Commit Graph
397 Commits
Author SHA1 Message Date
Mathews-Tom f2338da9a3 fix(coding-agent): match tree-selector onSelect(entryId, options) contract in ask-reanswer test
Upstream's shift+enter pre-answer feature (merged via upstream/main) changed
TreeSelectorComponent's onSelect callback to accept a second (options)
parameter carrying summarize state. The pickEntry() test helper still called
onSelect with a single argument, so options.summarize threw undefined-object
errors once merged.
2026-07-19 15:05:03 +05:30
Mathews-Tom ab1d7db7d1 Merge remote-tracking branch 'upstream/main' into feat/tree-ask-reanswer
# Conflicts:
#	packages/coding-agent/src/modes/controllers/selector-controller.ts
2026-07-19 15:02:33 +05:30
can1357 32dc282517 test: aligned read-tool and logout tests with landed contracts
- tools.test.ts still asserted the pre-#5812 ±context expansion for offset/
  limit and archive-entry reads; updated to the exact-bounds contract.
- selector-controller-logout.test.ts mocked the old modelRegistry.refresh;
  #5786 switched logout to a provider-scoped refreshProvider(id, 'online'),
  so the mock never resolved and the test timed out.
2026-07-18 21:58:03 +02:00
can1357 157e940d5e Merge PR #5786: fix(auth): scoped post-login model refresh and stripped cache credentials (@roboomp)
# Conflicts:
#	packages/catalog/src/model-cache.ts
2026-07-18 20:14:11 +02:00
can1357 8a25d9e517 Merge PR #5767: fix(coding-agent): clear inline images when disabled (@derekszen) 2026-07-18 20:12:48 +02:00
can1357 17212e22e3 Merge PR #5779: fix(tui): prevent vibe_wait TV-wall scrollback stacking (@roboomp) 2026-07-18 20:12:47 +02:00
can1357 f8cd966406 Merge PR #5988: fix(coding-agent): render ask option previews inline (@metaphorics) 2026-07-18 19:42:50 +02:00
can1357 127cca511a refactor(modes): removed scrollback compaction from TranscriptContainer
- Removed `#compactedChildStart` state, `compactable` segment field, and `#compactCommittedPrefix()` method, stopping the local-frame pruning of committed finalized rows.
- Post-finalize mutations now surface on every render via version tracking, instead of requiring a destructive replay to rehydrate the compacted block.
- Changed `print-mode.ts` to use `session.getLastAssistantMessage()` instead of array tail read, fixing access to terminal assistant messages after compaction removal.
2026-07-18 17:51:45 +02:00
robomp-bot 2300c9ff41 fix(coding-agent): addressed PR review feedback (#5988)
- Kept tall-preview pages inside the selected option row.\n- Compared cached overflow output against the initial width-adjusted render.\n\nNote: pre-existing repository formatting failures in bun check are not addressed by this PR.
2026-07-18 22:29:31 +09:00
robomp-bot 59b9f6568a fix(coding-agent): showed remapped cancel key in ask footer
Ask dialogs accepted the configured cancel binding but always advertised Escape. Derive the compact footer label from the active binding so the displayed key remains actionable.
2026-07-18 20:52:29 +09:00
robomp-bot a741e0b388 fix(coding-agent): rendered ask option previews inline
Rich ask options previously exposed preview content only for the highlighted row. Render every preview beneath its option and keep long content reachable without reviving the split-pane layout.
2026-07-18 20:42:23 +09:00
Derek Zeng 9a452077b2 fix(coding-agent): clear inline images when disabled 2026-07-18 18:12:08 +08:00
roboomp 84c6b6aa58 fix(tui): compact committed finalized transcript history
TranscriptContainer gated committed-prefix compaction on version === undefined, so version-tracked AssistantMessageComponent history never compacted and every stream tick re-walked all N sealed blocks (depth-linear compose).

Compact fully-committed finalized blocks regardless of post-finalize version tracking: their rows are immutable native scrollback the terminal owns. A post-commit mutation no longer recommits on ordinary frames (no duplication) and rehydrates on the next destructive full replay (no loss). Adds the permanent bench/transcript-compose.bench.ts fixture; ratio(N5000/N500) drops 2.30 -> 0.90.

Fixes #5930
2026-07-18 00:52:57 +00:00
Mathews-Tom 737dcb26d7 fix(coding-agent): reach ask re-answer flow from the active leaf in /tree
The interactive /tree selector's own no-op guard ("Selecting the current
leaf is a no-op") fired before ever reaching navigateTree()'s
allowAskReopen path added in 743c8ab7d, so that fix was unreachable from
the actual UI whenever the selected ask toolResult was already the
current leaf (interrupted right after answering, or navigated there by
another caller).

Let a current-leaf selection fall through to the reopen path when the
entry is an ask toolResult, mirroring the same targetIsAskResult check
navigateTree() uses.

Fixed in response to Codex review threads posted as PR review bodies
(not inline comments) on #5895 at 20:24:48Z and 21:54:30Z, which
predate 743c8ab7d and were never addressed.
2026-07-18 05:13:33 +05:30
can1357 ac3d779fad merge PR #5592 via eval/pr-5592: feat(warp): emit native CLI-agent events 2026-07-17 05:29:29 +02:00
can1357 8bdb69254b merge PR #5596 via eval/pr-5596: feat(coding-agent): support per-project model roles
Combined #5586's role-tag precedence with #5596's scope labels in the
selector status messages.
2026-07-17 05:23:49 +02:00
can1357 86b6265ef5 Merge branch 'sweep/2026-07-17' into eval/pr-5592
# Conflicts:
#	packages/coding-agent/test/agent-session-checkpoint-rewind-branch.test.ts
2026-07-17 05:22:52 +02:00
roboomp c654abc980 fix(auth): scoped post-login model refresh and stripped cache credentials
Native /login and /logout (plus setup-wizard sign-in and RPC login)
refreshed model discovery with the default all-provider
online-if-uncached strategy, which reused a fresh authoritative cache row
and never re-ran fetchDynamicModels with the just-persisted credential,
so newly authenticated models stayed unavailable in-session and stale
endpoint data survived a relogin. Each auth-completion path now awaits a
provider-scoped refreshProvider(providerId, "online").

Also fixed writeModelCache serializing credential-bearing request headers
(Authorization, X-Api-Key, api-key, cookie, proxy-authorization) into the
plaintext models.db; they are now stripped before persistence and
re-derived on load from AuthStorage / provider config.

Fixes #5780
2026-07-17 03:03:25 +00:00
roboomp 3c94ae4bbb fix(tui): prevented vibe wall scrollback duplication
Added an opt-in viewport-pinned live-region policy and propagated it through transcript composition for in-flight vibe_wait TV walls.

Pinned mutable wall frames now repaint virtually until finalization, while append-only live regions retain their existing frozen-snapshot behavior.

Fixes #5777
2026-07-17 02:22:47 +00:00
can1357 1b0d629a71 test(coding-agent): cover Ask single-select space input 2026-07-17 04:04:58 +02:00
Gerben Meijer 1e083eb832 feat(coding-agent): support per-project model roles 2026-07-17 01:22:23 +04:00
robomp-bot b7e21155cd fix(coding-agent): skip legacy completion notify under Warp protocol 2026-07-16 20:12:25 +09:00
can1357 f9977f5c69 fix: reconciled test contracts with merged behavior changes
- google boolean-subschema coercion, column-cap truncation semantics, caller-owned plan-review hide, rebuild image-visibility setting
- added flushPendingCommandOutput and refreshSkills stubs to event-controller and ACP mock contexts
- removed the never-passing acp stdio EOF subprocess test (covered by postmortem-epipe contracts)
2026-07-16 04:27:53 +02:00
can1357 3a75368b92 fix(images): preserve replay and transcript invariants 2026-07-16 03:48:59 +02:00
can1357 93cc1fed1c merged PR #5417: fix(openai): render native response images
# Conflicts:
#	packages/coding-agent/src/modes/components/chat-transcript-builder.ts
#	packages/coding-agent/test/agent-session-skill-keywords.test.ts
2026-07-16 03:48:21 +02:00
can1357 34f8eb70f0 fix(tui): honor ends during plan review reflow 2026-07-16 03:44:10 +02:00
can1357 37d38e1485 merged PR #5444: fix(tui): preserve Plan Review scroll position
# Conflicts:
#	packages/coding-agent/src/modes/components/plan-review-overlay.ts
2026-07-16 03:44:10 +02:00
can1357 ebaed59dda fix(tui): preserve deferred alternate exit 2026-07-16 03:32:00 +02:00
can1357 2a05d36be5 merged PR #5476: fix(tui): prevent stale-buffer flicker 2026-07-16 03:32:00 +02:00
can1357 bf3764fa4d feat(coding-agent): stabilize system-prompt cache across xd:// mount changes via delta notices
Instead of including the xd:// device inventory in the system-prompt signature, mount/unmount events now inject a steered `xdev-mount-notice` message so the system prompt (and its provider cache prefix) stays byte-stable across MCP connects and disconnects. Full device docs are picked up opportunistically on the next unrelated rebuild.

Also caps external (dynamic-mount) device descriptions to 200 chars in `docsAll` to prevent server-controlled prose from consuming prompt budget; built-ins keep their full curated docs, and `read xd://` always returns the untruncated text.

Legacy `discoveryMode: "off"` → `tools.xdev: false` migration is removed; the setting keeps its own default without inference from the deprecated key.
2026-07-15 19:07:31 +02:00
can1357 5ff277349c refactor(coding-agent): consolidated tool surface onto xd:// devices and hub
- Added the `xd://` virtual device protocol (`internal-urls/xd-protocol.ts`, `tools/xdev.ts`): tools declaring `loadMode: "discoverable"` are unmounted from the request tools array and driven via `read xd://` (list/docs+schema) and `write xd://<tool>` (execute), gated by the `tools.xdev` setting (default on) and inlined into the system prompt.
- Merged the `irc`, `job`, and `launch` tools into a single `hub` tool (`tools/hub/`, `async/job-manager.ts`): messaging keeps `send`/`inbox`/`list`, job control maps to `wait`/`cancel`/`jobs`, process supervision keeps `start`/`logs`/`stop`/`restart`/`describe` with `ps`, and the unified `wait` races background jobs against peer messages; SDK `IrcTool`/`JobTool`/`LaunchTool` are replaced by `HubTool`.
- Removed the hidden `resolve` tool in favor of the `xd://resolve`/`xd://reject`/`xd://propose` resolution devices, auto-including `write` whenever a deferrable tool or plan mode is present.
- Removed the BM25 tool-discovery system: the `search_tool_bm25` tool, the `tool-discovery` module, the `tools.discoveryMode`/`mcp.discoveryMode`/`mcp.discoveryDefaultServers`/`tools.essentialOverride` settings, per-tool MCP selection, and the `mcp_tool_selection` message type.
- Unified tool presentation on `ToolLoadMode` (`essential`|`discoverable`), replacing the custom-tool `xdev?: boolean` opt-out; custom, extension, MCP, RPC host, image-generation, and TTS tools now default to `discoverable`, and added a `satisfies` predicate to `SoftToolRequirement`.
- Removed the standalone `ssh` command tool and `ssh/ssh-executor` (the `ssh://` read/write/search protocol stays), and made `--tools` address hidden built-ins.
- Updated collab-web to render `xd://` dispatches and `hub` op families, dropped the `search_tool_bm25`/`ssh`/`report-finding` renderers, refreshed tool docs and prompts, and migrated the affected tests and changelogs.
2026-07-15 15:16:29 +02:00
can1357 404ebb0fb0 Merge remote-tracking branch 'origin/farm/ae7a5593/ttsr-inline-regex-flags-and-scope-quoting' 2026-07-15 09:54:46 +02:00
roboomp 02efdee788 fix(omfg): compiled generated-rule conditions via inline-flag helper
The /omfg generated-rule path validated conditions with raw new RegExp in normalizeConditionRegex and isValidRegexCondition, so a generated rule with a leading (?i)/(?m)/(?s) inline flag was rejected as "Invalid condition regex" before reaching TtsrManager.addRule. Route all three validation sites through compileRuleCondition.

Fixes #4796
2026-07-15 06:45:41 +00:00
can1357 1121a0018d Merge PR #5516: fix(auth): route OSC 5522 paste into login prompts (@roboomp) 2026-07-14 23:11:09 +02:00
can1357 413949ccf4 Merge PR #5450: fix(todo): signal removal intent so agent stops rebuilding cleared todos (@roboomp) 2026-07-14 22:58:47 +02:00
can1357 e755fcf983 Merge PR #5469: fix(tui): handle Kitty vim navigation sequences (@roboomp) 2026-07-14 22:58:46 +02:00
roboomp e49638ddac fix(auth): routed enhanced paste into login prompts
Forwarded OSC 5522 text from the focused login dialog to its credential input and added regression coverage for direct API-key prompts.

Fixes #5394
2026-07-14 20:06:14 +00:00
roboomp 68f84d7c20 fix(tui): prevented stale-buffer flicker
- Kept fullscreen replacement overlays mounted through asynchronous transcript rebuilds.
- Fused alternate-screen exit with destructive repaint and removed resize-time buffer switches.
- Preserved statically detected synchronized output when DECRQM probing is inconclusive.

Fixes #5319
2026-07-14 18:23:45 +00:00
roboomp 3fa5ffd0b1 fix(tui): handled Kitty vim navigation sequences
Routed vim-style h/j/k/l navigation through the protocol-aware key matcher across custom coding-agent selectors and overlays.

Fixes #5314
2026-07-14 18:08:23 +00:00
roboomp fd3f15c915 fix(todo): signal removal intent so agent stops rebuilding cleared todos
The /todo rm reminder was a generic "user manually modified" message
showing an empty list, so the model read the cleared list as missing and
re-populated it on the next turn. buildSystemReminder now emits an explicit
do-not-recreate / do-not-re-add directive for removals while keeping
status mutations (done/drop) neutral.

Fixes #5258
2026-07-14 17:33:21 +00:00
roboomp dc2235fa9c fix(tui): preserved plan review scroll position
Retained relative body progress across transient non-scrollable render frames and added regression coverage for terminal-height changes.

Fixes #5232
2026-07-14 17:16:12 +00:00
can1357 594a02e24a Merge PR #5248: feat(ai): report Cursor account usage (@riverpilot) 2026-07-14 19:16:09 +02:00
can1357 ba7bcf4cd1 fix(prompting): ignore code symbol magic keywords 2026-07-14 18:45:23 +02:00
can1357 334050d509 Merge PR #4968: fix(prompting): allow magic keywords beside punctuation (@roboomp) 2026-07-14 18:45:22 +02:00
can1357 353bb5c8e1 Merge PR #5239: fix(tui): compact transcript retention without losing resize history (@RensTillmann) 2026-07-14 18:34:14 +02:00
roboomp b6b947bdbe fix(openai): rendered native response images
- Normalized completed image_generation_call results into assistant image blocks.
- Persisted image bytes through the session blob store and rendered them in live, replay, ACP, proxy, telemetry, and HTML paths.
- Added response normalization, persistence, and TUI rendering regressions.

Fixes #4768
2026-07-14 16:15:53 +00:00
can1357 896c4bb17b fix(coding-agent/tools): capped expanded streaming diff previews to a viewport-sized tail
- Bounded expanded partial edit diff rendering in `formatStreamingDiff` to `previewWindowRows()` instead of an unbounded budget, preventing runaway preview growth during live updates.
- Updated streaming diff tests to simulate terminal height and verify expanded previews stay full only within the viewport, then switch to a truncated tail with the `more lines above` marker when too tall.
- Reinitialized in-memory `Settings` before each initial-messages test since the test suite reads global display configuration and needs isolation.
2026-07-13 19:00:26 +02:00
can1357 e42589d43d test(coding-agent): validated session persistence and downshift logic
- Added comprehensive tests for downshifting model behavior, including plan nudge injection and completion safety mechanisms.
- Verified session persistence accuracy by validating that from-disk rebuilds match the live agent state.
- Confirmed correct cache key propagation during tan commands to ensure provider caching is preserved.
- Removed obsolete reasoning slide tests.
2026-07-13 06:03:48 +02:00
can1357 0a98aa252b feat(coding-agent/modes): hardened tan fork isolation and session sync
- Clear inherited todo list state and persist empty edit at fork creation to prevent parent task reminders from affecting the tangential session.
- Re-inject the fork notice after each auto-compaction event to ensure the boundary between the parent and child session survives history summarization.
- Align the provider cache key with the parent's actual pinned key to correctly mirror cached session context.
- Update `AgentSession` to perform a full entry rewrite during tool result pruning to ensure session files match pruned state for reliable resuming and branching.
2026-07-13 06:00:30 +02:00
can1357 46ed33f27b feat(coding-agent): initialized session metadata during tan creation
- Initialized session metadata including system prompt, task, and toolset within the controller.
- Added session initialization tracking to the clone creation flow to ensure session state visibility.
- Updated unit tests to verify that session initialization data is correctly appended when a tan is created.
2026-07-13 01:09:42 +02:00