- New Costs tab with bar chart (All Models) and line chart (By Model)
- Toggle between 14d / 30d / 90d time ranges, filtered client-side
- Bar chart shows cost value on top of each bar
- Line chart uses straight lines with always-visible data points
- Summary cards: total 30d cost, avg/day, top model, trend vs prior period
- Backend: getCostTimeSeries() query grouped by day x model x provider
- All cost values displayed as whole dollar amounts (Math.round)
Previously, Ollama model discovery hardcoded contextWindow=128000 and
maxTokens=8192 regardless of the model's actual capacity. That caused
OMP's planner and overflow detector to disagree with Ollama — e.g. a
4k-context model would be planned against 128k, and a 32k-context model
would be silently clamped by OMP.
For each entry returned by /api/tags, POST /api/show and read the
first '<arch>.context_length' field from 'model_info' to pick up the
model's native context window. Fall back to Ollama's default 4096
when the endpoint or field is missing so discovery still works against
older builds. maxTokens is left at 8192 to match the existing default.
Fixes#760
The previous mismatch text ('1 line has changed since last read. Use
the updated LINE#ID references shown below.') reads like a successful
edit followed by an informational note. Providers whose tool-result
plumbing does not surface `isError: true` to the model (e.g. Qwen via
the OpenAI-completions shim, where mitmproxy traces show the model only
receives the content text) treat the response as a success and proceed
with stale state.
Reword the message to start with 'Edit rejected:' and explicitly state
'The edit was NOT applied' so the failure is unambiguous in plaintext.
The structural payload (>>> markers, updated LINE#IDs) is unchanged.
Fixes#742
Mirror the existing `commands.enableClaudeUser`/`commands.enableClaudeProject`
schema entries so the OpenCode discovery provider exposes the same
user/project toggle surface as Claude. Default remains true to preserve
current behavior.
Fixes#661
The structured SQLite helper interpolates `where=` directly into SQL.
A crafted clause like `where=1=1 LIMIT 1000000 --` could comment out
the helper's bound `LIMIT ? OFFSET ?`, returning the full table in
violation of the documented pagination contract.
Validate where= at the selector boundary and reject SQL comments,
statement terminators, and pagination/attach/pragma keywords. Raw SQL
remains available via ?q=SELECT... for callers that need it.
Fixes#735
Extracts a single `formatMatchPath` helper used by both the
fast-glob/native code paths and the streaming onMatch callback so
relative paths, trailing-slash handling, and directory markers are
produced consistently. Also drops the retry-without-gitignore fallback
when the gitignored pass returns zero matches, so a broad hidden-file
pattern that is fully ignored stays fully ignored instead of silently
flipping gitignore off on the second attempt.
resolveMultiSearchPath now reports `exactFilePaths` when every token
resolves to a plain file (no globs, no suffix glob) and accepts a
single resolvable token so partially-missing lists still search the
resolvable subset. grep iterates those exact files individually
instead of collapsing them into a brace-union glob, which preserves
the user's explicit file set even when siblings share a basename.
Also adds a small `[grep] match lines use ':'; context lines use '-'`
banner when context lines are rendered, and splits the per-file
rendering helpers so files with no remaining matches no longer emit
empty headers.
Apply now recomputes per-file replacement counts from the actual apply
pass and compares them against the preview. If totals or per-file
counts drift (file changed between preview and apply, or apply matched
nothing), the tool returns an isError result explaining that the
preview is stale instead of silently claiming success with mismatched
numbers.
The resolve tool now preserves the underlying tool result's details on
ResolveToolDetails.sourceResultDetails instead of dropping them, and
the renderer distinguishes a failed apply ("Failed") from a user
discard ("Discard") so errored applies are no longer mislabelled.
tree-sitter-cpp parses `ns::doThing($ARG)` without a trailing
semicolon as declaration-like syntax, so ast_grep returns no matches.
Tell agents up-front to include the statement semicolon (or use a
looser `$CALLEE($ARG)` pattern) instead of debugging silently empty
results.
When a bash tool call requests a timeout outside the allowed 1-3600s
range, the effective clamped value and the originally requested value
are now emitted as a notice appended to the tool output and exposed on
BashToolDetails via requestedTimeoutSeconds. The renderer shows the
clamped+requested pair inline in the timeout badge.
Reduces MAX_IDENT_CHARS from 6 to 3 in chunk path name truncation and
shortens the ChunkKind prefix strings (e.g. class->cls, array->ar,
body->b) so chunk paths stay compact across all supported languages.
Updates fixture expectations in ast_ipynb/edit/indent/resolve tests.
- Updated glob pattern construction to skip prepending the recursive `**/` prefix for exact brace unions wrapped in `{}`.
- Added an `is_exact_brace_union` helper that detected brace-only unions without wildcard or bracket meta-characters.
- Added tests covering `{alpha.txt,beta.txt}` as non-recursive and `{*.ts,*.tsx}` as still receiving the recursive prefix.
- Reworked #prepareStopOutcome to collect stopped, terminated, and exited event waits before racing them.
- Attached noop rejection handlers to each pending wait promise to prevent unhandled rejection noise after the race settles.
- Returned Promise.race(promises) so stop outcome preparation still waits for the first relevant lifecycle event.
- Queued outbound JSON-RPC messages behind a per-client promise queue to serialize writes.
- Added a project-load gate for project-aware LSP operations before diagnostics and reference lookups.
- Retried declaration-only references with a short delay until project metadata is available, then proceeded with normal results.
- Relaxed chunk-mode parameter validation to accept `{path}`-only edits as valid delete operations.
- Updated the invalid-parameters help text to document accepted chunk delete payloads.
- Added a test that verifies a bare `{path}` edit removes the targeted chunk when null values are stripped.
- Added a helper to detect whether a usage report indicates a Codex pro subscription.
- Updated credential ranking and selection to perform pro-plan-aware checks for requests that require pro models.
- Returned no credential when a pro model request lacked a matching pro usage plan before applying usage-limit blocking logic.
- Enabled Bedrock runtime and AWS credential calls to use a proxy-aware HTTP/1 handler when HTTPS_PROXY, HTTP_PROXY, or ALL_PROXY (including lowercase variants) is configured.
- Added a retry path that recreates the Bedrock client with HTTP/1 transport when an initial HTTP/2-related error occurs before streaming starts.
- Updated package and lock dependencies to include Bedrock credential-provider and proxy-agent support, and documented the new Bedrock proxy environment variables.
- Added a streaming parser path for apply_patch envelopes that tolerates incomplete patch bodies.
- Updated apply patch preview expansion to return best-effort hunks when the renderer is in partial mode.
- Added a renderer test confirming streaming apply_patch input shows file paths without end-marker parse errors.
- Added built-in model entries for gpt-5.5 and gpt-image-2, including updated context windows, token limits, and pricing.
- Updated generated-model policy application to set or clear applyPatchToolType based on inferred GPT-5 freeform rules.
- Changed Spark edit-mode resolution to return apply_patch by default, honoring explicit replace and strict-mode overrides.
- Added tests for GPT-5 freeform policy inference and Spark edit-mode default, variant, and strict-mode behavior.
Slots a new "apply_patch" variant alongside the existing edit modes
(replace, patch, hashline, chunk, vim). The mode accepts a single input
string containing a Codex *** Begin Patch / *** End Patch envelope,
parses it with a new lenient parser (heredoc-tolerant), and fans each
file-op out to the existing executePatchSingle so LSP writethrough,
plan-mode guards, fs-cache invalidation and diagnostics are shared
with the patch mode.
Exposes both tool shapes from the spec: the JSON function-tool variant
(§1.2, {input: string}) and the OpenAI custom-tool / Lark-grammar
"freeform" variant (§1.1, raw patch string). The edit tool advertises
a Lark grammar via customFormat and a wire name via customWireName;
openai-responses emits it as a grammar-constrained custom tool when a
model opts in with applyPatchToolType: "freeform" in models.json.
custom_tool_call / custom_tool_call_output are plumbed end-to-end
through the shared responses code (emission, streaming, history
replay), and the agent-loop dispatcher matches tool calls by either
name or customWireName so returned calls route correctly.
Also threads preview/diff rendering for apply_patch through the TUI
(tool-execution + edit renderer) so streaming patches show per-file
diffs like the other edit modes.
Default edit mode is unchanged (hashline); opt in via edit.mode or
PI_EDIT_VARIANT=apply_patch.
