The apply_patch language documents `*** Add File` and `*** Move to` as
strictly non-overwriting (create / rename), but the fs-level create and
rename paths in applyNormalizedPatch wrote through to the resolved target
without checking whether it already existed. Existing destinations were
silently replaced, and in the rename case the source was also deleted.
The multi-file executeApplyPatchPerFile aggregator caught each per-file
exception, appended an error entry, and kept iterating. Later files
still ran against an inconsistent post-state, and the aggregate result
had no top-level isError — so a mixed partial application looked like a
successful edit to the agent loop.
Changes:
- Add fs.exists guards before the create write and before the rename
write/delete in packages/coding-agent/src/edit/modes/patch.ts. Both
reject with ApplyPatchError before any side effect.
- Make executeApplyPatchPerFile in packages/coding-agent/src/edit/index.ts
stop at the first per-file failure, list applied vs. skipped files in
the aggregate text, and propagate isError, matching executeSinglePathEntries.
- Rename the two apply-patch scenario fixtures (010_move_..., 011_add_...)
that pinned the buggy overwrite behavior to _rejects_ variants, and
flip their expected/ trees so source and pre-existing destination
remain byte-identical after the rejected apply.
- Cover both failure modes with new regressions in
packages/coding-agent/test/core/apply-patch.test.ts and a new
packages/coding-agent/test/core/apply-patch-multi-file.test.ts.
Fixes#4074
Registered `edit.input` and `eval.code` alongside `write.content` so the reveal controller decodes those top-level string arguments incrementally between throttled full-JSON parses.
Added a regression test covering multi-key extraction so the wire-up survives future additions.
Refs #4043
Added incremental decoding for streamed write content so preview args update below the full JSON parse throttle.
Added a regression test covering sub-throttle content growth in ToolArgsRevealController.
Fixes#4043
AGENTS.md forbids inline `await import()` — move `fs`, `path`, and `prompt`
to top-level namespace/named imports. The `prompt-templates` module import
already registers the Handlebars helper as a side-effect, so the render
calls still resolve the new `renderYieldSchema` helper.
- Updated exact substring match assertions to use word-boundary regular expressions.
- Prevents false-positive test failures when target strings overlap with other generated text.
The eval tool's live agent()/parallel() subagent progress tree
(renderAgentProgressEvents) mutates on almost every progress tick: each
subagent's row inserts/removes a "current tool" line as it starts/stops a
tool call, and ticks its status icon/stats/duration in place. Meanwhile
options.isPartial holds true for the whole eval() cell — progress ticks
never carry an async completed/failed state, so the update handler keeps
passing isPartial: true throughout.
evalToolRenderer never opted out of the transcript's stable-prefix ratchet
for partial results, so ToolExecutionComponent.isTranscriptBlockCommitStable()
reported the block commit-stable during that churn. That let
deriveLiveCommitState promote still-mutating agent rows into native
scrollback (a "slow ticker"), and the renderer's committed-prefix resync
then repeatedly re-showed the frame tail under its "duplication, never
loss" contract — producing overlapping/duplicated subagent rows in the
TUI under heavy concurrent agent()/parallel() fan-out.
Set provisionalPartialResult: true on evalToolRenderer, the same opt-out
sshToolRenderer already uses for this class of bug (see the "pinned
expanded pending preview commit-unstable" fix). The block now stays
commit-unstable until the eval cell settles, keeping agent-progress rows
in the live, repaintable region for their whole lifetime.
Added eval-commit-stability.test.ts covering: partial → commit-unstable,
settled → commit-stable, non-opted-in tools (bash) unaffected, and
commit-unstable held across row-count/content churn between two partial
ticks.
Op: correct
Restores: spec:eval agent-progress rows must not be promoted into native scrollback while still mutating
- Removed the canonical model variant indexing, selection, and tracking logic from the model registry and resolver.
- Eliminated the `canonical` sub-command, tab view, search tokens, and equivalence configuration structures from the CLI and model selector components.
- Refined model identification, lookup, and provider fallback resolution to bind exclusively to standard, raw model IDs.
- Relocated the equivalence utility script within the catalog package to support script-only policy generation.
Preserved the referenced model's OpenAI-compatible reasoning-effort support when openai-models-list discovery enriches a thin /v1/models payload. The discovered model still keeps conservative proxy-local store and developer-role defaults, but known reasoning models like gpt-5 no longer force supportsReasoningEffort false and trigger the omitReasoningEffort request path.
Added a regression assertion that a thin proxied gpt-5 keeps supportsReasoningEffort true and omitReasoningEffort false after reference enrichment.
Fixes#3983
Thin OpenAI-compatible proxies that omit context_length / max_model_len on
/v1/models made every discovered model fall back to
DISCOVERY_DEFAULT_CONTEXT_WINDOW (128K/33K), even when the id matched a
bundled model with a much larger intrinsic window. discoverProxyModels
and discoverLiteLLMModels already resolve ids against the bundled
reference index; discoverOpenAIModelsList (which also backs lm-studio
discovery) now does the same.
Behavior:
- Build the reference index once outside the loop and resolve each item
via resolveModelReference().
- contextWindow precedence keeps provider-reported values authoritative:
item.max_model_len ?? item.context_length ?? nativeMetadata?.contextWindow
?? reference?.contextWindow ?? DISCOVERY_DEFAULT_CONTEXT_WINDOW.
- maxTokens uses reference?.maxTokens when available, otherwise the
api-specific discovery default, capped at contextWindow so a bundled
ref for a larger sibling can never over-request output tokens.
- name / reasoning / thinking / input inherit from the reference; native
lm-studio metadata still wins for input modality.
- Provider-specific baseUrl, headers, and local-unknown cost stay local.
- OpenAI-compat flags stay conservative (supportsStore / supportsDeveloperRole
/ supportsReasoningEffort all false) to match the proxy sibling.
Also updated two pre-existing regression tests that used
deepseek-v4-pro / deepseek-r1 / DeepSeek-V4-Flash as stand-in "fictional"
ids to exercise the default-fallback branch. Those model names have since
been added to the bundled catalog, so the tests were renamed to
vllm-lab-fork-* ids that unambiguously miss the reference index while
preserving each test's original default-fallback intent.
Fixes#3983
Added a cross-turn tool-call loop guard that hashes canonical tool names and arguments, ignores intent metadata, and injects a hidden redirect when identical calls reach the configured threshold.
Fixes#3971
- Introduced an `#editVariantCache` to memoize resolved edit modes for model variants.
- Replaced the generic `shallowStringRecord` helper with specialized, type-safe parsing methods for model variants and roles.
- Invalidated the cached edit variants during settings rebuilds and verified correct cache refreshment across project directories.
- Moved Streamable HTTP request and notify timeout cleanup after response body consumption.\n- Added regression coverage for stalled request JSON bodies and stalled notify error bodies.\n\nFixes #3974
can1357