hyparam
diff --git a/‎README.md‎
Lines changed: 41 additions & 1 deletion b/‎README.md‎
Lines changed: 41 additions & 1 deletion
diff --git a/‎bin/cli.js‎
Lines changed: 5 additions & 1 deletion b/‎bin/cli.js‎
Lines changed: 5 additions & 1 deletion
diff --git a/‎skills/collectivus-query/SKILL.md‎
Lines changed: 1 addition & 1 deletion b/‎skills/collectivus-query/SKILL.md‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎skills/collectivus-query/references/query-cli.md‎
Lines changed: 1 addition & 0 deletions b/‎skills/collectivus-query/references/query-cli.md‎
Lines changed: 1 addition & 0 deletions
@@ -105,6 +105,16 @@ tail -f "collectivus-data/$USER/proxy/$(date -u +%F).jsonl"
 
 Full step-by-step: [`docs/walkthrough-claude-code.md`](docs/walkthrough-claude-code.md).
 
+To capture agent-attributed transcripts from a gascity supervisor (separate
+from the proxy capture above), attach a city to the same daemon:
+
+```bash
+ctvs gascity attach hyptown --api-url http://127.0.0.1:8372
+ctvs query sql "select gascity_template, count(*) as parts from gascity_messages group by 1 order by parts desc"
+```
+
+See [Gascity source (`gascity_messages`)](#gascity-source-gascity_messages) below.
+
 ## Configuration
 
 Pass a JSON config with `--config <path>` (a local path or url). The schema:
@@ -552,7 +562,7 @@ outdated data).
 > unchanged; the new warning is written only to stderr. `missing`
 > partitions still error.
 
-Logical datasets are `logs`, `traces`, `metrics`, and `proxy_messages`. `ctvs collect <file.jsonl> --name <name>` registers an external JSONL file as a dynamic table; names are normalized for SQL, so `--name random-log` becomes table `random_log`. Collection tables include `_ctvs_source_path`, `_ctvs_line_number`, `_ctvs_raw`, and inferred top-level JSON fields. `ctvs query schema <dataset>` prints the schema, and `ctvs query catalog` shows which datasets have source and cached rows.
+Logical datasets are `logs`, `traces`, `metrics`, `proxy_messages`, and `gascity_messages`. `ctvs collect <file.jsonl> --name <name>` registers an external JSONL file as a dynamic table; names are normalized for SQL, so `--name random-log` becomes table `random_log`. Collection tables include `_ctvs_source_path`, `_ctvs_line_number`, `_ctvs_raw`, and inferred top-level JSON fields. `ctvs query schema <dataset>` prints the schema, and `ctvs query catalog` shows which datasets have source and cached rows.
 
 ### Conversation log model
 
@@ -566,6 +576,36 @@ JSON columns (`attributes`, `status`, `tools`, `tool_args`) carry sparse structu
 
 For the full per-column derivation table see [skills/collectivus-query/references/query-cli.md](skills/collectivus-query/references/query-cli.md).
 
+### Gascity source (`gascity_messages`)
+
+`ctvs gascity` is a separate listener that subscribes to a gascity supervisor's
+REST API, normalizes provider frames (Claude / Codex), and writes one row per
+content block (text / thinking / tool_use / tool_result / attachment) directly
+to Parquet at `~/.collectivus/sink/gascity_messages/date=<YYYY-MM-DD>/city=<name>/`.
+There is no JSONL stage and no `.meta.json` sidecar: the sink IS the queryable
+store, so `ctvs query gascity_messages` is always reading what the daemon has
+flushed up to the moment of the call.
+
+```bash
+ctvs gascity attach hyptown --api-url http://127.0.0.1:8372
+ctvs gascity list
+ctvs query schema gascity_messages --format markdown
+ctvs query sql "select gascity_template, count(*) from gascity_messages group by 1"
+```
+
+`gascity_messages` carries agent-identity columns the proxy can't see —
+`gascity_template`, `gascity_rig`, `gascity_alias` — plus per-frame token usage
+with cache breakdown (`input_tokens`, `cache_read_input_tokens`,
+`cache_creation_input_tokens`). Use it when you need agent-attributed cost
+analysis or tool-call inspection; use `proxy_messages` for HTTP-level retry
+visibility and request timing. They UNION cleanly via `gateway_id` (a constant
+`gascity-scribe` on every gascity row tags the source).
+
+The bundled [`ctvs-gascity` skill](src/cli/init_presets/gascity_skill.md) — installed per-workspace by
+`ctvs init gascity` — teaches Claude Code and Codex how to query all three
+gascity-aware tables (`events`, `session_segments`, `gascity_messages`) and
+their cross-source joins with `proxy_messages`.
+
 ### LLM skill
 
 Install the bundled `collectivus-query` skill so Claude Code and Codex know how
 
@@ -2,7 +2,7 @@
 
 import process from 'node:process'
 
-const SUBCOMMANDS = new Set(['install', 'uninstall', 'attach', 'detach', 'status', 'config', 'admin', 'invite', 'export', 'query', 'collect', 'rendezvous', 'join', 'skills', 'claude-hook', 'init', 'ignore'])
+const SUBCOMMANDS = new Set(['install', 'uninstall', 'attach', 'detach', 'status', 'config', 'admin', 'invite', 'export', 'query', 'collect', 'rendezvous', 'join', 'skills', 'claude-hook', 'init', 'gascity', 'ignore'])
 
 const argv = process.argv.slice(2)
 const subcommand = argv[0]
@@ -108,6 +108,10 @@ async function loadSubcommand(name) {
     const { runInitSubcommand } = await import('../src/cli/init.js')
     return runInitSubcommand
   }
+  case 'gascity': {
+    const { runGascity } = await import('../src/cli/gascity.js')
+    return runGascity
+  }
   case 'ignore': {
     const { runIgnore } = await import('../src/cli/ignore.js')
     return runIgnore
 
@@ -107,7 +107,7 @@ Use `JSON_VALUE(<col>, '$.path')` to extract scalars from the `attributes` / `st
 - Always read stderr. A successful exit code does not mean the data is fresh — a `warning: querying stale data; …` line on stderr means stdout reflects outdated Parquet, and the user should be told before drawing conclusions.
 - Do not paste `--config` into every command by habit. Use it when discovery shows the service is not using `~/.hyp/collectivus.json`.
 - Do not read arbitrary Parquet files directly for `ctvs query sql`; the CLI only allows logical tables.
-- Keep SQL read-only and use only logical datasets: `logs`, `traces`, `metrics`, `proxy_messages`, and registered collection tables from `ctvs query catalog`.
+- Keep SQL read-only and use only logical datasets: `logs`, `traces`, `metrics`, `proxy_messages`, `gascity_messages`, and registered collection tables from `ctvs query catalog`.
 - Use UTC dates with `--date YYYY-MM-DD`.
 - Use `--service`, `--gateway-id`, `--from`, `--to`, or `--since` to narrow broad investigations.
 
 
@@ -80,6 +80,7 @@ Collection tables always include `_ctvs_source_path`, `_ctvs_line_number`, and `
 - `traces`: OTLP spans. Common columns include `gateway_id`, `date`, `traceId`, `spanId`, `parentSpanId`, `name`, `kind`, `startTimestamp`, `endTimestamp`, `durationMs`, `status`, `serviceName`, `resource`, `scope`, and `attributes`.
 - `metrics`: OTLP metric points. Common columns include `gateway_id`, `date`, `metricName`, `metricType`, `timestamp`, `startTimestamp`, `serviceName`, `value`, `valueInt`, `count`, `sum`, `unit`, `resource`, `scope`, and `attributes`.
 - `proxy_messages`: One row per LLM proxy content part (text block, tool call, tool result, etc.), globally deduped by content-derived `message_id`. See **proxy_messages columns** below for the full 26-column schema; `gateway_id` and `date` are added as partition columns on the on-disk Parquet.
+- `gascity_messages`: One row per content block from gascity-captured agent sessions (text, thinking, tool_use, tool_result, attachment). Captured by the `ctvs gascity` supervisor source — agent-attributed (`gascity_template` / `gascity_rig` / `gascity_alias`) and includes per-frame token usage with cache breakdown. Always fresh: the daemon writes Parquet directly to `~/.collectivus/sink/gascity_messages/date=<YYYY-MM-DD>/city=<name>/` (no JSONL stage, no `.meta.json` sidecar). The constant `gateway_id = 'gascity-scribe'` tags the source for cross-source UNIONs with `proxy_messages`. Run `ctvs query schema gascity_messages --format markdown` for the full 47-column schema.
 
 Run `ctvs query schema <dataset> --format json` for the exact columns in the installed version.