MCP server URLs can carry secrets in userinfo
(`https://user:token@host/sse`) or a query string (`?token=...`). A few
connect/validate paths logged the raw `cfg.url` / `request.url`, so those
secrets could land in log files that are often shared or aggregated.
Add a small `_redact_url()` helper that keeps only scheme/host/port/path
and use it at the four sites that log a server or request URL. Logging
only; no other behavior changes.
Maintainer edit: add mocked coverage for the enterprise endpoint and client ID override paths, and document the environment variables users must set before OAuth login.
apply_final_call_ids iterated over all final tool calls, including
non-file-edit tools like read_file. The greedy path-match in
matches_final_tool_call could overwrite a correct unique id with a
stale one from a different streaming state, producing duplicate
tool_use ids that poison the persisted session.
Guard the loop with is_file_edit_tool() so only tracked file-edit
tools (write_file, edit_file, apply_patch) are subject to canonical
id remapping. Non-file-edit tools keep their authoritative id from
get_final_message().
Fixes#4595
Replace the tuple(list[dict], int) return of
Session.retain_recent_legal_suffix with a named RetentionResult
dataclass that exposes retained, dropped,
already_consolidated_count, and new_last_consolidated fields.
The tuple return was easy to misuse because the second value only
made sense relative to the first and the old last_consolidated
cursor. The named fields make the archive-skip semantics explicit
at every call site.
No behavior change. All existing tests pass unchanged in semantics.
Refs #4136
Signed-off-by: axelray-dev <110029405+axelray-dev@users.noreply.github.com>
Treat max_messages as a last-resort replay guard now that consolidation and idle auto-compact own normal history reduction. Raising the default avoids frequent sliding-window prefix churn in moderate conversations without adding a new cache-policy knob.
Combine malformed tool-call handling with placeholder filtering and a
no-tools fallback so a relay that returns tool_use blocks with null
id/name/input can no longer crash a turn or permanently wedge a session.
Adapted to the ContextGovernor architecture (context governance now lives
in nanobot/agent/context_governance.py, not runner.py):
- ToolCallRequest.has_valid_name(): single source of truth for "usable
name" (non-empty string).
- tool_hints.format_tool_hints(): skip tool calls with a non-string/empty
name instead of raising AttributeError on the whole turn.
- ContextGovernor.strip_placeholder_assistant_messages() and
strip_malformed_tool_calls() (plus the _tool_call_name_is_valid helper):
history-cleaning staticmethods invoked at the START of
prepare_for_model() — strip_placeholder, then strip_malformed, then the
existing drop_orphan/backfill chain. Both only repair the model-facing
copy and leave persisted history untouched (return a copy, or the same
list when nothing changes). Also wired into runner's minimal-repair path.
- AgentRunner._drop_malformed_tool_calls(): returns
(dropped, all_dropped, original_finish_reason); clears finish_reason to
"stop" when all calls are dropped.
- AgentRunner._malformed_tool_call_retry_messages() + _request_model
malformed_retry flag: when an all-dropped tool_calls response comes back,
retry once with a corrective note; if the retry STILL comes back
all-dropped, fall back to _request_no_tools for graceful text degradation.
Tests for the history-cleaning methods live with ContextGovernor in
tests/agent/test_runner_governance.py; response-layer and tool-hint tests
stay on AgentRunner / tool_hints.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
list_sessions() silently dropped corrupt session files whose filename
stem was a legacy non-base64 name (e.g. telegram_12345.jsonl from the
old lossy path scheme). The repair path called _repair(fallback_key),
but _repair re-encodes the key via _storage_key(), producing a
different base64 filename that never matches the actual file on disk.
Add an optional path parameter to _repair so callers can pass the
actual file path directly, bypassing the key-to-filename round trip.
Signed-off-by: axelray-dev <110029405+axelray-dev@users.noreply.github.com>
MCPToolWrapper.execute only handled TextContent; every other block was
rendered with str(block). An MCP ImageContent block therefore became a
large base64 string embedded in the tool result, which (a) was truncated
by max_tool_result_chars, corrupting the data, and (b) could never reach a
channel because it was plain text, not an image artifact.
Decode ImageContent (and EmbeddedResource blobs with an image/* MIME type)
and persist them via store_generated_image_artifact, returning the same
compact {artifacts, next_step} JSON the built-in image_generation tool
produces. The base64 stays out of the model context; the model delivers the
saved file via the message tool's media parameter.
After a gateway restart or websocket reconnect, the UI stays stuck in
processing state because reconnecting clients only replay running status
when a turn is active, never push idle when no turn is running.
Fix _hydrate_after_subscribe to always push goal_status (running with
started_at when turn is active, idle when no turn is running) so the
frontend can reset its processing indicator on reconnect.
Also fix cmd_stop reporting 'No active task to stop' when a task is
actually processing by draining the pending injection queue in addition
to cancelling active tasks. This prevents mid-turn injection deadlocks
and gives accurate task counts.
- Removes match_text regex that stripped # comments before pattern matching
(broke on quoted # inside strings)
- allow_patterns now run re.fullmatch against the full lowercased command
- deny_patterns search the original lowercased command
- Replaces comment-stripping test with comment-tail bypass regression
(touch canary # echo allowlisted must be blocked)
- Adds Re-bin regression for quoted hash + blocked command
(echo "#" followed by blocked command must be caught)
- All 10 tests pass
Signed-off-by: axelray-dev <110029405+axelray-dev@users.noreply.github.com>
Extract model-facing context governance from AgentRunner.
Only compact in-flight tool results when the model request is over budget, keep compacted IDs stable within a turn, and allow the newest result to be compacted as a last resort when it is the remaining source of overflow.
maintainer edit: add a regression test for the public ExecTool.execute path so omitted login stays non-login by default, and update the Unix environment docstring to match the new explicit login behavior.
Add fail_on_tool_error to AgentDefaults and wire it through
AgentLoop -> SubagentManager -> AgentRunSpec.
Previously hardcoded to True in SubagentManager._run_subagent.
Now configurable via config.json with default True for backward
compatibility. When set to False, subagents can retry on minor
tool errors instead of immediately failing.
Changes:
- nanobot/config/schema.py: add fail_on_tool_error field (default True)
- nanobot/agent/subagent.py: accept and forward fail_on_tool_error
- nanobot/agent/loop.py: pass config through to SubagentManager
- tests/agent/test_subagent.py: add regression test
Signed-off-by: axelray-dev <110029405+axelray-dev@users.noreply.github.com>
Widen thinking_style from Literal to str | None and add a
@field_validator that produces a helpful error message listing
valid options when an invalid value is provided.
Addresses the review feedback on #4482.
ProviderConfig.thinking_style defaults to None (Optional field), but
create_dynamic_spec expects a string. Coalesce None to "" at all call
sites (factory.py, settings_api.py) and fix the test assertion to
expect None from the config default.
When dream.enabled is false, the Dream cron job never runs, so the
dream cursor (.dream_cursor) stays at its initial value (0). This
causes read_recent_history_for_prompt() to treat every history entry
as unprocessed, injecting the full chat history into every system
prompt and growing without bound.
Fix: fast-forward the dream cursor to the latest history entry at
gateway startup when Dream is disabled.
The onboard wizard dispatched field handlers by bare field name, so
WebSearchConfig.provider was hijacked by the LLM-provider handler and
showed LLM providers instead of search engines. Keenable was also never
wired into the CLI wizard when it landed in the WebUI.
- Add a single source of truth for selectable search providers
(SEARCH_PROVIDER_OPTIONS in web.py); WebUI settings now import it.
- Add a WebSearchConfig-aware search-provider picker to the wizard and
resolve handlers by (model type, field name) so the LLM and search
provider fields no longer collide.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
richText messages only kept rich_text_list items whose type was
"text", so bold/italic/inlineCode/pre segments were silently dropped;
a message made entirely of formatted segments produced empty content
and fell through to the "unsupported message type: richText" warning.
Now any item carrying text is kept (matching the SDK's own
get_text_list, which keys off the "text" field) and its type is mapped
to Markdown so the formatting survives into the agent's context.
Text and downloadCode within a rich-text item are handled
independently (the SDK treats them as separate via get_text_list /
get_image_list), so an item carrying both a caption and an attachment
no longer drops the file.
The shared httpx.AsyncClient was created without a timeout, so all
requests (including large file/image downloads) used httpx's 5s
default and hit ConnectTimeout/ReadTimeout on uploads. Set an explicit
httpx.Timeout (connect=10s, read/write=30s).
Adds regression tests for formatted-segment preservation, the
all-formatted no-drop case, the text+downloadCode item, and the client
timeout configuration.
Closes#4497
The enabledTools allowlist was only enforced for MCP tools returned by
session.list_tools(). Resources and prompts from session.list_resources()
and session.list_prompts() were registered unconditionally, allowing a
deny-all or restrictive enabledTools config to leak resource and prompt
capabilities to the model.
Now resources and prompts are only registered when allow_all_tools is
true (default ["*"] wildcard). Any explicit tool restriction — including
enabledTools: [] (deny-all) or a list of specific tool names — also
blocks resource and prompt registration from that server.
Fixes#4435
maintainer edit: Telegram Web cannot render sendRichMessage payloads, so keep the rich path available only for explicit opt-in instead of enabling it by default.
Xubin Ren
xiaweiwei67-stackandXubin Ren
yu-xin-candXubin Ren
chengyongruandXubin Ren
04cbandXubin Ren
axelray-devandXubin Ren
codedragonandXubin Ren
yorkhellenandXubin Ren
r4sk1nandXubin Ren
chengyongruandXubin Ren
Max HsuandXubin Ren
michaelxerandXubin Ren