`idx stocks flow` now reads IPOT by default, which needs nothing installed:
per session, the all-investor broker summary gives the value traded and
the foreign one gives foreign buying (its footer), the foreign net and
selling (buying less the net), across all boards, through the broker
summary cache. IPOT's foreign net matched IDX's estimate within 0.3 B on
BBCA 2026-10-12 to 16.
`--source idx` (and `source` on get_foreign_flow) keeps IDX's trading
summary: exact share counts, close and the non-regular share, behind
curl-impersonate and Cloudflare.
- ForeignFlowDay gains foreign_buy_value, foreign_sell_value and
foreign_share_bps for both sources (estimated at the session average
for IDX); ForeignFlow gains source, the value totals and rounded.
- The table lays out each source's figures; the live smoke runs both.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3syn2fN2LNo5pvTSqc6eh
`idx stocks flow SYMBOL` shows what foreign investors bought and sold of a
stock, session by session, from IDX's own daily trading summary: foreign
buy, sell and net volume, net value at the session's average price, and
the share of value traded outside the regular board, with range totals.
Latest 10 sessions by default (--days, at most 60) or --from/--to. The MCP
server exposes it as get_foreign_flow.
- api/idx: pure parser for GetStockSummary (rows dated another session
are dropped) and a provider over curl-impersonate's profile fallback
with a 30 s limit; Cloudflare passes only some fingerprints.
- flow: each session is cached whole by date, so other stocks' flows for
the same sessions need no request. Weekends are never requested.
- Idx::idx_code is shared by broker and flow for the .JK-only check.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3syn2fN2LNo5pvTSqc6eh
opencode 2 (@opencode/cli) moved MCP servers to `mcp.servers`, turns
Code Mode on by default, replaced `permission` with ordered
`permissions` rules, and dropped `run --pure` for `--standalone` (runs
otherwise go through a shared background service). Pick the config and
flag from `opencode --version`.
Its `execute` tool stays allowed: with it denied, opencode 2.0.30 never
offers the idx tools to the model in `opencode run`, though the server
connects before the first step.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3syn2fN2LNo5pvTSqc6eh
opencode kept its built-in tools, so it could route around the server
under test: on published 0.3.1 it answered a quote from web search, and
on the live `changes` case it queried the ownership SQLite file with
bash and timed out. Deny every tool but `idx_*`, as Claude, pi, and
Hermes already are.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3syn2fN2LNo5pvTSqc6eh
The `changes` case names the fixture releases (2026-01-30, 2026-02-27),
which the live snapshot does not have, so under --live/--npx it failed
agents that correctly declined to answer about missing releases and
passed ones that called the tool anyway. A case's `live` fields now
replace the mock ones; this one asks about the two most recent releases.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3syn2fN2LNo5pvTSqc6eh
- agent-smoke `--npx <spec>` registers `npx -y <spec>` (the published package
or an `npm pack` tarball) with a fresh npm cache, instead of the local build,
so each agent's own npx handling and a cold install are tested.
- `nix develop .#agents-fhs` (Linux) runs agents in an FHS sandbox: Hermes
replaces a bare `npx` with its own generic-Linux Node, which NixOS cannot
load. `agent-fhs <cmd>` runs anything inside it.
- Hermes: only the idx toolset (with its terminal it repaired a broken
server mid-run and passed), the Node toolchain fetched before the first
case (`hermes -z` waits ~15s for MCP tools), JSON config.yaml (as profiles
write it), linked plugins for plugin model providers, and a copy of its
mcp-stderr.log per run.
- A failed run names its cause inline, since output is deleted without --keep.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WB13omP6h7YeyJx7GNtUnF
Findings from a Codex (gpt-6.1-sol, xhigh) review of v0.2.4..HEAD, each
verified in the code before fixing:
- high: ticker symbols reached cache file paths unchecked, so a symbol
like `../../REPORT` read (and deleted, if unparseable) .json files
outside the cache, reachable through MCP get_quotes. resolve_symbol now
accepts only ticker characters, and cache keys are encoded as single
safe path components.
- high: sync decided before downloading and replaced the database
without rechecking; an import that landed meanwhile was erased. It now
rechecks the local state before installing, and idx-mcp runs
ownership_sync exclusively with ownership reads.
- replaces_sqlite_sha256 never downgrades history: the client requires
the rebuild to keep at least the local release count, and the
publisher lists a replaced build only then.
- cache writes are atomic (temp file + rename), so concurrent readers
never see, and delete, a partial entry.
- idx-mcp caps symbols (20, deduplicated) and limits, and runs at most 4
tool calls at once.
- each Yahoo client gets its own cookie jar, paired with its crumb.
- ZIP entries (XLSX, KSEI archives) are read with a 256 MiB bound;
non-ASCII archive dates and huge percentages are parse errors instead
of panics or overflow.
- agent-smoke --keep deletes every copied agent config, not only auth
files.
CLI goldens unchanged; the MCP tool golden changes only to state the
new caps.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Require bash 4.4+ up front, and match answer facts with jq regexes
(Oniguruma, (?i) everywhere) instead of GNU-only grep -P.
- Unparseable agent output fails that run instead of aborting the
matrix; check_run now also reports unparseable tool calls, which
previously passed the tool check silently.
- Copy the Hermes model block with awk up to the next top-level key, so
a final or differently ordered block is handled.
- --keep keeps run output but deletes the copied agent credentials.
- docs: full path to the tool golden.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- tests/agents/agent-smoke.sh runs tests/agents/cases.json through
Claude Code, Codex, pi, Hermes Agent, and opencode headless against a
local idx-mcp build, each with an isolated config, and checks the
tools called, their key arguments, and (mock data) facts in the
answer. Opt-in; never part of the gate.
- crates/idx-mcp/tests/golden/tools.json pins tool names, descriptions,
and input schemas, so changes to what agents see are reviewed.
- nix develop .#agents adds Claude Code, Codex, and opencode from
nixpkgs after the host PATH.
First run: 30/30 (5 agents x 6 cases, mock data).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Phase 3a of docs/DESIGN.md. MockProvider moves to api/mock.rs, and it,
the embedded MSN fixture bodies, and the IDX_MOCK_* hooks compile only
with idx-core's new `testing` feature. idx-cli enables it as a
dev-dependency, so `cargo test` keeps the fixture-backed provider while
release binaries no longer embed fixture data or honor
IDX_USE_MOCK_PROVIDER. Parser helpers used only by the mock are gated
the same way.
The packaged-cli flake check no longer relies on the mock; it checks
an offline cache miss (JSON CACHEMISS, exit 3) instead.
Goldens unchanged; clippy is clean with and without `testing`.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Phase 0 of docs/DESIGN.md, before any refactor code:
- tests/golden.rs runs every case in tests/golden/cases.toml (126
outputs across help, completions, config, cache, all stocks commands
on MSN and Yahoo mocks, error paths, and ownership queries on a seeded
fixture DB) and compares exit code, stdout, and stderr byte for byte.
Regenerate only with UPDATE_GOLDEN=1 for a reviewed output change.
- scripts/live-smoke.sh --compare <old-idx> runs each live case with
both binaries and fails on differing exit codes, added/missing/retyped
JSON keys, or changed values for slow-moving data.
- Exclude golden files from the whitespace/EOF pre-commit fixers, which
would otherwise rewrite pinned help output.
Both gates were fault-injected: a one-word table change fails exactly
the three history goldens, and a binary dropping profile.long_name fails
only the profile live comparison.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The 43-case mock smoke duplicated tests/cli.rs, which already runs the
real binary against fixture providers. Replace the flake's smoke-mock
check with a small packaged-cli check (version JSON, bash completions,
one mock quote), and cut scripts/live-smoke.sh from 672 to ~170 lines:
it now only runs shipped commands against live MSN/Yahoo/IDX and
validates output shape. Rewrite docs/SMOKE.md around the Nix gate and
the drift check.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Remove FEATURE_SPEC.md, TODO.md, and docs/AGENT_INTEGRATION.md; their
core gaps have shipped. Open work moves to a short ROADMAP.md.
- Remove the CLAUDE.md symlink and rewrite AGENTS.md as a quick guide:
navigation, rules, and the nix flake check gate.
- Merge OWNERSHIP_SELF_HOSTED.md into OWNERSHIP_PUBLISH.md and drop
private host integration notes.
- ARCHITECTURE: add MSN endpoints, clarify Bing ingest is unsupported.
- OWNERSHIP_SYNC: note source.pdf_url also carries XLSX URLs.
- systemd example: --history 2 so snapshots stay under the 10 MiB
client cap.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Describe canonical local and CI verification, cache reuse, output assertions, workflow boundaries, and observed regression results without treating test counts as coverage targets.
Clear the smoke cache before each cache-group warm case so the following offline and stale-cache checks always start from a fresh baseline instead of earlier group state.
Document the runner behavior in the smoke guide to make the cache-group sequencing explicit.
