId]");
     const body = {
       companyName,
       source: flags.source,
+      dealOwner: flags.dealOwner || flags["deal-owner"],
       sourceDirection: flags.sourceDirection || flags["source-direction"],
       description: flags.description,
       website: flags.website,
@@ -1656,10 +1736,6 @@ async function main() {
   }
 
   // ----- Deal facts (AI-extracted or human-asserted, with verification) -----
-  // NOTE: server routes currently use session-only auth() — token-only
-  // callers will get 401 until /api/deals/:id/facts and
-  // /api/deals/:id/facts/:factId switch to authenticate(). CLI surface
-  // is forward-compatible.
   if (area === "deal" && action === "fact") {
     const sub = rest[0];
     const dealId = rest[1];
@@ -1675,10 +1751,12 @@ async function main() {
     }
 
     if (sub === "add") {
-      if (!flags.category || !flags.claim) {
+      const claim = flags.claim ?? flags.value;
+      const sourceUrl = flags["source-url"] ?? flags.sourceUrl;
+      if (!flags.category || !claim) {
         throw new Error(
           `Usage: llama deal fact add <dealId> --category <cat> --claim "<text>" ` +
-          `[--source <url>] [--confidence high|medium|low] [--attested]`
+          `[--source "..."] [--source-url <url>] [--confidence high|medium|low] [--attested]`
         );
       }
       // --attested: the caller takes responsibility that this is accurate
@@ -1686,8 +1764,9 @@ async function main() {
       // vouched; without it, it stays unverified. Declare honestly.
       print(await request("POST", `/api/deals/${encodeURIComponent(dealId)}/facts`, {
         category: String(flags.category),
-        claim: String(flags.claim),
+        claim: String(claim),
         source: flags.source ? String(flags.source) : "",
+        ...(sourceUrl ? { sourceUrl: String(sourceUrl) } : {}),
         confidence: flags.confidence ? String(flags.confidence) : "medium",
         attested: flags.attested === true,
       }));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaventures/cli",
-  "version": "1.17.3",
+  "version": "1.18.1",
   "description": "CLI + MCP server for the Llama Ventures investment workbench (command.llamaventures.vc).",
   "type": "module",
   "scripts": {