honcho-cli 0.1.4__tar.gz → 0.2.0__tar.gz

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/.gitignore

@@ -196,3 +196,7 @@ grafana-data/
 
 # Claude Code addon stuff
 .omc
+
+# Sandbox real-provider credentials (see sandbox/real.env.example)
+sandbox/real.env
+sandbox/.state.env

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/CHANGELOG.md

@@ -7,6 +7,29 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 
 ## [Unreleased]
 
+## [0.2.0] - 2026-09-21
+
+### Added
+
+- CLI requests carry `X-Honcho-Host: honcho-cli/<version> (<platform>)` so telemetry counts them as CLI traffic rather than direct SDK use (#1181)
+- Conclusion attribution on `honcho conclusion list` and `honcho conclusion search` (Honcho v3.2.0+): every row now carries `level`, `source_ids` and `times_derived`, so an extracted fact is distinguishable from a dreamed one. Table output shows a premise count; `--json` keeps the full id list, ready to pipe into `honcho conclusion get` (#952)
+- `honcho conclusion get <id>...` fetches conclusions by ID from anywhere in the workspace, with no observer/observed pair required. Feed it a conclusion's `source_ids` to walk a reasoning chain down to the explicit facts underneath it; IDs that no longer exist are reported rather than failing the command (#952)
+- `honcho conclusion derived <id>` lists what was built on top of a conclusion — the same edge walked upward. Worth checking before deleting or correcting a fact (#952)
+- `--level` on `honcho conclusion list` and `honcho conclusion search`, and `--derived-from` on `honcho conclusion list` (#952)
+- `--evidence` on `honcho peer chat` and `honcho workspace chat` (Honcho v3.2.0+): reports the conclusions and messages the dialectic read and the tools it called. Evidence is collated from what the agent accessed rather than reported by the model, so it over-reports and costs no extra model tokens. Messages are summarised per session, since evidence carries their identity but not their text (#1129)
+
+### Changed
+
+- Requires `honcho-ai` 2.5.0 (was 2.4.0), which carries the attribution fields and the evidence-bearing chat response
+
+## [0.1.5] - 2026-09-09
+
+### Added
+
+- `honcho scope` command group: `list`, `create`, `inspect`, `sessions`, `add-sessions`, `remove-session`, `status` (Honcho v3.1.0+) (#1162)
+- `honcho workspace chat` for reasoned questions across all peers (Honcho v3.1.0+) (#1150)
+- `--scope` on `honcho workspace chat` and `honcho peer chat`, and `--sessions` on `honcho peer chat`, to confine recall (Honcho v3.1.0+) (#1151)
+
 ## [0.1.4] - 2026-08-26
 
 ### Added

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: honcho-cli
-Version: 0.1.4
+Version: 0.2.0
 Summary: A terminal for Honcho — memory that reasons.
 Project-URL: Homepage, https://github.com/plastic-labs/honcho
 Project-URL: Repository, https://github.com/plastic-labs/honcho
@@ -14,7 +14,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries
 Requires-Python: >=3.11
 Requires-Dist: click>=8.0.0
-Requires-Dist: honcho-ai>=2.0.0
+Requires-Dist: honcho-ai>=2.5.0
 Requires-Dist: httpx>=0.27.0
 Requires-Dist: rich>=13.0.0
 Requires-Dist: typer>=0.15.0
@@ -100,6 +100,7 @@ honcho stop --wipe     # also delete volumes
 | `honcho workspace list` | List accessible workspaces |
 | `honcho workspace create <id>` | Create or get a workspace |
 | `honcho workspace inspect` | Peers, sessions, config for a workspace |
+| `honcho workspace chat <query>` | Query the dialectic across all peers (optional `-s` / `--scope` / `--reasoning`) |
 | `honcho workspace search <query>` | Search messages across workspace |
 | `honcho workspace queue-status` | Deriver queue status (filter with `--observer` / `--sender`) |
 | `honcho workspace delete <id>` | Delete a workspace. Use `--dry-run` to preview, `--cascade` to also delete sessions, `--yes` to skip the confirm prompt |
@@ -112,7 +113,7 @@ honcho stop --wipe     # also delete volumes
 | `honcho peer create <id>` | Create or get a peer |
 | `honcho peer inspect <id>` | Card, session count, recent conclusions |
 | `honcho peer card <id>` | Raw peer card content |
-| `honcho peer chat <query>` | Query the dialectic about a peer (peer via `-p` / `HONCHO_PEER_ID`) |
+| `honcho peer chat <query>` | Query the dialectic about a peer (peer via `-p` / `HONCHO_PEER_ID`; optional `--scope` / `--sessions`) |
 | `honcho peer representation <id>` | Formatted representation |
 | `honcho peer search <query>` | Search a peer's messages (peer via `-p` / `HONCHO_PEER_ID`) |
 | `honcho peer get-metadata <id>` / `set-metadata` | Metadata operations |
@@ -133,6 +134,17 @@ honcho stop --wipe     # also delete volumes
 | `honcho session get-metadata <id>` / `set-metadata` | Metadata operations |
 | `honcho session delete <id>` | Destructive; requires `--yes` |
 
+### Scopes
+
+| Command | Description |
+|---------|-------------|
+| `honcho scope list` | List scopes in the workspace |
+| `honcho scope create <name>` | Create or get a scope (`--sessions id,...` to add members, `--metadata`) |
+| `honcho scope inspect <name>` | Metadata, member sessions, backfill summary. Never creates a missing scope |
+| `honcho scope sessions <name>` | Member sessions, longest-standing first |
+| `honcho scope add-sessions <name> <ids...>` / `remove-session <name> <id>` | Membership; history backfills asynchronously |
+| `honcho scope status <name>` | Per-session backfill state — recall is complete once nothing is `pending` |
+
 ### Messages
 
 | Command | Description |

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/README.md

@@ -75,6 +75,7 @@ honcho stop --wipe     # also delete volumes
 | `honcho workspace list` | List accessible workspaces |
 | `honcho workspace create <id>` | Create or get a workspace |
 | `honcho workspace inspect` | Peers, sessions, config for a workspace |
+| `honcho workspace chat <query>` | Query the dialectic across all peers (optional `-s` / `--scope` / `--reasoning`) |
 | `honcho workspace search <query>` | Search messages across workspace |
 | `honcho workspace queue-status` | Deriver queue status (filter with `--observer` / `--sender`) |
 | `honcho workspace delete <id>` | Delete a workspace. Use `--dry-run` to preview, `--cascade` to also delete sessions, `--yes` to skip the confirm prompt |
@@ -87,7 +88,7 @@ honcho stop --wipe     # also delete volumes
 | `honcho peer create <id>` | Create or get a peer |
 | `honcho peer inspect <id>` | Card, session count, recent conclusions |
 | `honcho peer card <id>` | Raw peer card content |
-| `honcho peer chat <query>` | Query the dialectic about a peer (peer via `-p` / `HONCHO_PEER_ID`) |
+| `honcho peer chat <query>` | Query the dialectic about a peer (peer via `-p` / `HONCHO_PEER_ID`; optional `--scope` / `--sessions`) |
 | `honcho peer representation <id>` | Formatted representation |
 | `honcho peer search <query>` | Search a peer's messages (peer via `-p` / `HONCHO_PEER_ID`) |
 | `honcho peer get-metadata <id>` / `set-metadata` | Metadata operations |
@@ -108,6 +109,17 @@ honcho stop --wipe     # also delete volumes
 | `honcho session get-metadata <id>` / `set-metadata` | Metadata operations |
 | `honcho session delete <id>` | Destructive; requires `--yes` |
 
+### Scopes
+
+| Command | Description |
+|---------|-------------|
+| `honcho scope list` | List scopes in the workspace |
+| `honcho scope create <name>` | Create or get a scope (`--sessions id,...` to add members, `--metadata`) |
+| `honcho scope inspect <name>` | Metadata, member sessions, backfill summary. Never creates a missing scope |
+| `honcho scope sessions <name>` | Member sessions, longest-standing first |
+| `honcho scope add-sessions <name> <ids...>` / `remove-session <name> <id>` | Membership; history backfills asynchronously |
+| `honcho scope status <name>` | Per-session backfill state — recall is complete once nothing is `pending` |
+
 ### Messages
 
 | Command | Description |

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "honcho-cli"
-version = "0.1.4"
+version = "0.2.0"
 description = "A terminal for Honcho — memory that reasons."
 readme = "README.md"
 requires-python = ">=3.11"
@@ -19,7 +19,7 @@ classifiers = [
 dependencies = [
     "click>=8.0.0",
     "typer>=0.15.0",
-    "honcho-ai>=2.0.0",
+    "honcho-ai>=2.5.0",
     "rich>=13.0.0",
     "httpx>=0.27.0",
 ]

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/src/honcho_cli/__init__.py

@@ -1,3 +1,3 @@
 """Honcho CLI — a terminal for Honcho."""
 
-__version__ = "0.1.4"
+__version__ = "0.2.0"

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/src/honcho_cli/_help.py

@@ -80,30 +80,35 @@ def print_welcome(console: Console) -> None:
         ("[dim]pattern[/dim]", r"[dim]honcho <command> \[args] \[-w workspace] \[-p peer] \[-s session][/dim]"),
         ("[dim]example[/dim]", "[dim]honcho peer chat \"what does alice prefer?\" -p alice -w agents[/dim]"),
         ("", ""),
-        ("workspace",  "list · create · search · delete · inspect · queue-status"),
+        ("workspace",  "list · create · search · chat · delete · inspect · queue-status"),
         ("peer",       "list · create · search · inspect · card · chat"),
         ("",           "get-metadata · set-metadata · representation"),
         ("session",    "list · create · search · delete · inspect · view · add-peers"),
         ("",           "context · get-metadata · set-metadata · peers"),
         ("",           "remove-peers · representation · summaries"),
+        ("scope",      "list · create · inspect · sessions · add-sessions"),
+        ("",           "remove-session · status"),
         ("message",    "list · create · get"),
         ("conclusion", "list · create · search · delete"),
         ("config",     "inspect current configuration"),
     ]
     memory_rows = [
+        ("honcho workspace chat \"...\" -w <workspace>", "query the Dialectic across all peers"),
         ("honcho peer chat \"...\" -p <peer> -w <workspace>", "query the Dialectic about a peer"),
         ("honcho peer inspect -p <peer> -w <workspace>", "dashboard: peer card + recent conclusions + configuration"),
         ("honcho peer representation -p <peer> -w <workspace>", "global peer representation"),
         ("honcho peer representation -p <peer> -w <workspace> -s <session>", "session-scoped peer representation"),
+        ("honcho scope list -w <workspace>", "which session sets exist; inspect one for members + backfill"),
+        ("honcho peer chat \"...\" -p <peer> --scope <scope>", "answer from one scope's sessions only"),
         ("honcho peer card -p <peer> -w <workspace>", "synthesized identity: traits, preferences, instructions"),
         ("honcho conclusion list -p <peer> -w <workspace>", "browse peer conclusions"),
         ("honcho session view / context -s <session>", "transcript, or what an agent would see"),
         ("honcho workspace queue-status", "is the deriver processing?"),
     ]
     option_rows = [
-        ("-w / --workspace", "scope to a workspace"),
-        ("-p / --peer",      "scope to a peer"),
-        ("-s / --session",   "scope to a session"),
+        ("-w / --workspace", "target a workspace"),
+        ("-p / --peer",      "target a peer"),
+        ("-s / --session",   "target a session"),
         ("--json",           "force JSON output for scripts and agents"),
         ("--help",           "show help for any command (e.g. honcho peer --help)"),
     ]

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/src/honcho_cli/commands/conclusion.py

@@ -18,6 +18,43 @@ app = typer.Typer(cls=HonchoTyperGroup, help="List, search, create, and delete p
 add_common_options(app)
 
 
+_LEVELS = ("explicit", "deductive", "inductive", "contradiction")
+
+#: Columns carrying a conclusion's attribution, shown alongside the content.
+_ATTRIBUTION_COLUMNS = ["id", "level", "source_ids", "times_derived", "content"]
+
+
+def _format_conclusion(c, workspace_id: str | None) -> dict:
+    """Shape a Conclusion for output.
+
+    ``level``, ``source_ids`` and ``times_derived`` are the attribution the
+    server started returning in Honcho v3.2.0. In table mode ``source_ids``
+    collapses to a count, since the ids are nanoids and a list of them makes
+    the row unreadable; JSON mode keeps the full list so it can be piped back
+    into ``honcho conclusion get``.
+    """
+    source_ids = c.source_ids or []
+    return {
+        "id": c.id,
+        "level": c.level,
+        "source_ids": source_ids if use_json() else len(source_ids),
+        "times_derived": c.times_derived,
+        "content": c.content if use_json() else c.content[:160],
+        "workspace_id": workspace_id,
+        "observer_id": c.observer_id,
+        "observed_id": c.observed_id,
+        "session_id": c.session_id,
+        "created_at": str(c.created_at),
+    }
+
+
+def _validate_level(level: str | None) -> str | None:
+    if level and level not in _LEVELS:
+        print_error("INVALID_LEVEL", f"--level must be one of: {', '.join(_LEVELS)}")
+        raise typer.Exit(1)
+    return level
+
+
 def _require_observer(observer: str | None) -> str:
     """Resolve observer peer ID; emit combined error if peer+workspace both missing."""
     config = get_resolved_config()
@@ -39,6 +76,16 @@ def list_conclusions(
     observer: Optional[str] = typer.Option(None, "--observer", help="Observer peer ID"),
     observed: Optional[str] = typer.Option(None, "--observed", help="Observed peer ID"),
     limit: int = typer.Option(10, "--limit", help="Max results"),
+    level: Optional[str] = typer.Option(
+        None,
+        "--level",
+        help="Only this reasoning level: explicit, deductive, inductive, contradiction",
+    ),
+    derived_from: Optional[str] = typer.Option(
+        None,
+        "--derived-from",
+        help="Only conclusions derived from this conclusion ID",
+    ),
     workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Override workspace ID"),
     peer: Optional[str] = typer.Option(None, "--peer", "-p", help="Override peer ID"),
     json_output: bool = typer.Option(False, "--json", help="Force JSON output"),
@@ -46,31 +93,27 @@ def list_conclusions(
     """List conclusions."""
 
     handle_cmd_flags(json_output=json_output, workspace=workspace, peer=peer)
+    _validate_level(level)
     observer = _require_observer(observer)
     client, config = get_client()
 
     p = client.peer(observer)
 
+    filters: dict = {}
+    if level:
+        filters["level"] = level
+    if derived_from:
+        filters["source_ids"] = {"contains": derived_from}
+
     try:
         if observed:
             scope = p.conclusions_of(observed)
         else:
             scope = p.conclusions
 
-        conclusions = scope.list(size=limit).items
-        items = [
-            {
-                "id": c.id,
-                "content": c.content if use_json() else c.content[:200],
-                "workspace_id": config.workspace_id,
-                "observer_id": c.observer_id,
-                "observed_id": c.observed_id,
-                "session_id": c.session_id,
-                "created_at": str(c.created_at),
-            }
-            for c in conclusions
-        ]
-        print_result(items, columns=["id", "content", "workspace_id", "observer_id", "observed_id", "session_id", "created_at"], title="Conclusions")
+        conclusions = scope.list(size=limit, filters=filters or None).items
+        items = [_format_conclusion(c, config.workspace_id) for c in conclusions]
+        print_result(items, columns=_ATTRIBUTION_COLUMNS + ["observed_id", "created_at"], title="Conclusions")
     except Exception as e:
         _handle_error(e, "conclusion", "list")
 
@@ -81,6 +124,11 @@ def search(
     observer: Optional[str] = typer.Option(None, "--observer", help="Observer peer ID"),
     observed: Optional[str] = typer.Option(None, "--observed", help="Observed peer ID"),
     top_k: int = typer.Option(10, help="Max results"),
+    level: Optional[str] = typer.Option(
+        None,
+        "--level",
+        help="Only this reasoning level: explicit, deductive, inductive, contradiction",
+    ),
     workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Override workspace ID"),
     peer: Optional[str] = typer.Option(None, "--peer", "-p", help="Override peer ID"),
     json_output: bool = typer.Option(False, "--json", help="Force JSON output"),
@@ -88,6 +136,7 @@ def search(
     """Semantic search over conclusions."""
 
     handle_cmd_flags(json_output=json_output, workspace=workspace, peer=peer)
+    _validate_level(level)
     observer = _require_observer(observer)
     client, config = get_client()
 
@@ -99,24 +148,80 @@ def search(
         else:
             scope = p.conclusions
 
-        results = scope.query(query, top_k=top_k)
-        items = [
-            {
-                "id": c.id,
-                "content": c.content if use_json() else c.content[:200],
-                "workspace_id": config.workspace_id,
-                "observer_id": c.observer_id,
-                "observed_id": c.observed_id,
-                "session_id": c.session_id,
-                "created_at": str(c.created_at),
-            }
-            for c in results
-        ]
-        print_result(items, columns=["id", "content", "workspace_id", "session_id", "created_at"], title=f"Conclusion search: {query}")
+        results = scope.query(query, top_k=top_k, filters={"level": level} if level else None)
+        items = [_format_conclusion(c, config.workspace_id) for c in results]
+        print_result(items, columns=_ATTRIBUTION_COLUMNS + ["created_at"], title=f"Conclusion search: {query}")
     except Exception as e:
         _handle_error(e, "conclusion", "search")
 
 
+@app.command()
+def get(
+    conclusion_ids: list[str] = typer.Argument(help="Conclusion IDs to fetch"),
+    workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Override workspace ID"),
+    json_output: bool = typer.Option(False, "--json", help="Force JSON output"),
+) -> None:
+    """Fetch conclusions by ID, from anywhere in the workspace.
+
+    Pass a conclusion's source_ids to see the premises it was derived from,
+    and repeat to walk a reasoning chain down to the explicit facts it rests
+    on. IDs that no longer exist are reported rather than failing the command.
+    """
+
+    handle_cmd_flags(json_output=json_output, workspace=workspace)
+    client, config = get_client()
+
+    for cid in conclusion_ids:
+        validate_resource_id(cid, "conclusion")
+
+    try:
+        conclusions = client.conclusions.get_many(list(conclusion_ids))
+        found = {c.id for c in conclusions}
+        missing = [cid for cid in conclusion_ids if cid not in found]
+
+        items = [_format_conclusion(c, config.workspace_id) for c in conclusions]
+        print_result(items, columns=_ATTRIBUTION_COLUMNS + ["observed_id", "created_at"], title="Conclusions")
+        if missing:
+            print_error(
+                "MISSING_CONCLUSIONS",
+                f"Not in this workspace (consolidated or deleted): {', '.join(missing)}",
+            )
+    except Exception as e:
+        _handle_error(e, "conclusion", "get")
+
+
+@app.command()
+def derived(
+    conclusion_id: str = typer.Argument(help="The premise conclusion ID"),
+    limit: int = typer.Option(10, "--limit", help="Max results"),
+    workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Override workspace ID"),
+    json_output: bool = typer.Option(False, "--json", help="Force JSON output"),
+) -> None:
+    """List the conclusions derived FROM a conclusion.
+
+    Walks the reasoning tree upward (premise -> conclusion); `conclusion get`
+    on a conclusion's source_ids walks it downward. Worth checking before
+    deleting or correcting a fact.
+    """
+
+    handle_cmd_flags(json_output=json_output, workspace=workspace)
+    validate_resource_id(conclusion_id, "conclusion")
+    client, config = get_client()
+
+    try:
+        page = client.conclusions.list(
+            size=limit, filters={"source_ids": {"contains": conclusion_id}}
+        )
+        items = [_format_conclusion(c, config.workspace_id) for c in page.items]
+        print_result(
+            items,
+            columns=_ATTRIBUTION_COLUMNS + ["observed_id", "created_at"],
+            title=f"Derived from {conclusion_id}",
+        )
+    except Exception as e:
+        _handle_error(e, "conclusion", "derived")
+
+
 @app.command()
 def create(
     content: str = typer.Argument(help="Conclusion content or JSON payload"),

{honcho_cli-0.1.4 → honcho_cli-0.2.0}/src/honcho_cli/commands/peer.py

@@ -9,12 +9,13 @@ import typer
 
 from honcho.api_types import PeerConfig
 
-from honcho_cli.commands.workspace import _config_to_dict, _handle_error, _raw_list
+from honcho_cli.commands.workspace import _config_to_dict, _handle_chat_error, _handle_error, _raw_list
 from honcho_cli.output import print_error, print_result, use_json
+from honcho_cli.recall import parse_csv_repeatable, reject_incompatible_recall, scope_for_sdk
 from honcho_cli.validation import validate_resource_id
 
 from honcho_cli._help import HonchoTyperGroup
-from honcho_cli.common import add_common_options, get_client, get_resolved_config, handle_cmd_flags
+from honcho_cli.common import add_common_options, format_evidence, get_client, get_flag_overrides, get_resolved_config, handle_cmd_flags
 
 app = typer.Typer(cls=HonchoTyperGroup, help="List, create, chat with, search, and manage peers and their representations.")
 add_common_options(app)
@@ -130,6 +131,21 @@ def chat(
     query: str = typer.Argument(help="Question to ask about the peer"),
     target: Optional[str] = typer.Option(None, help="Target peer for perspective"),
     reasoning: Optional[str] = typer.Option(None, "--reasoning", "-r", help="Reasoning level: minimal, low, medium, high, max"),
+    scope: Optional[list[str]] = typer.Option(
+        None,
+        "--scope",
+        help="Recall only from this scope. Repeat or comma-separate for several (explicit conclusions only). Excludes -s and --sessions.",
+    ),
+    sessions: Optional[list[str]] = typer.Option(
+        None,
+        "--sessions",
+        help="Recall only from these session IDs (repeat or comma-separate); explicit conclusions only. Excludes -s and --scope.",
+    ),
+    evidence: bool = typer.Option(
+        False,
+        "--evidence",
+        help="Also report what the answer was built from: the conclusions and messages read and the tools called.",
+    ),
     workspace: Optional[str] = typer.Option(None, "--workspace", "-w", help="Override workspace ID"),
     peer: Optional[str] = typer.Option(None, "--peer", "-p", help="Override peer ID"),
     session: Optional[str] = typer.Option(None, "--session", "-s", help="Override session ID"),
@@ -139,25 +155,50 @@ def chat(
 
     _REASONING_LEVELS = ("minimal", "low", "medium", "high", "max")
     if reasoning and reasoning not in _REASONING_LEVELS:
-        from honcho_cli.output import print_error
         print_error("INVALID_REASONING", f"--reasoning must be one of: {', '.join(_REASONING_LEVELS)}")
         raise typer.Exit(1)
 
     handle_cmd_flags(json_output=json_output, workspace=workspace, peer=peer, session=session)
     pid = _get_peer_id(None)
     client, config = get_client()
-    p = client.peer(pid)
+    scope_names = parse_csv_repeatable(scope, kind="scope", flag="--scope")
+    session_allowlist = parse_csv_repeatable(sessions, kind="session", flag="--sessions")
+    session_id = config.session_id or None
+    reject_incompatible_recall(
+        session_id=session_id,
+        scope=scope_names,
+        sessions=session_allowlist,
+        session_from_env=not get_flag_overrides()["session"],
+    )
+
+    chat_kwargs: dict[str, object] = {
+        "target": target,
+        "session": session_id,
+        "reasoning_level": reasoning or None,
+    }
+    scope_arg = scope_for_sdk(scope_names)
+    if scope_arg is not None:
+        chat_kwargs["scope"] = scope_arg
+    if session_allowlist is not None:
+        chat_kwargs["sessions"] = session_allowlist
 
     try:
-        response = p.chat(
-            query,
-            target=target,
-            session=config.session_id or None,
-            reasoning_level=reasoning or None,
+        p = client.peer(pid)
+        if not evidence:
+            response = p.chat(query, **chat_kwargs)
+            print_result({"peer_id": pid, "query": query, "response": response})
+            return
+        result = p.chat(query, include_evidence=True, **chat_kwargs)
+        print_result(
+            {
+                "peer_id": pid,
+                "query": query,
+                "response": result.content,
+                "evidence": format_evidence(result.evidence),
+            }
         )
-        print_result({"peer_id": pid, "query": query, "response": response})
     except Exception as e:
-        _handle_error(e, "peer", pid)
+        _handle_chat_error(e, "peer", pid)
 
 
 @app.command()