Per maintainer ruling on #3196, eval agent() now defaults to non-isolated regardless of task.isolation.mode, mirroring the task tool. isolated=true is the only way to turn it on; isolated=true while task.isolation.mode === "none" still throws the same clear error.
Updated tests, workflow-notice.md, and Python agent() docstring to reflect the strict opt-in contract. Existing isolation tests now pass isolated:true explicitly; the inherit-from-settings assertion is replaced with a default-off + isolated=true opt-in regression.
Fixes#3196
When an isolated apply fails the bridge throws a ToolError and never returns details, so the nested-patch payload that previously lived in details.nestedPatches was unrecoverable after the isolation worktree was torn down.
The bridge now writes each captured nested patch to a file under the per-call artifacts dir (e.g. <agentId>.nested-<index>-<slug>.patch) before throwing and includes the resolved paths in the error message so the caller can apply them manually.
Added a regression test verifying the persisted file exists with the original patch contents and that the path is surfaced in the thrown error.
Fixes#3196
A failed isolated apply (changesApplied === false) previously only set details.isolationSummary and returned the subagent text. Schema-backed agent() calls then parsed the JSON and returned the object, so workflows saw a successful structured result while none of the edits had landed.
Throw a ToolError when mergeIsolatedChanges reports a failed apply, with the merge summary plus a recovery hint pointing at the preserved patch/branch/nested artifacts so the caller can apply manually.
Added regression tests for the schema and non-schema apply-failure paths.
Fixes#3196
Branch-mode isolation can capture nested repository changes without creating a root branch. Eval agent() with apply=false previously treated that shape as no captured changes and returned no recoverable nested patch payload after the isolation worktree was removed.
Expose captured nested patches in EvalAgentResult details and copy them onto JS/Python returnHandle nodes (nestedPatches / nested_patches). Document the return_handle escape hatch and add regression coverage for branch-mode nested-only apply=false runs.
Fixes#3196
Eval preludes now forward returnHandle to the bridge so no-session eval runs can preserve the temp artifacts backing returned agent:// handles. The bridge keeps those temporary artifact directories whenever returnHandle is requested, including non-isolated runs and successful isolated applies.
Branch-mode isolation now treats nested-only changes as merge-eligible even when no root branch was produced, letting callers apply nested patches instead of dropping them when the root repo had no diff.
Added regression coverage for returnHandle artifact preservation and nested-only branch isolation.
Fixes#3196
When agent() ran with schema and apply=false, the bridge correctly returned the captured patch/branch in details, but the preludes only forwarded id/agent/handle/data on the returnHandle node. Structured workflows had no way to recover the artifact for a manual apply.
Both runtimes now copy isolated, patchPath/branchName, changesApplied, and isolationSummary onto the returnHandle node (snake_case in Python, camelCase in JS), keeping null changesApplied so apply=false stays distinguishable from a successful apply. Updated the workflow notice and the Python agent() docstring to point callers at return_handle as the artifact escape hatch for isolated+apply=false runs. Added prelude tests locking the new node shape in both runtimes.
Fixes#3196
The cleanup gate was treating changesApplied===null (apply=false) the same as a clean apply, deleting the temp artifacts dir before returning details.patchPath. Sessions without a session file (which fall back to a per-call tmp dir) ended up with a patchPath pointing at a removed file, defeating the documented manual-apply path.
Tightened the cleanup condition to remove the temp dir only on a confirmed clean apply (changesApplied===true); apply=false and failed applies both keep the artifact for the caller.
Added regression tests for the apply=false preserve case and the apply-succeeds cleanup case.
Fixes#3196
Kept isolation merge/apply summaries out of agent() text when a schema is supplied so Python and JS eval helpers can still parse the JSON payload. The summary now lands in details.isolationSummary for callers that need the human-readable apply state.
Added a regression test that exercises an isolated schema-backed eval agent with a merge summary.
Fixes#3196
The workflowz eval path bypasses the task tool's isolation wrapper and
calls runSubprocess() directly, so parallel agent() fan-outs that edit
overlapping files all land in the parent worktree.
Extends the eval agent bridge schema with isolated/apply/merge, forwards
them through the Python and JS preludes, and adds a shared
task/isolation-runner.ts so the lifecycle (prepare context → run in
worktree → capture patch/branch → merge → cleanup) is implemented once
for both TaskTool and the bridge.
Default mirrors task.isolation.mode: isolated by default when settings
allow it, off when mode === 'none'. isolated=False explicitly disables;
isolated=True with mode === 'none' errors out to match the task tool.
apply=false keeps captured changes inside the worktree and surfaces the
patch path / branch name in details. merge=false forces patch mode even
when task.isolation.merge === 'branch'.
Fixes#3196
- Inlined the temporary model status formatting logic directly into the controller.
- Removed the unused `formatTemporaryModelStatus` utility function and its associated test.
- Update `shouldRetry` to treat `EISDIR` and `ENOTDIR` as terminal errors, preventing unnecessary retries when encountering Git reference directory conflicts.
- Add a test suite to verify graceful resolution of branches in scenarios where a packed ref conflicts with a directory path in the filesystem.
- Added `includeWorkspaceTree` configuration setting to optionally render the workspace directory tree.
- Configured the system prompt template and SDK to respect this toggle, allowing users to disable the tree to prevent prompt cache invalidation.
- Promoted `write` and `find` tools to `essential` status to ensure they are always available regardless of discovery mode.
- Updated `DEFAULT_ESSENTIAL_TOOL_NAMES` to include these tools by default.
- Updated documentation and tests to reflect the change in default essential tool availability.
Fixes#3165
- Synchronize tool arguments with the component state upon receipt of `tool_execution_start` to ensure visual consistency when final update events are missed.
- Terminate active argument reveal streams to prevent late ticks from overwriting valid, fully-materialized tool arguments with stale partial data.
- Add test coverage to verify that tool UI components render finalized arguments even in the absence of intermediate streaming updates.
- Implemented `tab.ariaSnapshot()` to capture and represent page structures as ARIA-tree YAML.
- Introduced `tab.ref()` and ref-based selector parsing to enable precise element interaction via unique ARIA identifiers.
- Integrated automated script bundling for cross-environment evaluation of ARIA snapshot logic.
- Updated browser action methods to resolve and target elements using ARIA-ref handles.
- Overhauled stealth spoofing mechanisms for WebGL, screen dimensions, Web workers, and iframe contexts using prototype-aware injection.
- Centralized function string representation patching to improve mimicry of native browser behavior across global objects.
- Patched puppeteer-core to remove detectable evaluation markers and implement lazy, pull-style execution context management.
- Enabled support for capturing LLM request JSON dumps and adjusted launcher flags to improve organic request patterns.
- Replaced the `/debug dump-next-request` command with an updated `/dump` command that exports LLM request context to JSON sidecar files.
- Removed persistent debug path state and manual path configuration in favor of automated generation.
- Updated session logic to handle serializing LLM request context to temporary directories.
- Refactored testing suites to remove path-based debug tests and verify dynamic request file generation.
- Update `llama.cpp` base URL to remove the `/v1` suffix.
- Consolidate local provider token validation in `coding-agent` using a `Set`.
- Add test coverage to ensure catalog model IDs are preserved verbatim on the wire.
`omp --approval-mode=yolo acp` was rewritten to `launch --approval-mode=yolo
acp`, swallowing `acp` as a launch prompt so the yolo override never reached the
ACP command path (the ACP permission gate from #2097 stayed in always-ask).
`resolveCliArgv` only inspected `argv[0]`, so any leading global option flag hid
the real subcommand. It now scans past leading flags using the launch parser's
value-consumption contract (a flag's value is never mistaken for the subcommand,
e.g. `--model acp`) and hoists the recognized subcommand to the front with the
flags preserved as its own argv. Genuine launch prompts are untouched.
The flag value-consumption rule is factored into `cli/flag-tables.ts`
(`flagConsumesValue` + the shared `isUnknownLongValueCandidate`) so the resolver
and the profile bootstrap share one source of truth.
Fixed permission mode not respected in ACP mode ([#2970](https://github.com/can1357/oh-my-pi/issues/2970))
Fixes#2970
The background message reader matched every incoming message against the
pending client-request map by id before checking for a `method`. Server
request ids live in the server's own id space and routinely collide with
the client's in-flight request ids, so a server-originated
`workspace/configuration` pull whose id matched a pending request (e.g. a
basedpyright pull landing while a `documentSymbol` request with the same
id was open) was swallowed as a bogus response: the client request
resolved with `undefined` and the pull was never answered, wedging
servers that gate analysis on configuration.
Route any message carrying a `method` as a server request (or
notification) before id-matching responses, so every config pull is
answered under lazy init -- parity with the warmup/reload path, which
escaped the bug only because it issues no concurrent semantic request
while the cold-start pulls drain. lsp.lazy default is unchanged.
Fixes#3001
The plugins docs advertise `omp list`/`omp remove` as top-level commands,
but only `omp install` is registered. `resolveCliArgv` rewrote any
unregistered first-arg to `launch`, so `omp list` silently started an
interactive agent session with "list" as the LLM prompt instead of
managing plugins.
Reserve the bare, documented-but-unregistered plugin verbs `list` and
`remove` with a helpful hint pointing at the real `omp plugin list` /
`omp plugin uninstall <name>` commands (same `extensions` mechanism /
same class as the `install` leak fixed in #1496/#1498). Multi-word
prompts that merely begin with those words still route to `launch`, so
genuine prompts are unaffected.
Fixes#2935
Updated /mcp enable and /mcp disable so they connect or disconnect only the named server instead of reloading every MCP server in the session. Added regression coverage for both toggle directions and updated the coding-agent changelog.
Fixes#3157
- Updated `render`, `renderMany`, and native snapcompact methods to return promises, ensuring scalable async execution.
- Refactored `transformProviderContext` and `buildSideRequestContext` to support asynchronous operations in agent loops.
- Integrated `Promise.all` for improved concurrency when processing frame rendering and rendering batch operations.
- Updated all internal call sites, SDK hooks, and test suites to accommodate the asynchronous API signatures.
- Added validation to scan for non-ASCII characters before performing snap-compaction, falling back to LLM-based summarization if the unrenderable ratio is too high.
- Updated event handling and status reporting to explicitly support snapcompact actions, including specific error warnings and cancellation states in the UI.
- Updated session logic to default to snapcompact strategy when auto-compaction is enabled.
- Stop the Esc key from aborting active background maintenance (compaction, handoff, or retry) while a subagent is focused.
- Remove "(esc to cancel)" hints from maintenance loaders when a subagent is active to avoid false affordance.
- Ensure that main-session maintenance remains cancellable via Esc when no subagent is focused.
Fixes#2819
Adds 'c copy' to the completed /btw panel footer (alongside b branch / Esc
dismiss), copying the sanitized visible answer to the clipboard. The copy
shortcut is guarded by canCopyBtw + main-editor focus + empty editor.
Sanitized MCP server names before status formatting so configured keys cannot leak home paths, tabs, newlines, or oversized text into the TUI.
Fixes#3150
Shows live per-command status (plan/goal/loop/model/advisor/collab/jobs/
context/...) in the slash-command autocomplete.
Adjustments on merge:
- Exclude the two .github/pr-assets/*.png screenshots.
- Resolve the autocomplete.ts conflict keeping main's skill-command empty-prefix
boost alongside the new static-vs-display description split.
- Compute the live display description lazily — only once a command actually
matches (name or alias) — instead of for every command on each keystroke, and
guard the getter with a typeof check. getAutocompleteDescription reads live
session state, so the eager call was O(commands) work per refresh.
CI caught that flooring by the raw local estimate falsely triggers compaction on
thinking-heavy turns: estimateTokens counts the opaque thinkingSignature /
redactedThinking payloads (providers bill them on replay, #2275), but their local
byte size diverges wildly from what the provider actually charges — so a turn
with a large encrypted-reasoning blob but small provider usage would trip the
floor (broke agent-session-handoff 'provider-anchored usage' test).
estimateTokens now takes { excludeEncryptedReasoning } and the compaction floor
(#estimateStoredContextTokens) uses it: the floor counts only reliably-countable,
on-wire-compressible content (text, tool results, tool calls), while the provider
usage arm of compactionContextTokens still accounts for encrypted reasoning. This
keeps the encrypted-reasoning case provider-anchored while still flooring upward
when a before_provider_request hook compresses tool results.
A before_provider_request extension (a context-compression proxy like Headroom,
an obfuscator, or inline snapcompact) can shrink the outgoing request below the
real stored conversation. The provider then reports deflated prompt tokens, so
the auto-compaction threshold never fires and the stored history grows unbounded
until it overflows the context window and can no longer be compacted at all.
Add compactionContextTokens(provider, storedEstimate) = max(provider, estimate)
and apply it to both the pre-prompt and post-response compaction decisions,
flooring the provider-reported tokens by the agent's own estimate of the stored
conversation. Display and cost accounting still use exact provider usage; only
the compaction trigger takes the floor.
- Added `buildSideRequestContext` to the `Agent` class to generate prompt-cache-friendly provider contexts.
- Updated ephemeral side-channel turns to forward the full tool catalog to maintain prompt cache hit rates.
- Injected a `developer` role reminder into ephemeral turns to instruct the model to suppress tool calls.
- Implemented automatic post-processing to strip any tool calls from ephemeral turn responses.
- Exported message and dialect helper functions in `agent-loop.ts` to support context construction.
Emitted MCP connection lifecycle events through the startup event bus so the TUI can replace the initial connecting banner with connected, pending, or failed server state.
Added manager and interactive-mode coverage for mixed success/failure MCP startup updates.
Fixes#3150
- Added a set to track tool result IDs that have been rewound to ensure they are not re-appended to the session history.
- Updated message handling logic to conditionally skip persistence for tool results associated with active rewind operations.
- Implemented message deduplication in `AdvisorRuntime` to collapse verbatim re-injected primary context (plan rules/approved plans) between turns.
- Reduced token consumption by replacing identical primary context segments with a status marker.
- Updated history formatter to allow expansion of load-bearing context types specifically, while retaining one-line summaries for other custom messages.
- Fixed session history desynchronization during `rewind` by performing a full context rebuild after applying branch changes.
- Prevented `rewind` tool output and assistant side-channel data from polluting the prompt cache by flushing and sanitizing session state.
- Added explicit test coverage for context reconstruction and assistant message sanitization after rewind events.
- Remove the static "pending" hourglass icon from edit and write tool headers to reduce visual noise.
- Update multi-file status lines to use the active spinner icon directly instead of replacing a static icon, ensuring consistent liveness cues.
roboomp