`long_task` registers a sustained objective, but `AgentRunner` would
still exit with `stop_reason="completed"` when the LLM produced a final
text response without calling `complete_goal`. This defeated the purpose
of sustained goals.
Add `goal_active_predicate` and `goal_continue_message` to `AgentRunSpec`.
When the predicate returns `True` at the natural completion checkpoint,
inject a continuation message via the existing `_try_drain_injections`
machinery, forcing the runner to continue looping.
Also extract the default continuation prompt to
`nanobot/utils/runtime.py` alongside the existing recovery-message
builders.
Drop the legacy unified-diff patch parameter and all related parsing/
generation logic (_parse_patch, _generate_patch, _apply_hunks, etc.).
The tool now accepts only the structured `edits` array, eliminating the
intermediate diff-string round-trip.
Also update file_edit_events tracking and tests to work exclusively
with edits.
Benchmark (zhipu glm-5.1, edits mode): 15/15 cases passed.
- Remove suppress(Exception) from poll loop and message processing; add
logger.exception so inbound errors are visible.
- Check both ret and errcode on send to avoid silent drops when iLink
returns ret != 0 with errcode == 0.
- Proactively refresh context_token via getconfig before sending if the
cached token is older than 60s. This prevents message loss on long
agent turns and cron pushes without relying on complex retry logic.
Refs: openclaw/openclaw#61174, NousResearch/hermes-agent#21011
Link nanobot.wiki documentation in 10 languages from README header:
English, 简体中文, 繁體中文, Español, Français, Bahasa Indonesia,
日本語, 한국어, Русский, Tiếng Việt.
Updates docs/image-generation.md and skills/image-generation/SKILL.md to
include MiniMax configuration examples, supported aspect ratios, and
troubleshooting references. Also updates the supported provider list to
include minimax alongside openrouter, aihubmix, and gemini.
Adds ImageGenerationProvider ABC with shared __init__, _http_post(), and
_require_images(). Introduces _IMAGE_GEN_PROVIDERS registry with
register/get/image_gen_provider_configs() helpers.
Four existing providers (OpenRouter, AIHubMix, Gemini, MiniMax) now inherit
from the base class and self-register. Adding a new provider only requires
writing one class + one registration line.
Eliminates if/else chains in the tool dispatch and hardcoded provider config
dicts in commands.py (3 sites) and nanobot.py (1 site). Fixes the agent CLI
command missing image_generation_provider_configs entirely.
Also simplifies test monkeypatch targets to patch the registry lookup.
Extract the [M] Model Presets interactive CRUD screen from PR #3696
and adapt it to the current main branch schema (fallback_models
instead of fallback_presets). Adds preset cache, field handlers for
model_preset/provider/fallback_models, and 9 new tests.
Add remark-breaks plugin so that single newlines in assistant messages
(such as /help output) render as line breaks instead of being collapsed
into a single paragraph by standard markdown behavior.
Runtime context (time, channel, sender) changes every turn, so placing
it before user content invalidated the prompt-cache prefix. Appending it
after user content keeps the prefix stable and improves KV cache hit
rates. The stripping logic in _save_turn was simplified from 16 lines
to 6 as a side benefit.
Update identity.md, TOOLS.md, skills README, and skill-creator
SKILL.md to remove mentions of the removed glob tool. Grep's
glob parameter remains documented where relevant.
GlobTool is redundant — GrepTool already supports glob-based file
filtering via its `glob` parameter, making a standalone glob-only
tool unnecessary. Removing it simplifies the tool surface and reduces
LLM confusion between glob and grep.
Slack hand-rolled the same generate_code + format_pairing_reply + send
sequence already in BaseChannel._handle_message. Replace with
delegation to _handle_message(is_dm=True), matching Feishu's pattern.
Removes 3 unused imports (generate_code, format_pairing_reply,
PAIRING_CODE_META_KEY) from slack.py.
- Remove TOCTOU exists() check in _load(); rely on FileNotFoundError
- Define PAIRING_CODE_META_KEY and PAIRING_COMMAND_META_KEY constants
in nanobot.pairing, replacing magic strings across base.py, slack.py,
and builtin.py
- Flatten nested revoke logic in handle_pairing_command()
- Trim redundant docstring/comment noise in is_allowed() and generate_code()
CLI pairing commands (list/approve/deny/revoke) are fully replaceable by
`nanobot agent -m "/pairing ..."`, which routes through the same
CommandRouter and handle_pairing_command() backend. Removing them
cuts 86 lines of duplicate surface area without losing any functionality.
- Remove pairing_app and its 4 subcommands from cli/commands.py
- Update format_pairing_reply() to drop the "Via CLI" line
Previously _validate_allow_from raised SystemExit when allowFrom was
missing, forcing every channel to declare an explicit allowlist.
With the pairing feature this is no longer necessary: a channel with
no allowFrom simply operates in pairing-only mode, letting users
approve senders via /pairing approve <code> from the WebUI or CLI.
- Replace SystemExit with an info log in _validate_allow_from
- Add test_validate_allow_from_allows_missing_allow_from
- Assert pending_user_turn is cleared from session metadata after
shortcut commands (e.g. /help) in test_auto_compact.py.
- Add test for None allow_from / allowFrom values in
test_base_channel.py to prevent TypeError regressions.
- Clear pending_user_turn after shortcut command persistence
- Guard is_allowed against None allow_from values
- Update pairing help text for two-arg revoke
- Reuse format_expiry in CLI pairing list
- AgentLoop._state_command now persists user message and assistant
response for shortcut commands (e.g. /pairing) so WebUI history
hydration after _turn_end no longer shows an empty chat. /new is
excluded because it intentionally clears the session.
- Feishu _on_message sends pairing codes for unauthorized DMs before
any media side effects (reactions, downloads, transcription).
Group chat unauthorized senders are still silently ignored early.
- Update test_feishu_reply to assert the new DM pairing behavior.
Update format_pairing_reply() to be more conversational and explicitly
mention both ways an owner can approve:
- In-chat: /pairing approve <code>
- CLI: nanobot pairing approve <code>
/pairing is now a first-class built-in command dispatched through
CommandRouter, just like /status, /model, /dream, etc.
Benefits:
- WebUI automatically shows /pairing in the slash command palette
(because builtin_command_palette() feeds /api/commands).
- All channels (Telegram, Discord, WebSocket, etc.) use the same
dispatch path for /pairing; no more channel-level interception.
- The command still only works for already-authorised users because
is_allowed() gates message ingestion before the bus.
Changes:
- Add handle_pairing_command() to nanobot.pairing.store — pure
function callable from CLI, CommandRouter, and tests.
- Add cmd_pairing to nanobot.command.builtin and register in
BUILTIN_COMMAND_SPECS + register_builtin_commands().
- Remove BaseChannel._handle_pairing_command() and the /pairing
interception logic from _handle_message().
- Clean up unused pairing imports from base.py.
- Add unit tests for handle_pairing_command and cmd_pairing dispatch.
Feishu was doing its own is_allowed check before _handle_message
without considering is_dm, so unrecognised p2p senders were silently
ignored instead of receiving a pairing code.
- Remove the early self.is_allowed() return so BaseChannel can handle
permission checks and pairing uniformly.
- Pass is_dm=chat_type == "p2p" to _handle_message so DM pairing
works for Feishu/Lark private chats.
WebSocket already authenticates clients at handshake time via token
or issued-token validation. Setting is_dm=True caused unrecognised
clients to receive a pairing code after they had already passed
token auth, which is nonsensical for a browser-tab client.
Treat WebSocket as non-DM so pairing is never offered; access control
remains at the WS handshake level (allow_from + token gate).
- Extract format_pairing_reply() and format_expiry() to eliminate
duplication between BaseChannel and SlackChannel.
- Use _write_text_atomic() from helpers.py instead of hand-rolled
fsync logic in pairing store.
- Convert approved lists to in-memory sets for O(1) lookup.
- Remove collision retry loop (8-char entropy is sufficient).
- Fix /pairing command parsing to split prefix exactly.
- Remove unused import time from base.py.
- Fix tests to pass subcommand_text, not full /pairing string.
- Add os.fsync with Windows-compatible directory flush in pairing store
- Increase pairing code length from 6 -> 8 characters for higher entropy
- Remove SystemExit on empty allowFrom; empty list now defers to pairing
- Update is_allowed docstring to document pairing fallback semantics
- Propagate is_dm to Matrix (direct rooms) and Slack (im channels)
- Slack _is_allowed now checks pairing store for DM allowlist mode
- Fix /pairing revoke to accept optional channel argument
- Move inline import time to module top-level
- Add WebSocket comment explaining is_dm=True assumption
- Add comprehensive tests for store and BaseChannel pairing integration
- Fix existing tests that expected empty allowFrom to hard-exit
Refs #3774
Replace the file-editing onboarding workflow with a chat-native pairing flow:
- New pairing store (nanobot/pairing/store.py) persists approved senders
and pending codes in ~/.nanobot/pairing.json.
- DM messages from unknown senders receive a short pairing code instead of
silent denial. Group chats remain silently ignored.
- Existing allowFrom semantics are fully preserved; approved pairing users
are merged at runtime so no config migration is needed.
- nanobot pairing list/approve/deny/revoke CLI commands for bootstrap and
emergency management.
- /pairing slash commands intercepted in-channel so owners can approve
senders without leaving the chat.
- is_dm flag added to BaseChannel._handle_message; Telegram, Discord and
WebSocket updated to pass it.
Closes#3768
Shortcut commands (e.g. /help, /pairing) skip BUILD and SAVE states,
so their turns were never persisted to the session. This caused WebUI
chats to appear empty after _turn_end because history hydration reads
from the session file.
Fix by persisting the user message and assistant response inside
_state_command, but tag them with _command=True so Session.get_history
filters them out of LLM context. /new is excluded because it
intentionally clears the session.
- AgentLoop._persist_user_message_early now accepts **kwargs so
_state_command can pass _command=True for the user turn.
- Session.get_history skips messages with _command=True.
Register handlers for im.chat.member.bot.added_v1 and
im.chat.member.bot.deleted_v1 to silence "processor not found"
errors that appear when any bot is added to or removed from a group.
Closes#3772
When the primary model returns a non-transient error and no content
has been streamed yet, the runner now tries each model listed in the
active preset's fallback_models in order. Each fallback model may
reside on a different provider — a temporary provider instance is
created on-the-fly via make_provider(config, model=...).
Key design:
- Failover is request-scoped (does not affect subagents/dream/consolidator)
- Provider is restored via try/finally after each fallback attempt
- Skipped when content was already streamed to avoid duplicate output
- Recursive failover prevented by clearing fallback_models on fallback spec
- Circuit breaker trips open after 3 consecutive primary failures (60s cooldown)
- Cross-provider routing: fallback model prefix (e.g. groq/) determines provider
Fixes: cross-provider fallback was broken because the factory passed the
original preset (with provider forced to primary's provider) when creating
fallback providers. Now uses provider="auto" so the model string prefix
correctly routes to the right provider.
Also fixes: log messages now distinguish between primary-failed,
previous-fallback-failed, and circuit-open scenarios.
closes: https://github.com/HKUDS/nanobot/issues/3376
The ask_user tool used AskUserInterrupt(BaseException) for mid-turn
blocking, creating heavy coupling across runner, loop, and session
management. The model now asks questions naturally in response text,
the turn ends normally, and the user's next message starts a new turn
with session history providing continuity.
Removed:
- nanobot/agent/tools/ask.py (tool, interrupt, helpers)
- tests/agent/test_ask_user.py
- webui/src/components/thread/AskUserPrompt.tsx
- AskUserInterrupt handling in runner.py
- Dual-path message building in loop.py
- Pending ask detection via history scanning
- button_prompt/buttons emission in WebSocket channel
- ask_user references in Slack channel docstrings
Preserved (MessageTool uses these independently):
- OutboundMessage.buttons field
- Channel button rendering (Telegram, Slack, WebSocket)
Remove unused code confirmed dead via vulture scan, grep verification,
and coverage analysis:
- _get_bridge_dir (cli/commands.py): 82-line function with zero callers
- add_assistant_message (agent/context.py): method body never executed,
also removed now-unused build_assistant_message import
- _tool_parameters_schema (agent/tools/base.py): redundant copy of schema
already exposed via the `parameters` property
- MSTEAMS_REF_TTL_S (channels/msteams.py): unused constant (production
uses config.ref_ttl_days directly); inlined in test
- MESSAGE_TYPE_USER (channels/weixin.py): unused constant
- Add `ModelPresetConfig` schema for named model presets
- Add `model_presets` dict to `Config` and `model_preset` field to `AgentDefaults`
- Add `resolve_preset()` to return effective model params from preset or defaults
- Add `@model_validator` to reject unknown preset names
- Update `_match_provider()` to use resolved preset model/provider
- Update `make_provider()` and `provider_signature()` to use `resolve_preset()`
- Add `model_preset` property to `AgentLoop` for atomic runtime switching
- Update `AgentLoop.from_config()` to inject a runtime `default` preset
- Wire self-tool to inspect/clear preset state
- Update CLI display strings to show active preset
This commit implements a progressive refactoring of the tool system to support
plugin discovery, scoped loading, and protocol-driven runtime context injection.
Key changes:
- Add Tool ABC metadata (tool_name, _scopes) and ToolContext dataclass for
dependency injection.
- Introduce ToolLoader with pkgutil-based builtin discovery and
entry_points-based third-party plugin loading.
- Add scope filtering (core/subagent/memory) so different contexts load
appropriate tool sets.
- Introduce ContextAware protocol and RequestContext dataclass to replace
hardcoded per-tool context injection in AgentLoop.
- Add RuntimeState / MutableRuntimeState protocols to decouple MyTool from
AgentLoop.
- Migrate all built-in tools to declare scopes and implement create()/enabled()
hooks.
- Migrate MessageTool, SpawnTool, CronTool, and MyTool to ContextAware.
- Refactor AgentLoop to use ToolLoader and protocol-driven context injection.
- Refactor SubagentManager to use ToolLoader(scope="subagent") with per-run
FileStates isolation.
- Register all built-in tools via pyproject.toml entry_points.
- Add comprehensive tests for loader scopes, entry_points, ContextAware,
subagent tools, and runtime state sync.
- Append [Archived Context Summary] to system prompt instead of injecting
it into the user message runtime context, improving KV cache reuse across
turns and avoiding consecutive same-role messages.
- _last_summary persists in metadata (no pop) for restart survival;
summary is re-injected every turn via the stable system prompt.
- Remove dynamic "Inactive for X minutes" from _format_summary — use
static last_active timestamp instead to preserve KV cache stability.
- Pass session_summary through build_messages() so both normal and
ask_user paths receive the archived summary in the system prompt.
- estimate_session_prompt_tokens now reads _last_summary from metadata
to include the summary in token budget estimation.
- Remove obsolete session_summary parameter from
maybe_consolidate_by_tokens and estimate_session_prompt_tokens
call sites in loop.py (summary flows through build_messages instead).
- Ensure /new (session.clear()) clears _last_summary from metadata.
The for loop at line 168 never executes because start is assigned
i + 1 immediately before slicing messages[start : i + 1], which
is always an empty list. Remove the dead code.
Fixes#3716
- TurnContext now carries a turn_id (session_key:time_ns)
- All state transition debug logs include [turn_id] prefix
- RuntimeError messages also include turn_id for observability
- State handlers now return event strings ('ok', 'dispatch', 'shortcut')
- Driver loop uses _TRANSITIONS lookup table: (state, event) -> next_state
- State graph is centralized and visible at a glance
- Added StateTraceEntry to record per-state timing and events
- Driver loop logs state duration + event at debug level
- Exception paths are traced with error field for observability
- Fix _assemble_outbound on_stream type annotation (Callable[[str], Awaitable[None]] | None)
- Use last_msg consistently in _state_save instead of re-indexing
- Remove dead fallback in _state_respond (guaranteed non-None by _state_save)
- Change pending_summary type from Any to str | None
- Make session optional in TurnContext to avoid redundant fetch
- Add defensive dispatch with RuntimeError for missing handlers
- Pop model and context_window_tokens from extra kwargs before
forwarding to __init__, allowing callers like _run_gateway to
pass snapshot-derived values instead of config defaults
- _run_gateway now explicitly passes model/context_window_tokens
from provider_snapshot to preserve pre-refactor behavior
Extract duplicated bus/provider/loop initialization from CLI commands
(serve, _run_gateway, agent) and Nanobot facade into a single
AgentLoop.from_config() classmethod.
- Remove _make_provider() from cli/commands.py and nanobot.py
- Remove inline provider creation in all three CLI entry points
- AgentLoop.from_config() creates MessageBus, calls make_provider(),
and assembles AgentLoop with all standard config-derived parameters
- Supports **extra overrides for callers that need custom args
(e.g. cron_service, session_manager, provider_snapshot_loader)
- Update tests to mock make_provider at nanobot.providers.factory
and add from_config classmethod to _FakeAgentLoop fixtures
This is PR 1/4 of the model-preset feature decomposition.
The previous implementation popped _last_summary from session.metadata
after injecting it into the prompt, then saved the session. This caused
the summary to be permanently lost after a process restart, making the
AI forget archived context and appear to ignore memory or reference
non-existent previous messages.
Replace the destructive pop with a _last_summary_used sentinel:
- _last_summary stays in metadata for restart survival
- _last_summary_used prevents duplicate injection within the same turn
- Clear the sentinel whenever a new summary is generated
Updates tests to match the new persistence behavior.
Add CLAUDE.md at the repository root to orient future Claude Code
instances, and split detailed constraints into .agent/:
- .agent/design.md — architectural constraints (core small, duplication
over abstraction, minimal changes, explicit over magical)
- .agent/security.md — workspace/SSRF/shell sandbox boundaries
- .agent/gotchas.md — config ${VAR}, Windows compat, templates,
heartbeat virtual tool call, atomic writes, ruff format warning,
skills extension point
Also updates .gitignore to not ignore .agent/.
Fixes two related input-handling bugs in the onboard wizard:
1. _input_text treated "" as None, preventing users from clearing
optional string fields or entering empty strings intentionally.
2. _input_model_with_autocomplete used `if value else None`, which
discarded falsy values such as empty strings or 0.
To support clearing optional string fields, add _is_str_or_none() and
normalize empty strings to None inside _configure_pydantic_model only
when the field annotation is `str | None`. Required str fields keep
"" as a valid value.
Also included:
- Remember last selected item in provider/channel/model menus for
better UX when configuring multiple items.
- Rename _SIMPLE_TYPES and _MENU_DISPATCH to lowercase to follow
Python naming conventions (they are local variables, not constants).
- Remove unused imports in test file.
Extracted from PR #3358.
PR introduced module-level logger in static methods, which drops
the channel context bound by BaseChannel.__init__. Revert to
self._channel.logger / self.logger to preserve log labels.
Also remove @staticmethod since these methods legitimately need
instance access (F821 was the real issue, not the logger source).
Follow-up to PR #3651:
- Replace logger.error with logger.exception inside except blocks
so stack traces are no longer lost:
- providers/transcription.py (5 occurrences)
- agent/tools/mcp.py (1 occurrence)
- Replace stdlib logging.getLogger with loguru logger in
providers/openai_compat_provider.py for consistency.
asyncio.create_task in connect_mcp_servers creates child tasks for
each MCP server, but close_mcp calls stack.aclose() from the main
task. anyio CancelScope requires enter/exit in the same task, so the
cross-task exit raises RuntimeError which gets silently caught. The
orphaned cancel scope keeps retrying via call_soon on every event
loop tick, consuming 100% CPU.
Fix: remove create_task/gather and connect servers sequentially in the
caller task. MCP servers are typically 1-2, so parallel connection
provides negligible benefit while introducing the cancel scope hazard.
Closes#3638
- Correct api_key type hint to str | None in _post_transcription_with_retry
- Remove unreachable final return ""
- Fix test_openai_missing_api_key_short_circuits to actually test
missing-key path (use audio_file fixture so file exists)
- Fix PermissionError patch for Windows (patch class method instead
of instance attribute)
Adds Olostep (https://www.olostep.com) as an optional web_search backend
using the official olostep Python SDK (client.answers.create()).
Changes:
- pyproject.toml: adds olostep>=0.1.0 optional dependency
- schema.py: adds olostep to provider comment in WebSearchConfig
- web.py: adds _search_olostep() with lazy import and provider branching
- docs/configuration.md: documents Olostep setup under web search config
- tests: unit tests for the new provider
Backward compatible: existing users see no behavior change unless they
opt into provider: "olostep". No hard dependency at runtime path.
Co-authored-by: umerkay <umerkk164@gmail.com>
When deployed with Docker and workspace mounted as a volume, sending
media files failed because relative paths (e.g. output/image.png) were
not resolved against the workspace directory. The process CWD differs
from the workspace in containerized environments, causing os.path.isfile
checks to fail in channel handlers. Normalize relative media paths at
the MessageTool entry point using get_workspace_path().
MCP resource/prompt/tool names containing spaces or special characters
(e.g. "PostgreSQL System Information") were forwarded verbatim to model
provider APIs, causing validation errors from both Anthropic and OpenAI
which require names matching ^[a-zA-Z0-9_-]{1,128}$.
Add _sanitize_name() that replaces invalid characters with underscores
and collapses consecutive underscores. Applied in MCPToolWrapper,
MCPResourceWrapper, MCPPromptWrapper constructors and the enabled_tools
filtering logic.
Closes#3468
When the main agent spawns multiple sub-agents, each completion
independently triggered a new _dispatch, causing 3-4 user-visible
responses instead of a single comprehensive report.
- Extend _drain_pending to block-wait on pending_queue when sub-agents
are still running, keeping the runner loop alive for in-order injection
- Pass pending_queue in the system message path so subsequent sub-agent
results can still be injected mid-turn via a new dispatch
- Add ISO-639 pattern validation (2-3 lowercase letters) to schema
- Normalize empty language to None in provider constructors
- Extract shared httpx mock stubs, parameterize provider tests
- Add test for language=None omitting field from multipart body
- Add test for Pydantic pattern validation rejecting invalid codes
ZhiPu API returns code 1302 with Chinese text "速率限制" instead of
standard HTTP 429 + "rate limit", causing the retry engine to treat
it as non-transient and fail immediately.
- Fix critical plain-text fallback that was sending raw HTML tags to
users: keep raw markdown available for the fallback path
- Extract TELEGRAM_HTML_MAX_LEN (4096) constant to replace hardcoded
magic number and document the difference from TELEGRAM_MAX_MESSAGE_LEN
- Add fallback to _send_text for extra HTML chunks when HTML parse fails
- Add missing @pytest.mark.asyncio decorator on
test_send_delta_stream_end_html_expansion_does_not_overflow
Replaces inline dedup logic with the existing helper to match the
style of _is_self_address and other reject branches, and to keep the
_processed_uids eviction logic in one place.
The previous fix hardcoded session_key_override as channel:chat_id which
broke unified session mode where pending queues use "unified:default".
Propagate the effective key from _set_tool_context through SpawnTool
into the origin dict so _announce_result routes to the correct pending
queue in both normal and unified session modes.
When mid-turn message injection (PR #2985) was introduced, the pending
queue routing uses the effective session key to match incoming messages
against active sessions. Subagent results, however, use channel="system"
which produces a session key of "system:feishu:ou_..." instead of the
main agent's "feishu:ou_...", causing the result to bypass the pending
queue and be dispatched as a competing independent task.
Fix: set session_key_override to the original channel:chat_id so
_effective_session_key returns the correct key and the subagent result
gets routed into the main agent's pending queue.
Cron jobs now pass on_progress=_silent to process_direct, matching
the heartbeat pattern. Previously, tool hints and streaming deltas
were published to the user channel via bus during execution, but the
final response could be rejected by evaluate_response — leaving users
with confusing partial output and no conclusion.
Closes#3319
When chat_with_retry returns an error response (finish_reason='error')
instead of raising an exception, archive() previously treated the error
message as a valid summary and wrote it to history.jsonl, while the
original session data was already cleared by /new — causing irreversible
data loss.
Fix: check finish_reason after the LLM call and raise RuntimeError on
error responses, which naturally falls through to the existing raw_archive
fallback. This preserves the original messages in history.jsonl instead
of losing them.
Fixes#3244
- Extract synthetic user message string to module-level constant
- Tighten comments in _snip_history recovery branch
- Strengthen no-user edge case test to verify safety net interaction
When _snip_history truncates the message history and the only user message
ends up outside the kept window, providers like GLM reject the resulting
system→assistant sequence with error 1214 ("messages 参数非法").
Two-layer fix:
1. _snip_history now walks backwards through non_system messages to recover
the nearest user message when none exists in the kept window.
2. _enforce_role_alternation inserts a synthetic user message
"(conversation continued)" when the first non-system message is a bare
assistant (no tool_calls), serving as a safety net for any edge cases
that slip through.
Co-authored-by: darlingbud <darlingbud@users.noreply.github.com>
Three improvements to Dream's memory consolidation:
1. Per-line git-blame age annotations: MEMORY.md lines get `← Nd` suffixes
(N>14) from dulwich annotate. SOUL.md/USER.md excluded as permanent.
LLM uses content judgment, not just age, to decide what to prune.
2. Dedup-aware Phase 1 prompt: reframed as dual-task (extract facts +
deduplicate existing files) with explicit redundancy patterns to scan for.
Validated through 20 experiments (exp-002 prompt + max_iter=15 was best,
averaging -1643 chars/5.4% compression per run).
3. Phase 1 analysis as commit body: dream git commits now include the full
Phase 1 analysis for transparency via /dream-log.
4. max_iterations raised from 10 to 15: 30% improvement over 10 with no
risk; 20 showed diminishing returns (exp-020: -701 vs exp-017: -1643).
- Pass resolved self.context_window_tokens to Consolidator instead of
raw parameter that could be None, preventing consolidation failures
- Calculate percentage against input budget (ctx - max_completion - 1024)
instead of raw context window, consistent with Consolidator/snip formulas
- Pass actual max_completion_tokens from provider to build_status_content
- Cap percentage display at 999 to prevent runaway values
- Add tests for budget-based percentage and cap behavior
- Check both jwt and cryptography in MSTEAMS_AVAILABLE guard so
partial installs fail early with a clear message instead of at runtime
- Add aclose() to test FakeHttpClient so stop() won't crash
- Move MSTEAMS.md into README.md following the same details/summary
pattern used by every other channel
- Note in README that validateInboundAuth defaults to false
Warn when validate_inbound_auth is disabled (default) so operators are
aware the webhook accepts unverified requests. Restore pymupdf to the
dev optional-dependencies group — its removal in the original PR was
unrelated to the Teams channel feature.
- Convert skills summary from verbose XML (4-5 lines/skill) to compact
markdown list (1 line/skill) with inline path for read_file lookup
- Exclude always-loaded skills (e.g. memory) from the skills index to
avoid duplicating content already in the Active Skills section
- Skip injecting the Memory section when MEMORY.md still matches the
bundled template (i.e. Dream hasn't populated it yet)
Feishu streaming cards auto-close after 10 minutes from creation,
regardless of update activity. With resuming enabled, a single card
lives across multiple tool-call rounds and can exceed this limit,
causing the final response to be silently lost.
Remove the _resuming logic from send_delta so each tool-call round
gets its own short-lived streaming card (well under 10 min). Add a
fallback that sends a regular interactive card when the final
streaming update fails.
Remove two debug log lines that fire on every idle channel check:
- "scheduling archival" (logged before knowing if there's work)
- "skipping, no un-consolidated messages" (the common no-op path)
The meaningful "archived" info log (only on real work) is preserved.
Remove two debug log lines that fire on every idle channel check:
- "scheduling archival" (logged before knowing if there's work)
- "skipping, no un-consolidated messages" (the common no-op path)
The meaningful "archived" info log (only on real work) is preserved.
When a subagent result is injected with current_role="assistant",
_enforce_role_alternation drops the trailing assistant message, leaving
only the system prompt. Providers like Zhipu/GLM reject such requests
with error 1214 ("messages parameter invalid"). Now the last popped
assistant message is recovered as a user message when no user/tool
messages remain.
Prevent proactive compaction from archiving sessions that have an
in-flight agent task, avoiding mid-turn context truncation when a
task runs longer than the idle TTL.
When a subagent result is injected with current_role="assistant",
_enforce_role_alternation drops the trailing assistant message, leaving
only the system prompt. Providers like Zhipu/GLM reject such requests
with error 1214 ("messages parameter invalid"). Now the last popped
assistant message is recovered as a user message when no user/tool
messages remain.
Prevent proactive compaction from archiving sessions that have an
in-flight agent task, avoiding mid-turn context truncation when a
task runs longer than the idle TTL.
- Use asyncio.to_thread for file I/O to avoid blocking event loop
- Add 200MB upload size limit with early rejection
- Fix file handle leak by using context manager
- Use memoryview for upload chunking to reduce peak memory
- Add inbound download size check to prevent OOM
- Use asyncio.to_thread for write_bytes in download path
- Extract inline media_type detection to _guess_wecom_media_type()
- Use asyncio.to_thread for file I/O to avoid blocking event loop
- Add 200MB upload size limit with early rejection
- Fix file handle leak by using context manager
- Free raw bytes early after chunking to reduce memory pressure
- Add file attachments to media_paths (was text-only, inconsistent with image)
- Use robust _sanitize_filename() instead of os.path.basename() for path safety
- Remove re-raise in send() for consistency with QQ channel
- Fix truncated media_id logging for short IDs
Make Consolidator.archive() return the summary string directly instead
of writing to history.jsonl then reading back via get_last_history_entry().
This eliminates a race condition where concurrent _archive calls for
different sessions could read each other's summaries from the shared
history file (cross-user context leak in multi-user deployments).
Also removes Consolidator.get_last_history_entry() — no longer needed.
history.jsonl may contain non-UTF-8 bytes (e.g. from email channel
binary content), causing auto compact to fail when reading the last
entry for summary generation. Catch UnicodeDecodeError alongside
FileNotFoundError and JSONDecodeError.
chengyongruandXubin Ren
