Commit Graph
265 Commits
Author SHA1 Message Date
sam f8ffbbdd69 merge: tg5 model/personality commands + conflict resolution 2026-07-29 07:29:02 +10:00
sam 568d4a4be3 resolve: merge gateway additions from alm.1/alm.2/alm.4 2026-07-29 07:28:43 +10:00
sam 6f549fe0a1 gateway: add /steer, /goal, /subgoal, and /queue chat commands
Implement session-scoped goal/subgoal/steer/queue state management
with thread-safe access and prompt injection for standing goals.

Commands:
- /steer <text> — queue a message to inject after the next tool call
- /goal [text|draft|show|pause|resume|clear|status|wait|unwait]
- /subgoal [text|remove N|clear]
- /queue (aliases /q, /bg, /btw, /background) [text|remove N|clear]

Architecture:
- SessionState in internal/gateway holds per-session goals, subgoals,
  steer queue, wait flag, and background queue
- Goals are injected into the system prompt via BuildGoalPrompt()
- Steer messages are consumed between agent tool-calling steps via a
  MaxSteps=1 loop in the daemon's respond closure
- Commands route through the existing gateway.Router with not-configured
  guards when State is nil

Closes: archie-core-alm.1
2026-07-29 03:41:05 +10:00
sam 52633833f5 archie-core-alm.4: extend /model and add /personality to Telegram
Extend /model command to support:
- /model [model] (direct switch)
- --provider <name> (provider switch)
- --global (persist scope, with ModelPersist callback)
- --session (explicit session scope, default)
- --refresh (show current active model)

Add /personality command:
- /personality lists available personalities with inline keyboard
- /personality <name> switches directly
- Callback handling for inline keyboard selection

Router changes:
- Add Personas field (wired to PersonaRegistry in main.go)
- Add ModelPersist callback for --global persistence
- Route /personality as a local command
- Extend handleModel to accept full rest text with flag parsing
2026-07-29 03:36:33 +10:00
sam 03a200d582 telegram: add /whoami, /profile, /sessions, /resume, /agents commands
Gateway-local commands that report from Archie-owned state:

- /whoami: reports the Archie identity the user is talking to
- /profile: shows active Archie profile (identity, provider, model, available models)
- /sessions: lists recent sessions with last-active timestamps
- /resume [id]: resumes a session by ID or prefix match
- /agents: lists active agents and running/waiting tasks

Adds SessionLister and AgentReader interfaces to Router, wired from the
daemon composition root. SessionStore already satisfies SessionLister.
AgentReader is a thin adapter over store.Task list filtered to active
states (running, waiting_human, parked).

All commands are published in Telegram's menu and /help, and respond
with 'not configured' when their backing interface is nil.

Closes archie-core-alm.2
2026-07-29 03:36:07 +10:00
sam d92ac87c25 style: golangci-lint autofix and formatter pass (qa4.1) 2026-07-29 03:25:20 +10:00
sam 1d85a0b532 fix: remove task approval from Telegram command surface (qnm) 2026-07-29 03:25:19 +10:00
sam deb5678d37 remove task approval from Telegram command menu/help
Hide /approve from Telegram's command menu, help text, and discoverability.
Telegraph users can no longer learn about task approvals through the bot.
/approve remains executable in the gateway router for email and webhook
channels; non-Telegram workflow callers are unaffected. Daemon polling of
forged waiting_human tasks and the Requeue(→implement) handoff are untouched.
2026-07-29 03:24:01 +10:00
sam d9f4de068b chore: golangci-lint --fix + formatters (gci, gofumpt, gofix, goimports)
Auto-fix lint issues and reformat imports across all files.
gci: group imports per project convention
gofumpt: format unused imports with blank lines
gofix: Go standard fixes
goimports: organize imports

Remaining 54 issues require manual judgment (not auto-fixable).
2026-07-29 03:23:57 +10:00
sam 1da53e2939 fix: resolve remaining unconvert and pre-existing skillscript test failure
- Remove unnecessary string() conversion on res.Status in workflow/agent.go
  (Status is already string in agentexec.Result)
- Fix TestRunWrapsExternalCommand: sh -c only reads the first argument as
  the command string. exec.CommandContext("sh", "-c", "echo wrapped")
  passes the intent correctly, while the previous split form
  (", "", "echo", "wrapped"") treated "wrapped" as /bin/bash.
2026-07-29 03:23:31 +10:00
sam 9859d10095 chore: park process-generating skills and add scope discipline
Move 5 skills (2093 lines) to /work/apps/archie-skills-parked: they
commissioned architecture campaigns, decision ledgers, evidence packets
and acceptance gates on every agent that opened the repo. Twelve factual
skills remain (6376 -> 4283 lines).

Add a CLAUDE.md scope-discipline section stating the architecture docs
are complete and authoritative, so agents implement against them instead
of extending them. Close the two architecture planning issues.
2026-07-29 03:17:42 +10:00
sam 69640b5216 docs: consolidate into a single docs/ tree
Fold the old docs/ into the VitePress site and rename docs-2 -> docs.
The 12 architecture PRDs become first-class pages at docs/architecture/
with sidebar nav, rather than being buried under an archive path.
Historical material stays at docs/archive/. Rewrites every docs-2 and
docs/prds/architecture reference across the repo. Site builds clean.
2026-07-29 03:17:42 +10:00
sam 2eae457e7b chore: untrack committed docs node_modules
248 pnpm files were tracked under docs-2/node_modules. Untrack them and
ignore node_modules, vitepress cache/dist, and crew scratch.
2026-07-29 03:17:32 +10:00
sam d1bbd37d95 chore: cleanup 2026-07-29 02:10:44 +10:00
sam 65aa5b462d chore: cleanup 2026-07-28 18:46:50 +10:00
sam 6ee605a4fc fix(worktreerpc): bound handler contexts and drop the git binary from tests
Missed in f800e1d, which ported internal/worktree but stopped at "the
sibling package still compiles".

Both NATS handlers ran their work under context.Background(). The client
side has a Timeout and passes a context, but the server discarded it, so
a prepare or push ran unbounded. That was survivable when the work was a
git child process that could be killed; after f800e1d it is an in-process
go-git clone, so an unresponsive forge wedges the handler goroutine
permanently. Removing the per-repo object cache in that same commit made
clones longer, which widens the window further.

Server now has a Timeout (defaulting to 15 minutes, sized for a large
clone over a slow link) applied via handlerContext, with a table test
asserting both the explicit and default paths produce a bounded deadline.

The fixtures also still shelled out to git, so every test in the package
skipped when no git binary was present and the helpers tripped noctx.
Rebuilt on go-git to match internal/worktree's suite, including pinning
commit.gpgSign=false on the seed repo so fixtures do not inherit signing
from the host's global config.
2026-07-28 02:05:06 +10:00
sam f800e1de36 refactor(worktree): replace git shell-out with go-git v6
internal/worktree no longer executes the git binary. Clone, fetch,
checkout, commit, push and diff all run in-process through go-git v6,
which also removes the package's 9 noctx findings since the Context
variants are first-class.

Security: the forge token no longer leaves the process. The old
implementation wrote a GIT_ASKPASS shell script to disk and exported the
token into the environment of every git child process. Authentication is
now an in-process credential passed via client.WithHTTPAuth. cloneURL
also stops embedding the bot user in the GitHub URL.

Dropped the per-repo object cache (PreparePersistent, prepareCache,
CleanupExpiredCaches). go-git can clone with shared alternates but has no
equivalent of --dissociate, so a cached bare repo would remain a live
dependency of every worktree built from it, and expiring one would
corrupt running tasks rather than fail cleanly. Every task now gets an
independent full clone. repo.PersistentStorage still governs the
container volume; only the git object cache is gone.

Two real defects surfaced while porting, both caught by the new tests:

  - go-git honours the host's global git config and cannot sign commits
    (no gpg fallback, only an ObjectSigner plugin). On any machine with
    commit.gpgSign=true set globally, every bot commit would have failed
    with "cannot auto-sign commit". setIdentity now pins gpgsign=false in
    the clone's own config so daemon behaviour does not depend on the
    ambient config of whatever host it runs on.
  - go-git's Add(All) does NOT honour .git/info/exclude, which is how the
    .archie-prepared sentinel was kept untracked. It was being committed
    and would have been pushed onto every task branch. The sentinel now
    lives at .git/archie-prepared, where nothing can ever track it, and a
    regression test asserts it never appears in a commit.

Diff is now merge-base relative via Commit.MergeBase, matching the three
dot semantics of `git diff origin/base...HEAD`; diffing against the remote
tip would attribute commits landed on base since the branch started to
this task and could trip the diff-size cap. Base resolution tries the
remote-tracking ref first and falls back to the short "origin/<base>"
revision, keeping git's more permissive lookup.

The test suite was rebuilt on go-git fixtures and no longer needs a git
binary installed to run.
2026-07-28 01:56:59 +10:00
sam 529b25eada docs: phase 3a — nilerr review, all 11 sites were false positives (qa4)
97 -> 85. Not one of the eleven nilerr findings was a bug.

I called these "real bug candidates" when I planned the phases. I was
wrong, and the reason is worth recording: every site is the same
deliberate idiom, and a linter cannot see intent.

  - inprocess.go (5) and gateway.go (2) are handlers that report a
    problem as TEXT to their consumer. A tool handler returning a Go
    error aborts the tool call; returning "rejected: ..." lets the model
    read the feedback and retry with valid arguments. A chat handler
    returning a Go error surfaces as a gateway fault instead of a usage
    hint to the human.
  - worker.go carries runErr in the response envelope's Error field.
    Returning it as a Go error too would double-report and abort the
    NATS reply.
  - email.go returns nil when Accept fails because context cancellation
    closed the listener. That is a clean shutdown.
  - codesearch.go skips an unreadable entry and continues the walk. A
    best-effort index must not abort on one bad file.
  - skill.go is documented in the function comment already: a
    non-directory skills path means "no skills", not a fatal error.

Annotated each with //nolint:nilerr and the specific reason rather than
excluding the linter by path, so nilerr stays live everywhere else and
the next reader wondering "why nil here?" gets an answer at the site.

This is the phase I insisted on keeping single-session and out of the
subagent fan-out. A worker told to "fix nilerr" would have converted all
eleven to error returns: malformed tool arguments would hard-fail the
agent loop instead of being correctable, chat typos would read as
gateway faults, and shutdown would log spurious errors. Every test would
still have passed.
2026-07-28 01:39:22 +10:00
sam 4ee8579ddc refactor: phase 2 of lint remediation — mechanical fixes (qa4)
130 -> 96. forcetypeassert, predeclared and usetesting are now at zero.

Fanned out across four isolated worktrees partitioned by package so no
two workers could touch the same file: internal/tools (20 assertions),
internal/webui, internal/memory + internal/ratelimit, internal/secret.
Four stragglers outside those scopes fixed inline (internal/pairing,
internal/forge, internal/channels/telegram, internal/tools/mcp).

Unchecked type assertions became comma-ok with a t.Fatalf naming the
actual type. One site in a goroutine uses t.Errorf + return instead,
since t.Fatalf from a non-test goroutine is undefined behaviour.

predeclared renames chose names from meaning rather than adding a
suffix: max -> maxQueryLen, maxMatchLen, maxRequests, alphabetLen, and
nextBackoff's max -> ceiling. `real` -> `base` in the webui tests.

os.Setenv became t.Setenv, which restores on cleanup, so the paired
deferred Unsetenv calls went with it.

Note for future fan-outs: the agent worktrees branched from origin/main
(a7388a0), not from this branch, so every diff arrived based on a tree
without the phase 1 autofix. They were applied with `git apply --3way`
and the phase 1 changes to internal/memory/manager.go were verified to
survive — in particular the repaired `ctx, cancel =` assignment. A plain
`git apply` would have silently reverted it.
2026-07-28 01:37:20 +10:00
sam 15d746c2f6 style: phase 1 of lint remediation — autofix pass (qa4)
golangci-lint run --fix plus the formatters: errorlint, gocritic,
sloglint, usestdlibvars, usetesting, gci, gofumpt, goimports.
160 issues -> 130.

One autofix was wrong and had to be reverted by hand. gocritic rewrote

    ctx, cancel = context.WithTimeout(ctx, m.prefetchTimeout)

to `:=` inside an if-block in internal/memory/manager.go. That does not
compile, which is the good outcome — had it compiled, the shadowed ctx
would have scoped the timeout to the if-block and the prefetch deadline
would silently never have applied. Restored the assignment and commented
why it must not be a declaration.

Worth recording: --fix is not a safe no-op. It broke the build on a
24-file change, and the failure mode it was one compiler error away from
was a silent behaviour change.
2026-07-28 01:37:20 +10:00
sam 2b7b3bd794 build: add golangci-lint v2 config with structural and correctness linters
The repo had no .golangci.yml at all, so golangci-lint ran on defaults
only — errcheck, govet, ineffassign, staticcheck, unused. That is why it
reported "0 issues" on a 745-line file containing 21 struct types and a
180-line finalize() with a cognitive complexity of 106.

Adds a curated set on top of the standard linters: structure (cyclop,
dupl, funlen, gocognit, gocyclo, maintidx, nestif), architecture
(depguard, importas, interfacebloat), correctness (nilerr, bodyclose,
forcetypeassert, noctx, contextcheck, errorlint, sqlclosecheck, and
friends), and hygiene (gocritic, godox, sloglint, usestdlibvars).

Deliberately not `default: all`: the formatting-opinion linters (wsl_v5,
nlreturn, varnamelen) and the absolutist ones (exhaustruct, err113,
wrapcheck) would add hundreds of pure-opinion findings. A gate that cries
wolf gets disabled, and a disabled gate enforces nothing.

depguard now encodes the internal/indexing layering rule structurally:
that package is ported from tau and must stay refreshable by diff, so it
may not import internal/config. Until now that constraint was a comment,
which is to say it was advisory.

This surfaces 160 issues (81 outside tests), so the gate is RED until they
are cleared. That is intentional: the config is the work list. Notable is
nilerr — 11 sites returning nil on a path where err != nil, six of them in
internal/agentexec, which is the class of bug that reads as "the task
silently did nothing".

Verified with `golangci-lint config verify` against the v2 JSON schema.
2026-07-28 01:37:20 +10:00
sam 05cfc30da3 fix(indexing): surface index config properly and stop silent degradation
Follow-up to c924281, which introduced two defects of its own.

1. indexing.Config was a private config island: index paths existed nowhere
   in internal/config or config.example.toml, so they were undiscoverable
   and unsettable by anyone reading the real configuration.

   Now [indexing] in config.toml, defined in its own internal/config/
   indexer.go rather than appended to the 21-struct config.go, and its
   defaulting lives with it as IndexingConfig.withDefaults so finalize
   delegates instead of growing. Paths default off work_dir, keeping the
   two archied instances on one host from sharing an index. Documented in
   config.example.toml.

   internal/indexing keeps its own plain Config and does NOT import
   internal/config, so it stays a straight diff against its tau original.

2. A failed index build was invisible. refreshAsync wrote the reason to a
   database column with no reader and degraded to unindexed search in
   silence — the failure mode that costs hours precisely because nothing
   appears to be wrong. Every give-up path now logs, and a successful
   build logs once.

The logger is resolved at the point of use, not in the constructor: a
Manager can be built as a struct literal (the ported tests do), and
constructor-only defaulting panicked on the build goroutine, where a panic
takes the daemon with it. Regression test covers the zero and nil Manager.
2026-07-28 01:37:19 +10:00
sam 446dc6b3de feat(indexing): port tau's codesearch workspace index (4we)
First slice of the tau cherry-pick strategy: copy-and-mutate rather than
extracting tau to pkg/. Exporting would force designing metrics, session
and logger seams upfront, before archie-core knows which of them it wants
differently — a cost paid for reuse not yet proven. ai-sdk earned library
status by stabilising across two consumers; nothing in tau/internal has.

indexing is the cheapest high-value lift: 512 LoC, one file, and its only
coupling to tau was three calls to process-global config path helpers.
Nothing else in tau imports it.

Mutations from upstream:
  - path helpers become an explicit indexing.Config. Two archied instances
    share a host (archie and winter), so they must not share one index.
  - the child-process helper is archied's own workspace-codesearch
    subcommand, dispatched before flag parsing so it touches no config,
    store or NATS.
  - deferred db.Close calls explicitly discarded; archie-core runs errcheck.

The child process is not incidental: google/codesearch calls fatal exits on
a corrupt index and leaks mmapped regions. Verified end to end against this
repo — 2.2MB indexed, correct hits for BuildSystemPrompt, [] for no match,
and a deliberately corrupted index returns "corrupt index" with exit 1
instead of taking the process down.

Every lifted file carries a provenance header naming its tau path and
commit (4893818d0c76), so refreshing from upstream is a diff rather than
archaeology.
2026-07-28 01:37:19 +10:00
sam c79c623e9c feat(chat): real system prompt for Archie — identity, tools, env (sc5)
The chat agent's entire system prompt was the four-sentence static string
in gateway.DefaultPersonas(). It carried no tool inventory, no environment
block and no instruction precedence, so the model invented its own
capabilities: asked to set something up it announced it "only has the
memory editing tool", then offered to walk through installing software it
has no tool to install.

Renders a template modelled on tau's agent.md.tpl + tau.agent.md:
instruction precedence, core rules, communication rules, a <tools> block
and an <env> block. The persona stays the style layer on top; the rules
and the tool inventory live in the template so switching persona cannot
remove them.

The tool list is derived from the same core.ToolSet handed to the model,
so the prompt cannot drift from what the agent can actually call, and an
empty toolset renders an explicit "no tools are available" rather than
silence the model fills in for itself.

Tool metadata is third-party data from MCP servers, so it is markup-escaped
(<, >, & only — not xml.EscapeText, which mangles prose into &#xA;/&#39;)
and whitespace-flattened, so a description cannot forge a closing tag or a
second "- tool: ..." list entry.
2026-07-28 01:37:19 +10:00
sam a7388a0a59 Merge pull request 'Fetch() masks JetStream errors as empty-queue when zero msgs arrive (archie)' (#84) from fix/35-fetch-masks-jetstream-errors-as-empty-queue-when-zero-msgs-a into main
Reviewed-on: sam/archie-core#84
2026-07-27 08:17:51 +00:00
archie 5045592d41 fix: Fetch() masks JetStream errors as empty-queue when zero msgs arrive (archie)
Fixes #35
2026-07-27 04:37:17 +00:00
archie 03899171e6 test: failing repro for #35 2026-07-27 04:36:14 +00:00
sam bcca6f9c25 feat(telegram): add approved component updates 2026-07-27 13:02:11 +10:00
sam c1c3a973c6 feat(telegram): report installed component versions 2026-07-27 12:53:59 +10:00
sam 647537c00a refactor(telegram): keep one model selector command 2026-07-27 11:44:27 +10:00
sam 2facb2be1b Merge pull request 'handleSummary ignores errors from WorkflowStats/StageStats/TokensByDay (archie)' (#78) from fix/53-handlesummary-ignores-errors-from-workflowstatsstagestatstok into main
Reviewed-on: sam/archie-core#78
2026-07-27 01:24:57 +00:00
sam 0ff8729080 Merge branch 'main' into fix/53-handlesummary-ignores-errors-from-workflowstatsstagestatstok 2026-07-27 01:24:45 +00:00
sam 329776de9c feat: establish Archie identity and use stable callback tokens 2026-07-27 11:03:40 +10:00
sam ec8534dfe2 feat(gateway): ship model controls, shell tools, and release tracking 2026-07-27 06:16:39 +10:00
archie 0b8560c2c2 fix: handleSummary ignores errors from WorkflowStats/StageStats/TokensByDay (archie)
Fixes #53
2026-07-26 20:08:20 +00:00
archie 902fd28bf5 test: failing repro for #53 2026-07-26 20:07:32 +00:00
archie ef12eb6141 fix: baseline gate repair (go test ./... -count=1) 2026-07-26 20:05:07 +00:00
sam 3cab289b41 refactor: centralize command specs and dynamic help text for Telegram 2026-07-27 05:34:46 +10:00
sam 19a6311f6c feat(telegram): /restart to reload config without dropping tasks (16.35)
Operator escape hatch: reload gateway config (notably the sender
allowlist) or recover a wedged adapter from chat, with no shell access to
the host.

Start becomes a supervisor loop that relaunches the bot on request, so a
restart is scoped to the gateway: the daemon keeps running and in-flight
agent tasks are untouched. Exiting the process would also have restarted
under the unless-stopped policy, but would have killed running work.

Two failure modes are handled deliberately:

- The handler runs on the very bot the supervisor is about to stop, so it
  hands off over a buffered channel and returns instead of tearing down
  inline, which would deadlock the restart it just requested. A duplicate
  request while one is in flight is dropped, not queued.
- A failed config reload logs and relaunches on the previous settings, so
  a bad config edit cannot take chat down permanently -- which would also
  remove the means to fix it.

Authorisation is inherited from authorizedMessage: only allowlisted
senders reach any handler, so /restart is admin-only by construction.
main.go supplies Reload, which re-reads config from disk and refreshes
token and allowlist; other fields still need a full daemon restart, since
they are wired at construction.
2026-07-27 05:21:58 +10:00
sam 9fd4696492 fix(telegram): publish command menu to all scopes, not just default
The menu still showed ~60 stale hermes commands (/steer, /reload_mcp,
/background) even though SetMyCommands succeeded and logged 8 commands.

Telegram resolves a chat's menu by scope specificity rather than by
recency: a list registered against all_private_chats wins over the
default scope in every DM. We wrote only the default scope, so hermes's
older per-scope registrations kept shadowing ours. getMyCommands confirms
it -- default held our 8, all_private_chats and all_group_chats each held
hermes's ~60.

That state lives on Telegram's side, keyed to the bot token, so it
survived the migration off hermes and would survive any redeploy. Publish
to default, all_private_chats and all_group_chats so the leftovers are
overwritten rather than shadowing us. One failing scope no longer aborts
the rest.
2026-07-27 05:18:26 +10:00
sam cb147b7a37 feat(telegram): deny-by-default sender allowlist + command menu (16.33, 16.34)
Allowlist (16.33). telegram.New was called with a nil allowlist and
isChatAllowed returned true whenever the list was empty, so any Telegram
user who found the bot could talk to it; AllowedChatIDs was not plumbed
into config, so there was no way to close it. Chat tools run with the
daemon's own authority, so this had to be fixed before wiring any real
tools to the chat agent.

Now chat.telegram.allowed_user_ids configures it and an empty list denies
everyone: a bot handle is public, so failing open is not a safe default.
The check matches the sender (from.id) rather than the chat, so adding
the bot to a group cannot be used to inherit access. Rejections log the
sender id and answer once, so a legitimate user missing from the list can
tell the bot is misconfigured rather than dead. Startup warns when the
gateway is enabled with an empty list.

The previous TestIsChatAllowed asserted 'empty allowlist allows all' --
it encoded the vulnerability -- and is replaced by fail-closed tests.

Command menu (16.34). SetMyCommands was never called, so Telegram showed
no menu and the commands Router implements were undiscoverable; asked
about /commands the LLM confidently answered it had none. The published
list mirrors what Router actually handles. Failure is logged, not fatal:
it costs discoverability, not function.
2026-07-27 05:14:34 +10:00
sam 285c618f74 fix(chat): drain FullStream, not TextStream — streaming deadlocked every reply
Streamed chat replies hung on the first token: the draft rendered an
empty cursor, the typing indicator never cleared, and the turn never
completed.

RouteStream consumed stream.TextStream, but ai-sdk's channel contract
makes FullStream authoritative and requires draining it until close --
its writes are synchronous, so an unread FullStream applies backpressure
and stalls the producer. Once its buffer filled, the producer blocked,
TextStream stopped yielding, and the range loop blocked forever.

TextStream was the wrong source regardless: it is explicitly best-effort
and drops deltas when not drained, so a reply reconstructed from it can
silently lose text. Range over FullStream and collect StreamPartTextDelta
parts, exactly as the SDK documents.

Also bumps ai-sdk v0.1.17 -> v0.1.18 (build, full suite and lint clean).
2026-07-27 05:04:04 +10:00
sam 3e3911a423 feat(telegram): native rich messages + streamed replies (16.32)
Upgrades go-telegram/bot v1.18.0 -> v1.22.0 and uses the Bot API's rich
message support instead of hand-rolled formatting.

The previous commit converted LLM Markdown into Telegram's HTML subset,
on the premise that the API could not take Markdown directly and had no
table element. Both are true of v1.18.0 but not of v1.22.0, which adds
sendRichMessage/sendRichMessageDraft taking InputRichMessage{Markdown},
plus RichBlockTableCell for native tables. markdownToHTML and its tests
are deleted: LLM Markdown, tables included, now goes to Telegram as-is.

Replies also stream. runtime.ChatStream already returned a TextStream
and sendRichMessageDraft renders partial output, so the only missing
piece was a gateway seam: gateway.LLMStreamResponder plus Router.
RouteStream, which degrades to the blocking Route when unset so any
adapter can call it unconditionally. Local commands answer from local
state and are not streamed; an unrecognised /command is, since Route
hands it to the LLM. main.go derives both responders from one shared
turn implementation.

Draft updates are throttled to one per 700ms to respect per-chat rate
limits, and every streaming/rich path falls back rather than dropping a
reply: a rejected rich send retries unformatted, and a failed draft
update is skipped since the final message is authoritative.
2026-07-27 04:57:36 +10:00
sam b52accf24a config: set containers.network explicitly for the docker deployment
Pins the agent-container network instead of relying on selfNetwork()
auto-detection, which silently fell back to the default bridge and broke
NATS resolution for spawned agents.
2026-07-27 04:51:10 +10:00
sam bf0e348cbb fix: pass HEYARCHIE_TELEGRAM_BOT_TOKEN through to archied
The telegram chat gateway is enabled via chat.telegram.token_env in
config.toml, but compose never forwarded the named variable, so
cfg.Chat.Telegram.TokenEnv resolved to empty and archied exited 1.
Same class of bug as ARCHIE_GITEA_TOKEN_ARCHIE.
2026-07-27 04:51:10 +10:00
sam cb1b0eb11a feat(telegram): typing indicator + Markdown rendering (part of 16.6)
Two gaps visible in the live heyarchie bot:

1. No typing indicator. A non-command message runs a full LLM turn
   (seconds), during which the chat looked dead. defaultHandler now
   shows the typing action for the duration, refreshed every 4s since
   Telegram clears it after ~5s.

2. ParseMode was never set, so LLM Markdown reached users verbatim:
   literal **bold**, backticks, and pipe tables. helpHandler was worse
   -- it emitted <b>Archie Gateway</b> with no ParseMode, so the raw
   tags were shown.

The SDK has no Markdown->Telegram converter (EscapeMarkdown does the
inverse: it escapes text so it renders literally), and neither native
parse mode helps, since Telegram's Markdown dialects use single-asterisk
*bold* whereas LLMs emit **bold**. So markdownToHTML converts to the
HTML subset Telegram accepts, mapping headings to <b>, bullets to '•',
and tables to <pre> (Telegram has no table element). Send falls back to
unformatted text if Telegram rejects the markup, so a conversion bug can
never swallow a reply.
2026-07-27 04:47:21 +10:00
sam 18948ac0e3 chore: remove accidentally-committed build/test scratch artifacts
.gotmp/ (Go build cache and test temp-dir output, created as a
workaround for a tmpfs disk-quota issue in this environment) got swept
into a prior commit by a broad `git add -A`. Remove it and gitignore
the directory so this doesn't recur.
2026-07-27 04:43:37 +10:00
sam 325aa7ae35 test message 2026-07-27 04:39:39 +10:00
sam 4c0fc12450 test message 2026-07-27 04:39:27 +10:00
sam 52015c81b0 fix: pass ARCHIE_GITEA_TOKEN_ARCHIE through to archied container
The archied service only forwarded ARCHIE_GITEA_TOKEN, but config.toml
names ARCHIE_GITEA_TOKEN_ARCHIE for the archie identity. Recreating the
container via docker compose (rather than a manual docker run with an
explicit -e) silently dropped the token.
2026-07-27 04:31:43 +10:00