Add interactive chat REPL with persistent sessions

[rejojer]

Summary

Introduces openkb chat, a multi-turn conversation REPL for the knowledge base. Conversations are automatically persisted to .openkb/chats/<id>.json and can be resumed across invocations. Also bundles a handful of adjacent cleanups that were surfaced while building it.

Main feature

• New openkb chat CLI command with --resume [ID] (latest or by id / unique prefix), --list, --delete ID, and --no-color.
• Built on prompt_toolkit: bottom toolbar, styled prompt, Ctrl-C aborts current response while Ctrl-D / /exit quit cleanly.
• In-REPL slash commands: /exit, /clear (start a fresh session, previous is kept on disk), /save [name] (export markdown transcript to wiki/explorations/), /help.
• Streams the agent response with the same visual language as openkb query (dim tool-call lines flush against the preceding text, blank line separating a tool batch from the following response paragraph).
• Header mirrors the Claude Code layout: brand-colored title with version, then <kb dir> · <model> · session <id>, then a short key hint.
• Resume view shows prior turns compactly (older turns collapsed to ... N earlier turns omitted).
• Reuses the existing build_query_agent so tool behavior is identical to single-shot query.

Prompt / agent polish bundled in

• Fix a copy-paste bug where the Q&A and lint agents were told to "Write all wiki content in X language" — they don't write wiki content. Switched to "Answer in X" and "Write the lint report in X".
• Give all three agents an "OpenKB" identity so the model introduces itself consistently.
• Finish the Q&A search-strategy step on summaries (tell the model to follow full_text when a summary is too thin), move the get_image "when to call" guidance into the tool docstring, and reword step 5 to refer to the tool by name.

Refactor bundled in

• Normalize get_page_content naming: rename the helper in openkb.agent.tools to get_wiki_page_content (matching the *_wiki_* sibling convention), rename the agent-side wrapper from get_page_content_tool to get_page_content so the tool name the model sees matches what the instructions have always said, drop the lazy-import workaround, and fix a stale test assertion.
• Derive openkb.__version__ from installed package metadata (importlib.metadata) so pyproject.toml is the single source of truth for the version string.

Test plan

• openkb chat from a kb root starts a new session, header renders, prompt works
• Single-turn question streams a response, tool-call lines render dim, blank-line spacing is correct
• Multi-turn: follow-up questions ("what about that?") use conversation context
• /save writes a readable transcript to wiki/explorations/
• /clear starts a fresh session; previous shows up in openkb chat --list
• Ctrl-C during streaming aborts the current response but keeps the REPL alive
• Ctrl-D / /exit quit with the friendly goodbye message
• openkb chat --resume picks up the latest session; --resume <prefix> resolves a unique prefix
• openkb chat --list and --delete <id> work
• Existing openkb query still works (shared agent)
• pytest tests/test_agent_tools.py tests/test_query.py passes (31/31 locally)

[rejojer]

Code review

Found 2 issues:

1. openkb chat --resume (and --list) sorts by creation time rather than activity — list_sessions uses key=lambda x: x.name to sort by filename (the creation-timestamp id), but resolve_session_id's docstring promises __latest__ returns "the most recently updated session id". record_turn does update updated_at, but sorting ignores it. After a user resumes an older session and keeps chatting, openkb chat --resume (flag value __latest__) still picks the most recently created session, not the most recently active one.

OpenKB/openkb/agent/chat_session.py

Lines 130 to 179 in e1207f4

	def list_sessions(kb_dir: Path) -> list[dict[str, Any]]:
	"""Return session metadata dicts, newest first (by id, which is timestamp-prefixed)."""
	d = chats_dir(kb_dir)
	if not d.exists():
	return []
	out: list[dict[str, Any]] = []
	for p in sorted(d.glob("*.json"), key=lambda x: x.name, reverse=True):
	try:
	data = json.loads(p.read_text(encoding="utf-8"))
	except (json.JSONDecodeError, OSError):
	continue
	out.append(
	{
	"id": data.get("id", p.stem),
	"title": data.get("title", ""),
	"turn_count": data.get("turn_count", 0),
	"updated_at": data.get("updated_at", ""),
	"model": data.get("model", ""),
	}
	)
	return out
	def resolve_session_id(kb_dir: Path, query: str) -> str | None:
	"""Resolve a query to a full session id.
	``query`` may be:
	- ``"__latest__"`` — returns the most recently updated session id.
	- A full session id — returned as-is if it exists.
	- A unique prefix of a session id — expanded to the full id.
	Returns ``None`` if no session matches. Raises ``ValueError`` when a
	prefix is ambiguous.
	"""
	sessions = list_sessions(kb_dir)
	if not sessions:
	return None
	if query == "__latest__":
	return sessions[0]["id"]
	for s in sessions:
	if s["id"] == query:
	return s["id"]
	matches = [s["id"] for s in sessions if s["id"].startswith(query)]
	if len(matches) == 1:
	return matches[0]
	if len(matches) > 1:
	raise ValueError(
	f"Ambiguous session prefix '{query}' matches: {', '.join(matches)}"
	)
	return None

2. Pressing Ctrl-C at the prompt exits the entire REPL — the header says "Ctrl-C to abort current response", but run_chat()'s main loop catches KeyboardInterrupt around prompt_async() and just returns. The practical effect: a single accidental Ctrl-C while typing the next message exits the whole chat. Only Ctrl-C inside _run_turn should count as "abort response"; Ctrl-C at the prompt should clear the current input line and continue the loop (Ctrl-D / /exit are the exit paths).

OpenKB/openkb/agent/chat.py

Lines 337 to 346 in e1207f4

	while True:
	try:
	user_input = await prompt_session.prompt_async()
	except KeyboardInterrupt:
	_fmt(style, ("class:header", "\nBye. Thanks for using OpenKB.\n\n"))
	return
	except EOFError:
	_fmt(style, ("class:header", "Bye. Thanks for using OpenKB.\n\n"))
	return

🤖 Generated with Claude Code

_{- If this code review was useful, please react with 👍. Otherwise, react with 👎.}

[rejojer]

Code review

No issues found. Checked for bugs and CLAUDE.md compliance.

🤖 Generated with Claude Code

_{- If this code review was useful, please react with 👍. Otherwise, react with 👎.}

[rejojer]

Superseded by #18 (same content, rebased into logical commits, plus a new commit sanitizing base64 image payloads from persisted chat history).