- Centralized thinking block demotion logic using `renderDemotedThinking` across all model providers.
- Updated `transformMessages` to default to text-based demotion for foreign thinking content.
- Restricted foreign thinking preservation to explicitly supported targets with `zai` thinking formats.
- Refactored message transformations and updated test suites to validate standardized demotion outcomes.
- Removed "running" status and hub hint details from the subagent badge text.
- Updated relevant status line tests to expect the simplified badge format.
Surfaced non-recovering advisor prompt failures through session notices so provider errors like OpenRouter ZDR endpoint rejection are visible in the main session.
Fixes#3635
- Updated `reconcileTitleCasing` to ignore purely uppercase words when restoring source casing.
- Restricted restoration logic to mixed-case identifiers (e.g., `TinyVMM`, `iOS`) to avoid overriding the model's clean sentence case with emphatic user shouting.
- Added regression tests to ensure all-caps input does not trigger title re-shouting.
- Implement `renderDemotedThinking` to encapsulate reasoning from prior turns when switching models across providers.
- Render reasoning in the target model's canonical thinking dialect (e.g., Markdown fences) to preserve context while ensuring the blocks are processed as reasoning.
- Use a neutral `<think>` tag fallback for models where canonical native formatting risks leaking incompatible chat-template instrumentation tokens.
- Added `tiny` as a first-class model role to override online models for lightweight background tasks.
- Updated session title generation, auto-thinking difficulty classification, unexpected-stop detection, and mnemopi backend to resolve via the `tiny` role before falling back to `smol`.
- Updated configuration schema and documentation to reflect the new role precedence.
- Introduce `resolveWithThinkingLoopCook` to manage automated retries for detected model thinking-loop stalls.
- Update `complete` and `completeSimple` to utilize the new retry orchestrator instead of direct stream resolution.
- Configure `pi-native-server` to respect the `loopGuard` option flag.
- Enable a final unguarded pass for persistent stalls after the retry budget is exhausted to ensure generation completion.
On a long subagent-heavy run the TUI thought stream froze for 1.5–4 s
at a time, with the loop watchdog blaming `subagent:*` phases and the
log carrying ~1,255 `Skipping mid-run compaction because turn persistence
is out of order` debug lines per session (issue #3629).
`#persistTurnMessagesForMidRunCompaction` and the persistence-check
helpers it calls were doing two O(n²) things per `onTurnEnd`:
1. Every call rebuilt the branch path via `SessionManager.getBranch()`
(O(branchSize) `unshift` per call), once per turn message twice (once
in `#sessionMessageAlreadyPersisted`, once in
`#hasPersistedLaterTurnMessage`).
2. Every pairwise message comparison serialized full message content
through `#messageValueSignature` (=`JSON.stringify`), even though
the content was almost always orthogonal to the identity decision.
Replace the structural comparator with a stable persistence key
(timestamp + role-specific discriminators) extracted to a sibling module
`session/turn-persistence.ts` and drive the planner off one snapshot of
the branch built per `onTurnEnd`. Content equality is retained as the
slow-path tiebreaker for the rare case where two messages collide on the
cheap key (e.g. two assistant turns at the same millisecond with
`undefined` responseId — the shape the test harness emits).
The new helpers (`sessionMessagePersistenceKey`, `planTurnPersistence`,
`sameMessageContent`) are pure functions covered by direct unit tests
in `test/turn-persistence.test.ts`; the existing mid-run / eager
compaction integration tests prove the end-to-end behavior is preserved.
Fixes#3629
Coerced missing scope on installed_plugins.json entries to user before suppressing them, matching listClaudePluginRoots semantics, so users carrying registries written before the scope field still see marketplace plugins hidden from plugin list and doctor.
Fixes#3628
Derived marketplace runtime package names from plugin IDs when package.json is absent, preserving suppression for config-only marketplace installs. Added regression coverage for package-less LSP plugin installs in plugin list and doctor.
Fixes#3628
Compared marketplace runtime entries by realpath before suppressing link-only plugin-manager entries. Added a regression where a local runtime link reuses a marketplace package name but points at a different path.
Fixes#3628
Filtered marketplace-managed runtime symlinks out of the npm plugin listing and OMP extension-package status provider while keeping marketplace installs available to the runtime loader. Added regressions for both duplicate surfaces.
Fixes#3628
- Added formatAdvisorContextPrompt to render project context files into the advisor's system prompt.
- Updated AgentSession to accept and inject advisorContextPrompt into the session system prompt.
- Registered project context files for the advisor to ensure the reviewer evaluates the agent against standing project instructions like AGENTS.md.
Resolved live ACP generate_image payloads through the blob store before emitting image content while keeping rawOutput compact.
Added regression coverage for content[] image blocks and details.images entries without duplicating blob refs as fallback text.
Fixes#3623
Expanded environment variable placeholders in Claude marketplace plugin MCP url and headers before registration. Added a regression test covering context7-style HTTP server headers.\n\nFixes #3621
- advisor-toggle: the advisor role now falls back to the slow priority
chain when modelRoles.advisor is unset, so enabling the advisor with no
explicit model now resolves one and activates. Assert the inactive-but-
enabled path via an explicit unresolvable advisor model override.
- acp-builtins: dropped the /move happy-path test that ran the real
command (setProjectDir -> process.chdir into a temp dir) then removed
the dir, leaving the process cwd unlinked and poisoning every later file
in the chunk with CurrentWorkingDirectoryUnlinked when Bun.Transpiler
initialized in rewrite-imports.
- Update `acp-builtins.test.ts` to support interactive session movement and path session file testing.
- Clarify `/move` command routing in `/move` slash command tests.
- Rename internal `search` references to `grep` to align with product definitions.
- Refactor TUI render tests to use `Promise.withResolvers` for cleaner flow control.
- Added `resolveAdvisorRoleSelection` to handle the advisor role's distinct configuration logic.
- Implemented `rolePriorityDefaults` to allow the advisor role to alias the `slow` model priority chain.
- Updated `AgentSession` to utilize the new advisor-specific resolution logic during session operations.
- Added new Gemini flash-lite and 3.5-flash variants to the priority list.
- Included additional OpenAI codex model versions in the slow priority configuration.
- Update `umans-provider` test to remove references to deprecated GLM 5.1 model.
- Rename search tool reference to `grep` in `advisor` test.
- Improve test stability in TUI components by explicitly draining `setImmediate` queues before flushing terminal state.
- Clarified the advisor's role to focus on strategy, proactive course correction, and user advocacy.
- Expanded guidance on identifying churn and handling agent drift or premature completion.
- Instructed the advisor to avoid redundant advice and allow the agent space to iterate.
Initialized the Z.AI Streamable HTTP MCP session before calling web_search_prime and preserved the returned session id on subsequent requests.
Added regression coverage for the authenticated MCP request sequence.
Fixes#3619
- Redesigned the Todo HUD as a connector tree with fixed-budget stage previews.
- Anchored status and HUD containers to prevent redundant UI elements in terminal scrollback.
- Implemented tree-based rendering for project phases and tasks while removing dynamic border rules.
- Upgraded `sherpa-onnx` and related packages to support current infrastructure.
Address PR #3602 review feedback from chatgpt-codex-connector:
when a stdin read carries the empty bracketed paste followed by
a trailing keystroke (a user pressing Enter right after Cmd+V),
the pre-fix paste path was fire-and-forget. The trailing byte
processed synchronously while the clipboard image read was still
pending, so submit ran against an empty pendingImages and the
image landed on the next draft instead.
CustomEditor now tracks in-flight pastes with #pasteInFlight and
buffers subsequent input into #pendingInput. #trackAsyncPaste
increments the counter, awaits the paste promise, decrements, and
drains the queue through handleInput (so requeueing still works
if a drained chunk triggers another async paste).
For an assembled paste whose remaining bytes are present in the
same call, those bytes are pushed onto #pendingInput before the
async paste starts, so they always run AFTER it settles. The
text-paste branch stays sync and drains its own queue inline.
New repro test asserts the call ordering: paste:start fires, the
queued Enter does NOT, and only after the paste promise settles
does Enter dispatch.
- Enhanced the edit renderer to support visual tracking of delete and move/rename operations.
- Updated diff computation to correctly handle file-level changes and suppress erroneous "No changes" warnings.
- Improved terminal output with a clearer activity indicator and accurate state representation during multi-file operations.
- Extended the rendering pipeline to display source-to-destination paths for file renames and added validation tests for edit workflows.
- Added `rewrite-changelog.ts` and `fix-changelogs.ts` utilities to automate the consolidation of release notes using LLM-assisted processing.
- Updated multiple internal changelog files by consolidating redundant entries and improving phrasing for readability.
- Implemented `previewLine` utility in `coding-agent` to prevent visual spillover in status rows by managing text truncation and whitespace.
- Updated `package.json` with new workflow scripts for managing package-level change histories and documentation indexes.
- Updated task rendering to use `previewLine` for truncating descriptions consistently.
- Ensured progress and result descriptions are truncated before formatting.
can1357