* feat: data table migration tools and role guidance in ai sessions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* feat: shared data table guidance and safer migration tool failures
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep a migration that fails to apply and let the session rewrite it
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: rewrite only a pending migration and qualify fork isolation
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat: make hub integrations usable as examples in global chat
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: keep web search guidance in sync with provider capability
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: resync web search guidance before the request is built
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: carry loop web search availability into every prompt rebuild
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: drop web search guidance on the completions api fallback
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: correct onBeforeIteration contract for the fallback re-entry
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: give the ai chat hub script descriptions and integration metadata
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: treat authored hub metadata as evidence the scripts were curated
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: treat hub curated as three-state and speak only for a stated true
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: let the benchmark hub serve integration metadata
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: benchmark the hub tool against a real integration's scripts and metadata
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: cover two more real integrations where the scripts already answer
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: report metadata_source from whether the fixture has authored meta
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: parse the hub resource type schema instead of relaying it as a string
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: match integration suggestions on slug words instead of substrings
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: search the integration a query names outright instead of ranking past it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: reject hub integration slugs that would re-target the proxied request
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: add a mentioned integration's hits instead of filtering the search to it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep named-integration hits under the content cap and unmangle fixture placeholders
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: cut the middle of a capped hub result instead of repeating its tail
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: cap hub results by keeping the best of the ranked and named hits
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep a named integration that ranking placed below the content cap
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: let plan mode use the hub integration lookup
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* feat: mark which hub integrations carry authored provider knowledge
The hub flags the integrations whose document holds hand-written provider
knowledge, so a caller can tell before spending a call on the metadata
endpoint: 18 of ~216 qualify, and for the rest the endpoint returns what
was inferred from the same scripts a search already hands back.
Carry the flag onto search results, where the model first meets a slug, so
get_hub_integration is aimed at the few instead of guessed at. A hub that
predates the flag omits it and nothing is marked.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: stop the documented mark reading as a reason not to call
The flag says the hub additionally holds provider knowledge checked against
the live API. It is not a signal to skip the lookup elsewhere: that call
still returns the resource type and the usage-ranked examples, neither of
which a search result carries, and neither guessable.
The prompt said to read a script instead when the mark is absent, which
traded those for a guess on the ~198 undocumented integrations.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep the benchmark's documented flag true to what it serves
The eval hub reported Baremetrics and Holded as undocumented while its
metadata endpoint handed back their authored notes, so a case could teach
the model the flag means nothing. Derive it from both fixture sources, and
pin the agreement.
Also trims the documentedIntegrations comment to the four lines AGENTS.md
allows, keeping the case-folding constraint.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: keep the benchmark hub mostly undocumented, like the real one
Adding holded and baremetrics to the documented set resolved the fixture's
contradiction the wrong way: it left five of six integrations marked, against
the live hub's 18 of ~216, and claimed authored notes for two the hub reports
as having none. Drop the notes instead. Their auth and endpoints are in their
shipped scripts, which is what the cases that use them are about.
Also drops the last two places still describing the flag as a reason to spend
or skip the metadata call.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* refactor: let the model name the integration instead of guessing it from the query
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* refactor: word web search guidance conditionally instead of tracking provider capability
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: open the hub metadata route to job tokens and share one integrations fetch
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: record a copied hub script's source where write_script keeps it
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* test: pin that a query narrows to the integration it was given
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: match integration suggestions on the name the hub curates
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* fix: name an integration the hub leaves unnamed from the local word table
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: let test_run_flow name the conversation of a chat-mode test run
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: refuse a non-UUID conversation_id and mint chat test-run ids in one place
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(ai-evals): add a chat-flow follow-up case and mock flow preview runs
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: expect the conversation id argument on the manager's flow test bridge
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(ai-evals): require the chat-flow follow-up runs to share one conversation id
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: name the test_run_flow argument memory_id after the run parameter
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: disable a dynamic input when its schema field is disabled
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* refactor: extract the run form's argument hygiene into job_args
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* feat: give Tabs an opt-in sliding selection indicator
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* refactor: share the chat's scroll-fade measurement
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* feat: give the chat a run-form contract and incremental job output
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* feat: run and test a script from the chat through an argument form
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* feat: carry a chat run's card and job across saves and reloads
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* feat: render a chat run as a tool call row with its form, logs and result
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* feat: open a pending run form in the sessions preview pane
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* test: benchmark running a deployed script from the chat
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ERed9zo2oJjpSczzMayaNh
* feat: offer a test run's dynamic options from the draft it previews
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
* docs: say that a test run's dynselect helper executes on form display
* fix: send a schema default the model omitted when yolo skips the form
* fix: infer a test run's schema when the stored one declares no properties
* docs: tighten the note on the form's mount-time helper job
* fix: apply a nested schema default the bypass posture counts as answered
* fix: apply a declared default to a null value and an optional nested field
* fix: check required fields inside a supplied optional object before bypassing
* fix: read required args as own properties before bypassing the form
* fix: stop the turn from the run form's action row in the preview panel
* refactor: drop the run-form prediction and share its secret minting
* refactor: prefill a proposed secret instead of emptying the field
* docs: correct the comments the run-form prediction left behind
* fix: keep a proposed secret out of the chat's stored messages
* docs: say what a literal secret argument now does
* test: restore the copilotInfo export the aiStore mock omits
* docs: cut the run form's helper-script note to its constraints
* refactor: settle a run form from one entry and fetch a job's logs once
* fix: separate colliding secret paths, gate plan mode, keep polled logs
* fix: mint before the form opens, skip empty fields, show what ran
* revert: mint a run form's secrets at submit, not before it opens
* fix: settle a cancelled run card on the form's arguments, not the proposal
* fix: settle a stopped run form like a cancelled one, and keep an empty secret empty
* fix: snapshot a run's arguments before minting its secrets
---------
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
* docs: teach agents to pass a resource as $res:<path> in run arguments
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XjRARL7JA7xm772iJP4mJk
* docs: extend run-argument rule to in-editor chats, fix run-as wording
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XjRARL7JA7xm772iJP4mJk
* docs: tighten resource run-argument rule after review
- Drop the false rationale that "$var:" only works inside a resource value
from the write_variable description and its runtime rejection message; keep
the rule (a variable cannot reference itself).
- MCP resource-argument description: the title fallback renders "No title",
so say the title is only a label rather than that it can be empty. Guard the
real-newline fix with asserts in the existing enrichment test.
- Eval: assert the full "$res:f/evals/global/github_main" value as one prefix
so a wrong path with a right prefix fails.
- resources.md: narrow "a trigger's payload" to its configured static args.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XjRARL7JA7xm772iJP4mJk
* docs: scope the run-argument rule to global chat, add an exact eval matcher
The ai_evals A/B on the two in-editor modes showed no effect: script mode
sonnet 5/5 both with and without the description, flow mode sonnet 5/5 and
haiku 5/5 on the baseline alone. A flow's input schema already carries
`format: resource-<type>`, so those modes have a signal global mode does not
give. Revert both files to keep the tool schemas free of a description that
buys nothing per iteration; global mode keeps it, where haiku goes 0/5 -> 5/5.
Add `stringEqualsAnyOf` to toolCallArgs and use it for the resource reference:
nothing in the eval resolves the value, so a prefix match accepted a near-miss
path like `$res:f/evals/global/github_main_backup`.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XjRARL7JA7xm772iJP4mJk
* docs: address cubic review — CLI wording, mock resource getter
- `-d --data` help on all four run/preview commands: give $res: and $var:
their own clauses instead of a parenthetical that read as if a resource
were a kind of variable.
- Mock backend: `getBenchmarkResource` now resolves AI-provider seeds as well
as plain ones, so it agrees with `existsResource` and `listResource` — both
report either kind, and a case that listed a resource and then read it by
path got a row it could not fetch.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XjRARL7JA7xm772iJP4mJk
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: ground the chat's AI agent provider in the workspace's models
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: never reject an AI agent model the catalog could not confirm
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: benchmark AI agent provider grounding in ai_evals
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: only reject an AI agent model an exhaustive listing rules out
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: keep instance-level AI settings out of the workspace provider catalog
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: keep untrusted model ids out of the chat's context
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: carry completeness on the model listing itself
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: correct two comments left behind by the catalog rework
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: bound the model listing and verify the default against it
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: honour a workspace default a filtered listing names
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: recognise a workspace default past the prompt's model cap
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: keep an aliasing provider's unlisted model ids permissive
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: let global evals seed the session's preview tabs
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* feat: advertise the pinned artifact version in get_preview_status
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: reject ambiguous preview-tab and artifact eval fixtures
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: stop the AI chat destroying secret variables on edit
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: clear stale staged secret values and state the draft-staging rule
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: condense the pending-secret invariant to its field
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: refuse empty and oauth-managed secret values, keep drawer-staged ones in the draft
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: resolve a variable deploy's secret from one draft snapshot
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* refactor: make the variable draft the single source of a staged secret
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: drop stale in-memory secret invariants from comments and the eval
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: stop null account/expires_at leaking into variable drafts and diffs
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: report when a variable deploy leaves the secret value unchanged
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: scope the variable-value readability claims to the chat
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: correct the secret-draft invariant in the diff masking comment
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: record why a non-secret value is resent on a partial update
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: stop "Load secret value" discarding a staged secret
The audit-logged load writes the deployed secret into the draft row the
variable drawer shares with the AI chat, so offering it while that row
already stages a value silently replaces it — and the deploy that follows
carries the old value with no sign the staged one was lost.
The gate that hid the action already existed but keyed on
`isEncryptedDraftValue`, which only holds once a draft has round-tripped
through the server. A value staged in the same tab is still plaintext, so
it slipped through. Key on "anything staged" instead; clearing stays
explicit via Reset.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: extend the variable draft's empty-value sentinel past secrets
Two gaps in the chat's variable write path, both from treating "the draft
cannot carry this value" as meaning only "the value is secret".
`variableToDraftState` drops the value of an OAuth-managed variable so a
refreshed live token is never pinned into a draft, leaving '' behind. The
deploy body resent that '' verbatim for a non-secret one, wiping the token
the refresh flow owns. The sentinel now covers every value the draft is not
allowed to hold, which also removes the divergence from
`VariableEditor.save` and the shared deployer.
Making a variable secret when it holds no value produced a secret draft
staging '', a deploy body with no `value`, and the backend's "cannot change
is_secret without updating value too" — the sibling create path already
answers that case with guidance, so answer it here too.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix: gate the Secret toggle's secret load on the staged value too
The toggle calls `onLoadSecret` on every change so an is_secret flip has a
value to send, but that load overwrites the shared draft row — the same
discard the button gate just closed, reached by a different control.
It now loads only when the row stages nothing, which is exactly when the
flip needs a value fetched. With a value already staged there is one to
send, and it is the one the user or the chat put there.
Blocking the load costs the side effect that used to mask a worse bug: for
a deployed variable, the load replaced an `$encrypted:` marker with real
plaintext before save. Without it, un-securing a marker would store the
marker string as the value, since the deploy endpoints only decrypt it while
is_secret stays true. So the toggle is disabled outright while a marker is
staged — Reset first. That closes the marker case for draft-only variables
as well, where no load could ever have masked it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test: add global-mode path-selection eval cases with seeded user
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(copilot): guide global-mode path selection with injected folder list
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(copilot): tailor global-mode folder guidance for workspace admins
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(copilot): type folders_read; isolate global-eval user from store
Addresses PR review:
- Add folders_read to the User/whoami openapi schema and UserExt; the global prompt builder and eval harness now read it typed instead of via inline casts (regen the client to pick it up).
- prepareGlobalSystemMessage takes an explicit user; the eval harness passes it rather than mutating the process-global userStore, removing the concurrency race (path cases no longer need --verbose).
- Rewrite the path-selection case comment as a current invariant.
- Add buildFolderGuidance unit tests in core.test.ts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: add global AI chat context-optimization plan for raw apps
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): add global raw-app debugging cases on a large fixture
Adds a ~20-file analytics_dashboard raw-app fixture (incl. a 5k-line data module
and a planted wrong-totals bug), two global cases (read-heavy debug + small-edit
baseline), app-seed support in the mock backend, directory-fixture loading, and a
decorateHelpers seam so read-dedupe is measurable. Records tokenUsage for before/
after comparison of the read-tool optimization.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): cap and dedupe read_app_file to bound context in large apps
read_app_file now defaults to a head slice (1500 lines / 50k chars) with offset/
limit to page further, and skips resending a file whose earlier read is still in
context (per-conversation ledger keyed off the originating tool-call id, so it
self-heals after compaction). Bounds the file-content portion of global-chat
context when working in large raw apps.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): add read-heavy raw-app debug case (large data module)
global-test31 induces the model to inspect the 5k-line seedData module, exercising
the read_app_file cap/offset path. Baseline ~262k tokens vs ~200k with the cap+dedupe
change (-24%).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: record A+B benchmark results and fixed-overhead finding
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): clearer read_app_file past-EOF message + unit tests for cap/dedupe
Addresses local-review nits: out-of-range offset now reports 'offset N is past the
end of the file' instead of a backwards 'lines 11-10' label; adds unit coverage for
the slicing (line cap, offset/limit window, char budget, past-EOF) and re-read dedupe
(hit + miss-when-not-retained).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): char-level paging + per-range dedupe for read_app_file
Adds char_offset/char_limit so minified/long-line files can be paged within a line
window, keys the re-read ledger by range (so reading different ranges no longer
collides), and dedupes on the full-file hash (a cached range stub is invalidated
when any byte of the file changes, not just the returned range). Tests updated for
the char-slice behavior plus single-line capping, char paging, and out-of-window
change detection.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-chat): add read_app_file context micro-benchmark + re-read eval case
Adds a deterministic micro-benchmark (no LLM) that drives read_app_file through a
realistic big-project read pattern (large file, re-read, minified bundle, paging)
and asserts the cap+dedupe cut returned context >50% vs the old whole-file behavior
— isolating the feature's effect from model nondeterminism and guarding against
silent weakening. Adds global-test32, a cross-file consistency investigation that
revisits overlapping files so re-read dedupe is exercised in a real run.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): clarify test32 measures the read cap, not dedupe
Verified: sonnet and haiku both read each file once per conversation and retain
it, so test32 never triggers read_app_file re-read dedupe. Dedupe is measured
deterministically by the micro-benchmark instead. Comment corrected to match.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): drop read_app_file re-read dedupe, ship the cap only
Benchmarking showed the per-conversation re-read dedupe never fires in practice:
across sonnet/opus/gpt-5.5/haiku, every model reads each file once per conversation
and keeps it in context (0 within-conversation re-reads). It was a correct but unused
guard, so this removes the ledger, full-file hash, retention predicate, the
AIChatManager wiring, and the eval decorateHelpers seam — keeping the read cap +
offset/limit/char paging (A), which is the lever that actually bounds context. The
micro-benchmark is now cap-only; test32 is kept as a multi-file read-load case.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai-chat): add search_app grep tool for global raw-app chat (experimental)
Client-side grep over a raw app's frontend files and inline runnables (literal,
case-insensitive, optional file_glob/context_lines/max_matches, head-capped).
Completes the list -> search -> ranged-read triad. Includes the eval A/B gate
(WMILL_AI_EVAL_DISABLE_SEARCH_APP), unit tests + micro-benchmark, and a
find-all-usages eval case (global-test33).
Experimental: A/B benchmarking shows it is not an unconditional win — it helps
on find-all-usages but adds agentic iterations on navigable apps.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai-evals): accept search_app as a valid file-inspection tool in raw-app cases
Add requiredToolsAnyOf alternatives-group to ToolValidationSpec and switch
global-test29..32 to it so a model that locates files via search_app instead
of read_app_file no longer false-fails the tool assertion.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: remove stale ai-chat context-optimization planning doc
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): drop read_app_file char paging for a hard char cap
The char_offset/char_limit params guarded minified files (a single line over
the char budget) but were effectively unused in benchmarks. Remove them and the
in-window char paging; keep the hard 50k-char budget and, when a read hits it,
tell the model to narrow the line limit (or treat the file as unreadable if a
single line exceeds the budget). Proper long-line handling is left as a TODO.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): bake search_app context to 1 line, clarify query is literal
Drop the context_lines param (models varied it to little effect) for a fixed
SEARCH_APP_CONTEXT_LINES=1, and cap on matching lines instead of pushed rows so
max_matches stays accurate with context always on. Sharpen the query description
to state it is a literal (non-regex) substring and to suggest the call form
(e.g. formatCurrency() to hit call sites and skip formatCurrencyPrecise.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai-chat): widen baked search_app context to 2 lines
Models that set the old context_lines param leaned to 2; match the lean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): count every file with a match in search_app header
Move fileHadMatch ahead of the render cap so files whose matches fall past max_matches are still counted (with a regression test). Also swap the raw NUL globstar sentinel for a printable escape (the NUL bytes made core.ts read as binary to grep) and reword two comments to describe current constraints instead of drafting history.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai-chat): drop redundant input echoes from app tool results
read_app_file and search_app no longer prefix results with the tool name or echo back the caller's own inputs (file path, query, file_glob) — the model already has them from the call args, and the unbounded query echo could push the search result past its output budget. Keeps the useful signals (line range, match/file counts, truncation) and the actionable advice. Also reword max_matches to 'matching lines' since it caps lines (each expands to context rows). Unit tests updated to the new format.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(ai): add list_runs and get_job_logs tools to global chat mode
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(ai): always suppress ansi hint in get_job_logs, drop misnamed param
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(ai_evals): add global list_runs and get_job_logs eval cases
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* style(ai): trim get_job_logs description and format global core
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(ai): surface list_runs/get_job_logs output as tool result
The tools set showDetails but never set message.result, so the details panel rendered "No result yet" even on success. Set result in setToolStatus (logs go in result for get_job_logs).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: add datatable tool coverage to global ai_evals (stage 0+1)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: add seeded datatable difficulty-ladder global ai_evals (stage 2)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: skipJudge datatable evals and make stringIncludesAnyOf existential
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test: make ai_evals datatable mock reflect SQL writes
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore: record app benchmark baseline
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: strengthen app benchmark persistence checks
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: seed inventory tracker benchmark case
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add deterministic app diagnostics
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add app chat patch_file tool
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add app session id micro-edit case
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: narrow app patch file content
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: stop gating app evals on lint
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: use compact json for flow patches
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: improve flow eval harness
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: record flow benchmark history
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: preserve schema in set flow json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* style: clean set flow json schema guard
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: clean flow patch review followups
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: support special flow modules in evals
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: extract shared flow helper logic
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: make special flow tools openai-compatible
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: improve flow eval prompts and validation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: relax flow benchmark overfits
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: record updated flow benchmark history
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: address flow review findings
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: source flow chat special module prompt
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: narrow rawscript helper return type
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: dedupe flow chat prompt guidance
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: relax flow test10 validation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add backend preview validation to ai evals
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: refresh shared preview workspace assets
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: harden shared backend preview validation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Ruben FiszelandClaude Opus 5.5
hugocasaandClaude Opus 5
AlexRV12andClaude Opus 5
GuilhemandClaude Opus 5
centdix
