thoughtleaders-cli 0.7.13__tar.gz → 0.7.14__tar.gz

{thoughtleaders_cli-0.7.13 → thoughtleaders_cli-0.7.14}/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "tl-cli",
-  "version": "0.7.13",
+  "version": "0.7.14",
   "description": "ThoughtLeaders CLI — query sponsorship deals, channels, brands, uploads, and intelligence from the terminal",
   "author": {
     "name": "ThoughtLeaders",

{thoughtleaders_cli-0.7.13 → thoughtleaders_cli-0.7.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: thoughtleaders-cli
-Version: 0.7.13
+Version: 0.7.14
 Summary: ThoughtLeaders CLI — query sponsorship data, channels, brands, and intelligence
 Project-URL: Homepage, https://thoughtleaders.io
 Project-URL: Repository, https://github.com/ThoughtLeaders-io/thoughtleaders-cli

{thoughtleaders_cli-0.7.13 → thoughtleaders_cli-0.7.14}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "thoughtleaders-cli"
-version = "0.7.13"
+version = "0.7.14"
 description = "ThoughtLeaders CLI — query sponsorship data, channels, brands, and intelligence"
 readme = "README.md"
 license = "MIT"

{thoughtleaders_cli-0.7.13 → thoughtleaders_cli-0.7.14}/skills/tl/SKILL.md

@@ -238,8 +238,22 @@ tl sponsorships update 98765 '{"publish_status": 3}'
 tl channels update 12345 '{"demographic_male_share": 62}'
 tl channels update 12345 '{"demographic_geo": {"US": 60, "UK": 12, "CA": 8}}'
 tl channels update 12345 '{"demographic_male_share": 55, "demographic_usa_share": 70}'
+tl channels update 12345 '{"outreach_email": "press@creator.com"}'
+tl channels update 12345 '{"all_emails": {"press@creator.com": {"timestamp": "2026-06-25T12:00:00+00:00", "source": "manual"}}}'
 ```
 
+**Channel contact emails.** Besides demographics, `tl channels update` accepts two
+contact fields:
+
+- **`outreach_email`** — the channel's primary outreach address (a single email string, or `null`).
+- **`all_emails`** — the channel's full email archive. It is **not** a free-form blob: it's
+  a JSON object keyed by email address, each value an object `{"timestamp": <ISO-8601 datetime>, "source": <string>}`.
+  `timestamp` must parse as ISO-8601 (e.g. `"2026-06-25T12:00:00+00:00"`); `source` records
+  where the address came from. Known `source` values: `outreach_email` (the address that was
+  the primary outreach email, archived when the channel was blacklisted), `google_search`,
+  `scheduled_rescrape`. Use a descriptive token such as `manual` for hand-added entries.
+  An edit **replaces** the whole `all_emails` object, so include every entry you want to keep.
+
 ### Creating and vetting sponsorships
 
 This is the end-to-end workflow for proposing a sponsorship, then moving it through the funnel as the two sides respond. Three create commands plus `tl sponsorships update` cover every state transition the CLI exposes.

{thoughtleaders_cli-0.7.13 → thoughtleaders_cli-0.7.14}/skills/tl/references/elasticsearch-schema.md

@@ -41,8 +41,8 @@ Filter with `{"term": {"doc_type": "article"}}`.
 | `id` | keyword | Video/article ID. Compound form `<channel_id>:<youtube_id>` (matches PG `adlink.article_id` and ES `_id`). |
 | `title` | text | Video title |
 | `description` | text | Video description |
-| `content` | text | Full content/transcript text |
-| `transcript` | text | Raw transcript |
+| `content` | text | Full content/transcript text (plain text; not always populated) |
+| `transcript` | text | Raw transcript — stored as YouTube timed-text **XML**, not plain text (see note below) |
 | `transcript_language` | keyword | Transcript language code |
 | `summary` | text | AI-generated summary |
 | `publication_date` | date | When video was published |
@@ -244,6 +244,18 @@ Repeat until a page comes back short (`next_search_after` is absent on an empty
 
 `text` fields on article docs (`title`, `summary`, `transcript`) appear to use the `standard` analyzer (tokenize + lowercase, no stemmer, no English-possessive filter), so inflections, plurals, and possessives are each indexed as distinct terms. For example: `bitcoin` (4,466,300) vs `bitcoins` (489,262). For stemming-style recall, expand the query side with a `bool.should` over the variants.
 
+## Transcript field format
+
+The `transcript` field's `_source` is **YouTube timed-text caption XML**, not plain prose. Each caption cue is a `<text start="…" dur="…">` element wrapped in `<transcript>`, and the inner text is **double HTML-entity-encoded** (an apostrophe is `&amp;#39;`, i.e. an escaped `&#39;`):
+
+```xml
+<?xml version="1.0" encoding="utf-8" ?>
+<transcript><text start="0.05" dur="4.33">I&amp;#39;m going to</text>...</transcript>
+```
+
+- **Searching is unaffected** — the field is analyzed as `text`, so `match` / `match_phrase` queries hit the words directly regardless of the markup. The XML only matters when you retrieve and read the raw `_source`.
+- **For plain prose**, either use the `content` field (plain text, but not always populated) or strip the markup yourself, e.g. `jq -r '.results[0].transcript' | sed -E 's/<[^>]+>/ /g'` and then unescape entities twice (the encoding is doubled).
+
 ## Notes & gotchas
 
 - **Composite IDs:** `tl-platform.id` and `_id` are `<channel_id>:<youtube_id>`. The `youtube_id` portion alone is what Firebolt's `article_metrics.id` stores.

{thoughtleaders_cli-0.7.13 → thoughtleaders_cli-0.7.14}/src/tl_cli/__init__.py

@@ -1,3 +1,3 @@
 """ThoughtLeaders CLI — query sponsorship data, channels, brands, and intelligence."""
 
-__version__ = "0.7.13"
+__version__ = "0.7.14"

{thoughtleaders_cli-0.7.13 → thoughtleaders_cli-0.7.14}/src/tl_cli/commands/db.py

@@ -108,6 +108,10 @@ def es_cmd(
         False, "--pricing",
         help="Estimate the query's credit cost without running it (flat 1 credit).",
     ),
+    highlight: bool = typer.Option(
+        False, "--highlight",
+        help="Keep ES highlight fragments in each result row. Only meaningful when the query body includes a `highlight` clause; otherwise no-op.",
+    ),
 ) -> None:
     """Run a raw Elasticsearch search query.
 
@@ -116,6 +120,7 @@ def es_cmd(
     Examples:
         tl db es '{"size": 5, "query": {"term": {"channel.id": 5607}}}'
         tl db es '{"size": 0, "aggs": {"by_channel": {"terms": {"field": "channel.id"}}}}'
+        tl db es '{"query": {"match": {"transcript": "vpn"}}, "highlight": {"fields": {"transcript": {}}}}' --highlight
     """
     fmt = detect_format(json_output, csv_output, md_output, toon_output)
     raw = _read_query(query)
@@ -127,4 +132,6 @@ def es_cmd(
     body: dict = {"query": body_query}
     if pricing:
         body["pricing"] = True
+    if highlight:
+        body["include_highlight"] = True
     _run("/raw/es", body, fmt, "Elasticsearch results", pricing=pricing)