Reviewer flagged that ToolExecutionComponent.isTranscriptBlockCommitStable\ntreated any block with a defined #result as commit-stable, so a long\nstreaming SSH partial render could sit on its stable pending header until\nderiveLiveCommitState's stable-prefix ratchet promoted it to native\nscrollback, then the final SSH glyph render would land below and strand a\nduplicate pending header above the settled frame.\n\n- Added ToolRenderer.provisionalPartialResult opt-in for renderers whose\n partial-result chrome differs from the final render.\n- Honored it in ToolExecutionComponent.isTranscriptBlockCommitStable so the\n block stays commit-unstable while isPartial holds and flips stable as soon\n as the result settles.\n- Set provisionalPartialResult: true on the SSH renderer.\n- Added test/tools/ssh-commit-stability.test.ts covering the partial/final\n transition and the non-regression for bash.\n\nFixes #3177
- Kept SSH result frames in the pending state while partial output is streaming.\n- Added renderer coverage for the partial-to-final SSH header transition.\n\nFixes #3177
- sdk-mcp-discovery: `find` became an essential tool (2eef88978), so it can no longer be hidden/rediscovered under `tools.discoveryMode: all`. Switch the discoverable-tool assertions to `search` (still `loadMode: discoverable`).
- agent-session-concurrent: the agent loop now drops tool calls that never reached `toolcall_end` from an aborted turn (0890b2be6, partial args are unsafe to replay). Emit `toolcall_end` before the TTSR rule-driven abort so the labeled placeholder result is minted.
- 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
- Added error handling to docker container and network removal commands.
- Print yellow warning messages to stdout when cleanup commands fail to exit cleanly.
- 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.
- Mocked stdout rows for the AgentTranscriptViewer tests to ensure consistent terminal height.
- Added an afterEach cleanup to restore the original property descriptor for process.stdout.rows.
- 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 the test configuration to specify an explicit compaction strategy.
- Enabled context-full compaction to match expected behavior during tests.
- 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.
- Unify `previousText` resolution to correctly concatenate `textHead` and `textTail` during re-compaction.
- Ensure summary fallback logic correctly handles non-text legacy archives.
- Add test coverage for cross-compaction text retention and legacy archive continuity.
- Enable snapcompact strategy in agent plan reference re-injection tests.
- 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.
- Verified that side-channel turns maintain stable prompt cache parity with main turns.
- Applied secret and tool obfuscation to ephemeral assistant side-channel data to prevent leakage.
- Updated `Agent` and `AgentSession` test suites to validate consistency under native dialect environments.
Mirror of the provider-anchored handoff test: a ~20k-token stored conversation
whose provider usage was deflated to 1k (as a before_provider_request compressor
would) now triggers pre-prompt compaction, proving #estimateStoredContextTokens
floors the decision through the real call-site (not just the helper math).
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
roboomp