- Added `AgentSession.freshSession()` to rotate provider-facing IDs and prune provider stream state.
- Added `/fresh` command handling in the builtin registry and mode command flow.
- Kept persisted session metadata intact during `/fresh` and cleared transient IDs on session switches.
- Invalidated `appendOnlyContext` and provider caches when refreshing provider state.
- Lazy-loaded OTEL SDK, HTML export, TTSR, and autoresearch modules.
- Made resolveMemoryBackend async to import backends on demand.
- Replaced backend resolution with direct settings reads for rekey checks.
- Made "auto" the default, hiding MCP tools past 40-tool threshold.
- Centralized discovery mode resolution in shared mode helper.
- Activated search tool in createAgentSession once full registry exists.
- Added image-reference rendering to make `[Image #N]` placeholders clickable in chat.
- Added MIME-aware image blob materialization with extensioned sidecar paths.
- Added clickable path, line, and URL hyperlinks for read, search, and fetch outputs.
- Hardened OSC8 hyperlink emission with URI validation and control-byte/idempotency checks.
Add retry.modelFallback so users can keep automatic retry enabled while preventing retry recovery from switching through configured fallback model chains.
The default remains enabled, preserving existing fallback behavior. When disabled, retry still honors retry-after delays and retry limits while staying on the primary model.
Op: correct
Restores: spec:retry can stay enabled without automatic model switching
AgentSession now stores the same scoped AsyncJobManager reference that tools receive: owning top-level sessions use their constructed manager, subagents inherit the parent's manager, and secondary in-process top-level sessions get no manager when a singleton is already live.
getAsyncJobSnapshot and ACP delivery drains now use that scoped manager instead of AsyncJobManager.instance(), so secondary sessions cannot report or drain the primary session's background jobs. The regression test covers a secondary session created while the primary has a Main-owned running job.
- Added AES-GCM cache for at-rest broker snapshots keyed on token, with URL as additional data.
- Added `onSnapshot` hook to RemoteAuthCredentialStore for persisting applied snapshots.
- Exposed cache read/write and TTL defaults through the coding-agent re-exports.
- Added `getAuthBrokerSnapshotCachePath` with `OMP_AUTH_BROKER_SNAPSHOT_CACHE` override.
Any in-process secondary createAgentSession() (e.g. the Agent Control Center's create flow in agent-dashboard.ts) was constructing its own AsyncJobManager, overwriting the process-global singleton, and then clearing it on its own dispose. The primary session still held its #ownedAsyncJobManager reference, but AsyncJobManager.instance() was undefined for the rest of the process — the task async path hard-failed with "Async execution is enabled but no async job manager is available" and only a full restart cleared it.
- sdk.ts: skip constructing/installing a second AsyncJobManager when a singleton is already live, so secondary top-level sessions share the owning session's manager instead of clobbering it.\n- agent-session.ts: scope #cancelOwnAsyncJobs so a secondary session inheriting the singleton with the default MAIN_AGENT_ID can no longer cancel the primary session's running bash/task jobs at dispose time. Subagents still reach the inherited singleton via their unique agent ids; the owning session still cancels its own jobs through #ownedAsyncJobManager.
Fixes#1923
- Stopped leaking absolute home directory to the model in ttsr-interrupt and ttsr-tool-reminder blocks.
- Rendered rule paths as cwd-relative in-project, `~`-relative under home, else raw.
Mid-session edits to hindsight.bankId / bankIdPrefix / scoping kept the
active HindsightSessionState pinned to the bank selected at session
start, so retain/recall/reflect calls landed in the stale bank. Settings
hooks now fire onHindsightScopeChanged; the backend rebuilds the
primary state against the recomputed scope, disposing the previous one
after flushing its queue so queued tool-initiated retains still land in
the bank they were enqueued for.
Also:
- Renamed ensureBankMission to ensureBankExists. The old version
skipped creation entirely when bankMission was blank, so the first
mental-model POST (auto-seed) could land against a never-PUT bank.
Bank creation is now idempotent and unconditional, and runs before
mental-model bootstrap.
- Fixed AgentSession.dispose to flush the retain queue BEFORE clearing
the session state pointer. Reversed, HindsightRetainQueue.#doFlush's
identity guard would see the cleared pointer and drop the spliced
batch with a 'session vanished' warning.
- Snapshotted hindsightScopeCallbacks before iterating because each
rebuild subscribes a fresh callback inside the same fire; iterating
the live Set would spin.
Fixes#1902
- Marked steering user messages and wrapped them pre-LLM so the model sees a `` envelope.
- Kept transcripts and persisted history with the user's original raw text.
- Restored `AssistantMessageComponent` stable-prefix completion API.
- Registered and triggered a session-switch reconciler during init and after switch.
- Rebuilt resume flow to restore plan/goal mode state and clear stale mode flags.
- Marked fallback and context-promotion model switches ephemeral and skipped them on restore.
- Added regression tests for temporary model ordering, fallback precedence, and mode cleanup.
- Removed early FTS-only return so prefix and substring matches merge.
- Sorted merged results globally by prompt recency before limiting.
- Added /force, /copy, and /shake tips.
Centralized append-only context auto-mode resolution so SDK sessions, interactive sessions, and the status display use the same provider checks. Auto mode now enables for Xiaomi/SGLang hosts and explicit stored-request compat signals while preserving DeepSeek behavior.
Added focused regression coverage for Xiaomi Token Plan SGLang HiCache endpoints and explicit on/off behavior.
Fixes#1851
- Added `isReadOnlyAgent` and `READ_ONLY_TOOL_NAMES` to classify agents.
- Marked read-only agents and forbade edits, commands, and reasoning offload.
- Added tests for capability classification and description rendering.
- Renamed `TodoWriteTool` to `TodoTool` and its source/prompt files.
- Updated tool registration, schema, renderers, and gating to `todo`.
- Adjusted cursor provider native tool names and tests to match.
- Renamed strike-animation constants and `todo-error-reminder` type.
- Added `IndexedSessionStorage` with `SessionStorageBackend` for index-based storage reads.
- Removed `readTextSync` from the public `SessionStorage` API and sync backends.
- Changed Redis and SQL backends to warm `{size, mtimeMs}` metadata and read via `readTextSlices`.
- Added per-path write queues and `drain()` to serialize operations and surface first failures.
- Classified each session's final message as done, interrupted, aborted, error, or pending from a 32 KiB tail read.
- Rendered the status as a colored segment on the session metadata line.
- Added `peekFileTail` and `readTextSuffix` across storage backends to read file tails in one pass.
- Simplified `MemorySessionStorage` to a string array mirror with a sidecar mtime map.
- Added shared `getReadToolPath` API to extract paired read `path` values for protection matchers.
- Added `createPlanReadMatcher` and session wiring so compaction prune/shake keeps active plan reads intact.
- Updated `todo-write` instructions to initialize every user-supplied plan item as an individual task.
- Added compaction tests validating plan reads are protected from prune and shake while regular reads are still removable.
- Added optional `AgentTool.matcherDigest(args)` hook so tools can expose plain source text instead of wire-encoded arguments to TTSR rule matchers.
- Implemented `matcherDigest` on edit (all modes: hashline, patch, apply_patch, replace) and write tools, stripping patch prefixes and JSON escaping.
- Added `TtsrManager.checkSnapshot()` to replace the scoped buffer with a tool digest rather than appending raw deltas.
- Fixed TTSR conditions never matching streamed edit/write calls whose wire format obscured real content.
- Added `parseClaudeRateLimitHeaders` to extract 5h/7d utilization from `anthropic-ratelimit-unified-*` response headers.
- Added `AuthStorage.ingestUsageHeaders` to warm the per-credential usage cache from headers, throttled to 60s per key.
- Merges header-derived limits onto the last full usage report, preserving per-tier data not present in headers.
- Wires ingestion into `AgentSession` on each Anthropic response to reduce direct OAuth `/usage` probes.
- Derived Anthropic and session metadata `device_id` from `getInstallId()` deterministically.
- Added CLAUDE bootstrap identity lookup and merged fallback into token exchange/refresh.
- Recovered `accountId` and `email` during token exchange/refresh when token payloads lacked them.
- Enforced bootstrap failures for non-OK responses and invalid JSON payloads.
Treat temporary model_change roles as non-restorable when resuming sessions so context-promotion and retry-fallback models do not override the saved default.\n\nFixes #1649
Try the last active role model first, then the saved default model when the role model cannot be restored during session switching or startup resume.\n\nFixes #1649
Use the last model_change role when resuming an existing session instead of always restoring models.default. Covered both /resume switchSession and startup continue paths.\n\nFixes #1649
- Changed `AgentOutputManager` to use requested names verbatim, adding `-2`/`-3` suffixes only on repeats (e.g. `Anna`, `Anna-2`).
- Renamed main agent id from `0-Main` to `Main`; nested ids now use dot notation without numeric prefix (e.g. `Parent.Child`).
- Updated task widget to render dotted hierarchy as `Parent>Child` breadcrumb without leading index.
- Resume scan now tracks seen names instead of a counter to avoid clobbering prior outputs.
- Enabled resume picker to preload sessions and toggle folder/all scope with Tab.
- Enabled resume flow to fall back to all-project sessions and switch cwd on resume.
- Added centralized applyCwdChange to refresh caches, commands, and UI after cwd updates.
- Updated session restoration to adopt restored session cwd and sessionDir when present.
- Fixed `session_id` never being created or populated; every history row had `NULL` for session.
- Added schema migration (`ALTER TABLE history ADD COLUMN session_id`) for pre-existing databases.
- Wired interactive mode to call `setSessionResolver(...)` so prompts are stamped with the active session at submission time.
- Re-enabled session ranking in `--resume` and in-session pickers via `matchingSessionIds()`, merging fuzzy and prompt-history signals.
Switch the pre-prompt token estimate to computeNonMessageTokens so the guard sees the same system-prompt, tool-schema, and skills accounting as /context. Without tool tokens, sessions with large MCP tool sets stayed below the compaction threshold while the outbound request was over the model limit.
Refs #1618
Include pending prompt messages in the pre-send context estimate so auto maintenance runs before providers reject over-limit requests. Suppress auto-continue when maintenance runs inline for an active prompt.
Fixes#1618
When Zed provisions MCP servers through `session/new.mcpServers`, the
ACP agent
correctly connects to them and registers their tools via
`refreshMCPTools`, but
the tools were never activated. `refreshMCPTools` builds the next
active tool
set from `getSelectedMCPToolNames()`, which — with discovery disabled —
returns
only MCP tools already in the active set. Since ACP sessions start with
no MCP
tools, this created a circular deadlock: tools could only become active
if they
were already active.
Added an optional `{ activateAll?: boolean }` parameter to
`refreshMCPTools`.
When true, every newly registered tool is force-activated regardless of
prior
selection. `AcpAgent#configureMcpServers` passes `activateAll: true` on
both
call sites so client-provisioned tools are immediately usable.
- Dropped `summarizeShakeRegions`, the shake-summary prompt, and related types.
- Removed `shake-summary` compaction strategy and `providers.shakeSummaryModel` setting.
- Migrated existing `shake-summary` configs to plain `shake` on load.
- Simplified `/shake` to `elide` and `images` modes only.
- Added +Nk/+Nm turn-budget parsing with whitespace-boundary matching, multipliers, and hard `!` indicator.
- Added per-turn budget lifecycle plus APIs (`getTurnBudget`, `recordEvalSubagentUsage`) and hard-cap checks in eval runs.
- Added hard budget observability in eval preludes and docs by exposing `budget.hard` and documenting ceiling modes.
- Fixed streaming preview stutter with max-row tracking and padding, with tests for preview height and budget parsing.
can1357