On Discord, Telegram, Slack and Matrix a plain `/branch` used to rebind the
CURRENT chat/thread's session key to the clone, ending the original session
on that surface. The user could not keep the original path live while
exploring an alternate one — the opposite of what a branch is for.
Now the handler opens a sibling thread through the adapter's existing
`create_handoff_thread` BEFORE cloning (a failed create never orphans a
branch row), binds the thread's own session key to the clone with the
thread's routing columns written at create time, and leaves the origin key
untouched. `/branch --here` keeps the legacy in-place switch; platforms
without threads, DMs, unknown Discord parents and adapters that cannot open
a thread fall back to in-place with a one-line note. The CLI strips the
flag through the same parser so `--here` never becomes a session title.
Destination source shapes mirror each adapter's inbound key (Discord keys
threads on their own id; Telegram/Slack/Matrix on the parent chat), the
same rules the CLI->platform handoff uses.
Live repro (real gateway + real Slack adapter against a stand-in Slack
Socket Mode/Web API): base ends the origin session and rebinds its key;
fixed posts the thread seed, replies "this chat stays on it", the origin
thread keeps its session and the follow-up typed in the new thread lands on
the branch (parent_session_id = origin).
Design and first implementation by Angello Picasso (#66014, #66024);
this is a slim port onto the split slash_commands_* layout.
Co-authored-by: Angello Picasso <angello.picasso@devsu.com>
Two more production AIAgent() sites (same class as #85153) never passed
reasoning_config, so agent.reasoning_effort was ignored there. The /compress agent
uses the gateway's session-aware resolver (session /reasoning > per-model > global),
the curator the shared chokepoint against its review model. Also pins the Feishu
comment-agent sibling shipped earlier on this branch with a test.
Mechanical migration of the `_adapter_for_source` call sites in this sibling. Intake policy sites take `_intake_adapter_for`; every send/edit/typing/pending-slot site takes `_delivery_adapter_for`. Part of #88715 (phase 4).
reset_file_dedup treats a falsy task_id as "all tasks"; mirror the existing
`or "default"` guard from the hermes-mode /compress site at the three forwarded
sites, and shrink the run_turn comment to the one non-obvious fact.
Sibling site of the previous commit: _compress_codex_app_server_session passed
no task_id either, so a manual /compress on a codex_app_server session reset the
"default" bucket and left the live session's read_file dedup armed. Forward the
session row id; one parametrised test covers both codex entry points through
the real compress_context against the real read tracker.
The SQL chain step (#114287) stopped a `_reset_from` child of a compression-ended parent
from winning tip projection. The Python twin had the same blind spot:
`_is_compression_child_row` / `_compression_lineage_root` treated the reset fork as a
continuation, so `get_compression_lineage(tip)` collapsed to `[tip]` (ancestors lost for
prompt-cache scope and export) and the fork shared the lineage's turn-lease key. Both now
ask `_is_explicit_fork_child_row(include_reset=True)`; `get_compression_lineage`'s own
early return keeps excluding only branch/delegate/tool so a reset child that later
compresses still walks forward to its children.
Gateway bare `/resume` lists with `order_by_last_active=True`: a lineage compressed for
days is projected onto its live tip and belongs where the user last touched it, not at
its root's `started_at` (the reporter's tip, active yesterday, was buried under a
September-12 start). Desktop already requests `order=recent`.
Docs: `/resume` row in slash-commands reference. Tests: one lineage-walk invariant, one
/resume ranking invariant, both red on origin/main.
Part of #114271
A committed proactive tool-result prune (`prune_tool_results_only`, driven from
`agent/turn_preflight.py::compress_after_tool_results`) demotes old skill_view and
read_file bodies to one-line markers, but only the full-compaction path called
`_reset_read_dedup_caches`. The repeat-view dedup therefore kept answering
"unchanged / content_returned: false" for content that no longer existed in the
transcript, so the `[SKILL_PRUNED: ... reload with skill_view(...)]` marker asked
for a reload the tool then refused (#112763). Treat the committed prune as the same
content-loss boundary compaction already is: reset the task's read/skill dedup right
where the pruned list is committed.
Sibling surface: manual `/compress` on CLI, TUI and the messaging gateway called
`compress_now()` without `task_id`, so the boundary reset hit the "default" bucket
instead of the session's. Pass the session-scoped task id on all three.
Test double in tests/hermes_cli/test_cli_manual_compress.py gains the `task_id`
kwarg the real `_compress_context` facade already accepts.
Supersedes #103268 (@jo0wz), which reached the same path with a process-global
ghost registry (not task-keyed, skill_view only).
`GatewayRunner` never had a `get_adapter` method, so every gateway `/save`
(Telegram, Discord, ...) rendered the file and then failed with
"'GatewayRunner' object has no attribute 'get_adapter'". Resolve the adapter
through `_adapter_for_source`, the profile-aware lookup the rest of the runner
uses, so multiplex secondaries deliver through their own bot rather than a
missing key on the default map.
Co-authored-by: pierrenode <298902573+pierrenode@users.noreply.github.com>
Co-authored-by: KoNit-K <124019182+KoNit-K@users.noreply.github.com>
Co-authored-by: Baophan00 <109447498+Baophan00@users.noreply.github.com>
The shared core applied `has_content_to_compress(head) is False -> nothing_to_do`
on every surface, where origin/main only had it in the gateway handler. That
predicate only knows the local summarizer's window: on CLI/TUI/ACP,
`_compress_context(force=True)` still routes codex_app_server sessions to native
compaction before any local-compressor check, and `ContextCompressor.compress`
commits the phase-1 tool-result prune / blank-echo drop even when no summary
window exists -- so the gate wrongly skipped real work there. It is now an opt-in
`skip_without_window` that only the gateway passes, restoring each surface's
prior behavior.
Review follow-up on #109610.
CLI, gateway, TUI and ACP each re-sequenced the same chain (partial split -> estimate ->
_compress_context(force=True) -> lock-skip detection -> rejoin tail -> summary), and the
flag set differed per surface: TUI treated `--preview` as a focus topic, ACP ignored
arguments entirely. For the one command that legitimately breaks the prompt cache that
divergence is a correctness problem, not a style one.
`agent/conversation_compression_manual.py::compress_now` owns the sequence; surfaces parse
their own argv, install `after_messages`, re-anchor session ids and render. TUI and ACP gain
`--preview`, `--aggressive` refusal and `here [N]` parity.
Inside a routed satellite's turn the ambient scope is the satellite's, whose
.env has no token or allowlist. Five sites still called `_is_user_authorized()`
directly there — `/topic`, the sibling-thread `/stop` grant, plugin message
injection, Discord voice transcripts and startup auto-resume — so the shared
bot's owner was refused ("not authorized to use /topic") and a satellite that
DID copy an allowlist widened who may drive those commands. They now go through
`_is_user_authorized_for_source`, and `_under_authorization_profile` derives the
transport home from the delivering adapter's owner when ingress did not stamp
one (restored/cached sources).
`_adapters_for_profile` (the resolver behind `_authorization_adapter`,
`_adapter_for_source` and now `_resolve_injection_adapter`) returns the primary
map for a shared-bot satellite: a served profile with the `{}` startup
placeholder, no reconnect pending, targeted by a default-bot route. Kanban and
cron already applied that rule; the gateway's own resolvers returned None, so
heartbeats, process completions, goal notices and delegation results for such
profiles were undeliverable after a restart. A secondary that owns a credential
(connected on any platform, or queued for reconnect) still fails closed.
Two multiplex key/store mismatches in the gateway session layer:
- SessionStore._db_for_key resolved legacy agent:main keys to the AMBIENT
store. Named-profile keys were already pinned to profiles/<x>/state.db
(#97309), but a default-profile session touched inside a secondary's
runtime scope (a coalesced async-delegation drain, a cron mirror into a
default chat, a scoped watcher) was written into the secondary's state.db
— the profile_name='<A>' row inside B's store reported in #102157, after
which the routing index and row disagree and the #54878 self-heal drops a
live conversation. Default keys now resolve to _routing_home/state.db, the
launch home already pinned for the routing index. Single-profile gateways
(multiplex off) keep the ambient store byte-for-byte.
- /undo evicted the cached agent under build_session_key(source) —
agent:main:… — while the cache is keyed by the profile namespace, so on a
secondary profile the eviction missed and the next turn reused an agent
whose in-memory history still held the undone turns. Use
_session_key_for_source like /reset and /retry.
Addresses #102157.
Breaks the two import cycles that forced Protocol stand-ins in the F821 sweep, so the two
sites now name the real types.
gateway/platforms/event.py (new leaf): MessageType, ProcessingOutcome, MessageEvent moved
out of base.py verbatim. Their only dependency is gateway.session.SessionSource; base.py
imported helpers.py at module level, so helpers could not name MessageEvent. Now
TextBatchAggregator is typed by the real MessageEvent. 249 importers repointed
(`from gateway.platforms.base import` -> `.event`, preserving each import's layout);
gateway.platforms.__init__ re-exports from .event. The three revert-scheduled PLUGIN-COMPAT
pointers that named these symbols (gateway.slash_commands → MessageType, dingtalk → MessageType,
photon → ProcessingOutcome) and their COMPAT_MANIFEST rows now target gateway.platforms.event.
Docs updated: ADDING_A_PLATFORM.md, adding-platform-adapters.md (en + zh-Hans).
tools/mcp_tool_sampling.py: ElicitationHandler no longer holds a back-reference to its
MCPServerTask (mcp_tool imports sampling, so the task type cannot be named there). It only
ever read owner._pending_call_context, so it takes `call_context: Callable[[], Context | None]`
and MCPServerTask passes `lambda: self._pending_call_context`. The consent call is one
`functools.partial`, run directly or inside the captured Context.
ty on the 11 touched production files vs origin/main: 0 new diagnostics, 14 resolved.
(The one `source: SessionSource = None` diagnostic moves with the class; typing it Optional
exposes ~60 unguarded call sites — separate follow-up.)
Tests: tests/gateway + tests/plugins + tests/tools + touched files, 18,235 passed; the 31
failures reproduce identically on origin/main (macOS /private/tmp, systemd socket,
long-path fixtures, live-service tests).
Re-applies the gateway compat removal byte-for-byte; see 92d0bd0d73 for the
full inventory (30 re-exports/aliases + 2 shim modules dropped, 3 shim-only
names re-removed, 24 callers + 34 test files repointed). No new changes.
BASE's _compress_codex_app_server_session was the single cache-peek site that read
_agent_cache without a lock when _agent_cache_lock was None (tests/gateway/
test_codex_hygiene_compaction.py::_slash_host relies on it). Every other BASE caller returned
None without a lock. Model that as an explicit lockless_fallback=True at that one call site.
For each issue anchor present in BASE 63279301bc non-test .py and absent on HEAD, the BASE comment/docstring block was re-attached at the HEAD location of the code it explained (matched by the distinctive code line / enclosing def). Sentences already covered by an existing HEAD comment were deduped; the issue number always survives. Insert-only: no code lines changed.
Implicit-concatenation string literals re-wrapped to 100 cols (byte-identical values, verified
by AST constant diff vs base); remaining fitted calls folded. Group now -25.2% LOC.
