* feat(provider): add GitHub Copilot provider with device-flow auth
Adds GitHub Copilot as a model provider, so Copilot models (gpt-4o/4.1/5,
Claude, Gemini, …) work through the normal chat + agent loop, incl. native
tool calling and vision.
Auth is one-click via the GitHub OAuth device flow; the access token is stored
as the endpoint's (encrypted) api_key and sent directly as `Authorization:
Bearer` (no Copilot-token exchange, no refresh — matching how editors talk to
the Copilot API). Copilot is a normal ModelEndpoint detected by host; the only
provider-specific behaviour is a small set of required request headers,
injected centrally.
Sign-in is available from Settings → model endpoints ("Connect GitHub
Copilot") and from chat via `/setup copilot`.
- src/copilot.py (new), routes/copilot_routes.py (new): constants, header
builders, device-flow start/poll, model discovery, owner-scoped endpoint
provisioning.
- src/llm_core.py, src/endpoint_resolver.py: detect `copilot`, inject headers,
per-request x-initiator/vision.
- src/agent_loop.py: allowlist api.githubcopilot.com for native tool schemas.
- src/model_context.py: known context windows for Copilot (no unauthenticated
/models probe).
- static/, README, tests/test_copilot*.py.
* Tidy copilot_routes: clarify supports_tools, note _PENDING is per-process
* fix(llm): auto-detect <think> in content stream for unregistered thinking models
_THINKING_MODEL_PATTERNS only covers known model families by name. Qwen3-derived
models with non-standard names (e.g. Qwopus, custom QwQ forks) are not matched,
so their <think>...</think> content streams through as visible chat text instead
of being routed to the thinking display.
When the first content delta opens with <think> and the model was not already
identified as a thinking model, dynamically flag the stream as a thinking model
for the remainder of the response. This enables the existing </think> repair path
(line below) and ensures the frontend receives the full <think>...</think> wrapper
it needs to split thinking from the final answer.
The check is restricted to the very first content delta (_first_content_sent is
False) to avoid misidentifying models that happen to write "<think>" mid-answer.
Fixes#2225
Related: #2420 (covered by separate PR from @AmmarS-Analyst), #2224 (@RaresKeY)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(llm): replace inert _thinking_model flag with _in_think_tag state machine
The original auto-detect set _thinking_model=True on the first <think> chunk
but still emitted it as a regular delta and set _first_content_sent=True
immediately, so no subsequent chunk could enter the repair path.
Replace with _in_think_tag bool: enter thinking mode when first content starts
with <think>, route all chunks to the thinking channel until </think> is found,
then the tail becomes the first regular delta. Adds three regression tests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(llm): replace _first_content_sent guard with _think_open_stripped
Opening-tag stripping used `not _first_content_sent` as the guard, but
_first_content_sent stays False throughout the entire think block (it only
flips when regular content is emitted). So `find(">")` ran on every
reasoning chunk — not just the first — and silently truncated everything
before the first ">" in any reasoning text containing comparisons, arrows,
or code.
Fix: add `_think_open_stripped = False` alongside `_in_think_tag`. Use it
as the strip guard in both the "still inside <think>" path and the
"</think> found in same chunk" split path. Set it True once the opening
tag is consumed so all subsequent chunks reach the thinking channel
unmolested.
Add regression test: 3-chunk stream where the middle chunk contains
"c > d" — confirms "more c " is not dropped.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Agent subprocesses (bash, python) previously inherited the container's default
working directory (/app), so files created with relative paths landed in the
ephemeral container layer and were silently destroyed on any docker compose up
--build or container recreation.
Set cwd=_AGENT_WORKDIR (resolved to <repo_root>/data at import time) and
HOME=_AGENT_WORKDIR on both subprocess launchers so that:
- pwd inside a bash tool returns the persistent data directory
- relative paths and ~ resolve to a location that survives rebuilds
- the agent can still cd to any absolute path it needs
The resolution uses pathlib.Path(__file__).parent.parent / "data", which
works for both Docker (/app/src → /app/data) and manual installs
(<repo>/src → <repo>/data) without requiring a new env var or compose change.
Fixes#2512
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
A system message that arrives without a 'content' key — possible via
malformed tool results — raised a KeyError in the hot path of llm_call,
llm_call_async, and stream_llm. Replace m["content"] with
m.get("content") or "" in all three functions so a missing key degrades
to an empty string instead of crashing.
Also removes a redundant .rstrip() after .strip() in _model_activity_key.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The retry loop raised immediately for any non-success HTTP response
regardless of attempt count. For transient upstream errors (rate limit,
bad gateway, gateway timeout) the function should back off and retry
within the existing attempt budget.
Also lets ConnectError / ConnectTimeout retry when the host has not been
cooled and attempts remain, instead of always raising on the first
connect failure.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Gives the agent first-class code navigation instead of shelling out via bash
(token-heavy, unreliable on weaker models, unstructured). Mirrors the
Grep/Glob/Read primitives that Claude Code / opencode expose.
- grep: regex search over file contents across a tree. Uses ripgrep when
available (with explicit excludes so junk dirs are skipped even without a
.gitignore); falls back to a pure-Python walk+regex when rg is absent.
Returns file:line:match, capped.
- glob: find files by glob pattern (recursive), newest first.
- ls: list a directory (folders first, then files with sizes).
- read_file: optional offset/limit for line-range reads of large files
(plain-path calls stay back-compatible).
All confined by the same path policy as read_file (_resolve_tool_path:
data/tmp allowlist + sensitive-file deny). Junk dirs (.git, node_modules,
venv, __pycache__, dist/build, …) skipped. Output capped (200 hits,
400 chars/line). Admin-gated like the other filesystem tools.
Wiring: schemas + native arg->content serializer (src/tool_schemas.py), tool
tags (src/agent_tools.py), always-available + descriptions (src/tool_index.py),
admin gate (src/tool_security.py), dispatch + impls (src/tool_execution.py).
Tests: tests/test_code_nav_tools.py — match/skip-junk/ignore-case/glob-filter,
allowlist rejection, glob/ls, read-range, and the no-ripgrep Python fallback.
* Add edit_file tool + file-change diffs
edit_file is an exact old_string -> new_string replacement on a file on disk
(fails if old_string is missing or non-unique unless replace_all); write_file
also returns a unified diff. Diffs render collapsed in the tool bubble
(filename + +adds/-dels, theme colors); the raw JSON command box is hidden.
Security: edit_file is a sensitive filesystem-write tool, treated everywhere
write_file is —
- added to NON_ADMIN_BLOCKED_TOOLS (is_public_blocked_tool / blocked_tools_for_owner),
so on auth-enabled deployments a non-admin cannot run it; execute_tool_block
refuses it for non-admin owners.
- confined by the same path policy as read_file/write_file (allowlist +
sensitive-file deny) via _resolve_tool_path.
Disambiguation in tool descriptions + bash prompt: edit_file/write_file are the
only way to write files (they show a diff) — never edit_document (editor panel)
or a bash heredoc/redirect.
Tests (tests/test_edit_file.py): non-admin block (policy + execution gate),
successful edit, not-found old_string, non-unique old_string (+ replace_all),
and path outside the allowed roots.
Files: src/tool_execution.py, src/agent_loop.py, src/tool_schemas.py,
src/agent_tools.py, src/tool_index.py, static/js/chat.js, static/style.css,
tests/test_edit_file.py.
* Drop redundant import os in write_file closure
os is already imported at module top.
* chore: dedupe src/search/cache.py into a re-export shim
src/search/cache.py was a byte-identical copy of services/search/cache.py.
Convert it to a sys.modules alias of the canonical services module (matching
src/search/core.py, providers.py, ranking.py) so the two cannot drift, and add
an identity assertion to test_search_module_consolidation.py.
content.py and query.py are intentionally left as-is: the copies have drifted
and services lacks fixes that src has, so they need services reconciled first
before they can be shimmed safely.
* chore: dedupe src/search content.py and query.py into shims
Convert src/search/content.py and query.py to sys.modules aliases of the
canonical services/search/* (matching cache.py, core.py, providers.py,
ranking.py) so the duplicate copies cannot drift.
Repoint the two tests that were coupled to the src-copy internals onto the
canonical services surface (behaviour is equivalent):
- test_src_search_query_nonstring.py: import services.search.query instead of
loading the src file by path.
- test_security_regressions.py::test_web_fetch_guard_blocks_redirect_into_private:
mock httpx.get (services uses the module-level get, not httpx.Client) and
assert on the canonical 'Blocked' message.
Drop the now-redundant [src_content, service_content] parametrization in
test_search_content_extraction_parity.py and test_search_content_url_guards.py
(after the shim both params are the same object); add content/query identity
assertions to test_search_module_consolidation.py.
The compatibility re-export shim at src/search/ranking.py forgot
_SPORTS_HINT_RE, so tests importing src.search.ranking raised
AttributeError on the [src] parametrize variant.
Fixes#1995
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: SSE parser crashes with NoneType on MiniMax-M3 (and any provider sending null choice/usage/tc)
Three guards added in stream_llm:
1. choices[0] null check — MiniMax (and some other providers) send a
choices entry as None. `_choices[0].get("delta")` raised
AttributeError. Now checks `_choices[0] is not None` before calling
.get().
2. usage null guard — j["usage"] can arrive as None (not a dict) on
some providers. Added `or {}` so subsequent .get() calls don't crash.
3. tool_calls null entry skip — individual entries in the tool_calls
array can be None. Added `if tc is None: continue` before
tc.get("function").
All three match the `or {}` / null-guard pattern used elsewhere in the
same block. Safe for all OpenAI-compatible providers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: guard null choice in elif-choices SSE branch
The usage-chunk path already guarded _choices[0] is not None, but the
elif "choices" branch that processes content/tool-call deltas did not.
A chunk like {"choices": [null]} or {"choices": [null], "usage": null}
reaches j["choices"][0].get("delta") and crashes with:
'NoneType' object has no attribute 'get'
Fix: extract choices[0] into _c0 and continue to the next chunk when
it is None, matching the guard already applied in the usage path.
Adds three focused regressions covering the paths the maintainer flagged:
- {"choices": [null]}
- {"choices": [null], "usage": null}
- tool_calls array containing a null entry alongside a valid call
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The visual research report is assembled from LLM output over crawled web
pages (untrusted content) and served under a relaxed `script-src
'unsafe-inline'` CSP. Two values reached that HTML without sanitization:
- `_md_to_html` rendered the report markdown via python-markdown, which
passes raw HTML through verbatim, so `<script>` / `<img onerror>` /
`<svg onload>` / `javascript:` links carried in crawled content ran in
the app origin.
- `category` (from the /api/research/start request body, no enum check) was
interpolated raw into `<body class="category-{category}">`.
Allowlist-sanitize the rendered markdown with nh3, keeping the formatting
the report emits (tables, code, details/summary, toc anchors, codehilite
classes, external-link target/rel) while dropping active content, and
html.escape the category. Adds regression tests.
Adding GigaChat (Sber) or an on-premise enterprise LLM gateway as a
model endpoint fails on first probe with
CERTIFICATE_VERIFY_FAILED: self-signed certificate in certificate
chain (_ssl.c:1000)
because their TLS chain is signed by a private root CA (Russian Trusted
Root CA for GigaChat; corporate CA for on-prem) that isn't part of the
default system / certifi trust store. The endpoint shows offline in
the picker even though the URL and API key are correct (issue #722).
The right fix is to extend the trust store, not to weaken verification.
This change:
- src/tls_overrides.py: new module that resolves an opt-in env var
LLM_CA_BUNDLE at import time, builds a shared SSLContext via
ssl.create_default_context() (so the system / certifi bundle is
loaded first) and layers the operator's PEM on top with
load_verify_locations(). Exposes llm_verify() returning a value
suitable for httpx `verify=`. Defaults to True (httpx built-in
trust) when the env var is unset, when the file is missing, or
when the PEM fails to load — verification is never silently
disabled, the warning is logged and we fall back to the safe path.
- src/llm_core.py: thread llm_verify() into the shared AsyncClient
used by stream_llm / streaming completions.
- routes/model_routes.py: thread llm_verify() into the five httpx.get
call sites in _probe_endpoint / _ping_endpoint so adding a
private-CA endpoint goes green on the very first probe and the
picker stops showing it offline.
- .env.example: document LLM_CA_BUNDLE with the GigaChat case as the
concrete example.
Deliberately NOT included: a verify=False knob (global or per-host).
Disabling verification exposes the affected endpoint to MITM, and the
operator-supplied bundle is the correct fix for legitimate private-CA
providers — so the only switch in this PR is the safe one.
Closes#722.
get_builtin_overrides() was swallowing all exceptions with a bare
`except Exception: pass`, so misconfigured tool-description overrides
would silently produce wrong agent behaviour with no log trace.
The background endpoint refresh loop had the same pattern: any probe
failure was silently ignored, giving operators no signal that the
refresh was broken.
Also removes a circular self-import (`from src.agent_loop import
_build_base_prompt`) inside _build_system_prompt; the function is
already in scope and the import created a latent circular reference risk.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
ModelEndpoint is defined in core.database, not src.database. The wrong
import silently prevented the module from loading in deployment
configurations that do not have a src/database.py shim, resulting in an
ImportError at startup.
Also adds a warning log when resolve_endpoint finds no usable model
(all models hidden or the list is empty), making the otherwise-silent
failure visible in operator logs.
The test_auth_regressions stub for src.endpoint_resolver was missing the
build_models_url attribute, which caused test collection errors.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Agent mode treated local /v1 endpoints, including Ollama on :11434, as native-tool-capable by host/model heuristics. On Ollama's OpenAI-compatible surface some models that advertise tool support stop after a single token when schemas are sent (issue #1567). Default local Ollama /v1 back to fenced tool blocks unless the endpoint explicitly has supports_tools=True.
Also compare both the runtime chat URL and the normalized endpoint base when reading ModelEndpoint.supports_tools. That keeps a saved base URL such as http://localhost:11434/v1 effective when the active session URL is /v1/chat/completions.
Tests: .venv/bin/python -m pytest tests/test_tool_support_heuristic.py
* fix: support large proxy model endpoint refresh
Large OpenAI-compatible proxy endpoints can expose hundreds of models and make /v1/models slow. Treating those endpoints like local model servers caused model picker opens and background probes to repeatedly hit /models, producing timeouts and making otherwise usable endpoints appear offline.
Make model endpoint discovery cached-first for normal UI usage, add explicit proxy/API classification and refresh policy fields, exclude proxy/API endpoints from aggressive local probing, and preserve cached models when refresh fails.
Manual Test/Add/Refresh actions still fetch the full model list with longer timeouts so users can intentionally import large proxy model lists without blocking normal model picker usage.
* fix: preserve endpoint ping status semantics
save() called load(), which DECRYPTS every stored key, then re-encrypted
only the key being saved and wrote the whole dict back. The other
providers' keys were thus persisted in plaintext; on the next load()
Fernet raised InvalidToken on them and they were silently dropped.
Add _load_raw() that returns the still-encrypted on-disk dict (reusing the
existing missing/corrupt-file guards) and have save() build on that, so
untouched providers keep their ciphertext. load() now also goes through
_load_raw(), keeping its behavior identical.
Fixes#1914
Co-authored-by: EkaTantra Dev <dev@ekatantra.com>
- Claude Agent integration: AGENT_CONFIGS.claude, INTG_TYPES.claude,
setup_claude_routes + integrations/claude/ skill bundle. Wired in
app.py alongside the existing Codex integration; same scope-gated
/api/codex/* backend; agent form has new description so users know
it's setup for an external CLI, not an agent streamed inside Odysseus.
- Remove mark_email_boundaries action: not good enough yet. Stripped
from task UI, scheduler defaults, registry, tool schema, clear-cache
route. Added to RETIRED_HOUSEKEEPING_ACTIONS so existing rows + their
task_runs auto-purge on startup.
- Cookbook download reliability: "Reconnect" fix button in the crash
diagnosis runs _reconnectTask after probing has-session. 30s confirm
window before marking a download "done" — kills the Finished/Downloading
flicker when tmux briefly drops between captures.
- Mobile UX: tap anywhere on a note card body opens the editor;
Update button morphs to Archive when no text was edited; bell icon
accent-colored; chip-trashing notif pills fade so only the icon
rotates into the trash zone.
- Settings integrations: SVG-per-provider in email + API preset
dropdowns, custom drop-up-aware menus, accent sub-header icons
(IMAP/SMTP), consistent card styling between list + edit, contacts
Edit/Delete icons, agent form description copy.
Validate only token-supplied direct base_url values for API-token chat requests, while keeping admin-configured endpoints available for local/LAN providers.
Scope configured endpoint fallback selection to the API token owner, fail closed for unknown token owners, and preserve strict session ownership checks when resuming sessions from chat-scoped API tokens.
Add focused regression coverage for direct base_url SSRF rejection, configured endpoint fallback behavior, token-owner scoping, URL validation, and null-owner session/endpoint handling.
parse_markdown_to_values — the read-back path for export-pdf, the export
preview, and prepare-signed-reply — matched the bold field label with [^*]+, so
it could not match a label containing '*' (the near-universal required-field
marker: "Email *", "State *", "Signature *"). The value then stayed empty, so
the exported PDF and the signed-reply attachment came out blank for that field
with no error — a whole form of required fields could export completely empty.
Match the label non-greedily (.+?) so '*' in labels is tolerated while still
splitting at the first ':**' / '**[', which also preserves a value that itself
contains ':**'.
Adds tests/test_form_markdown_roundtrip.py (render -> parse roundtrip): asterisk
text/choice/signature labels survive (fail before, pass after); plain labels and
colon-bearing values are unaffected.
Co-authored-by: NubsCarson <nubs@nubs.site>
If session.initialize() or list_tools() raises after the stdio
subprocess or SSE connection is already open, the AsyncExitStack is
never closed — leaking the child process or HTTP connection. Wrap the
setup phase in try/except to aclose() the stack before re-raising.
PermissionError was not in the except tuple so an unreadable settings.json
would crash the app instead of falling back to defaults. Added alongside the
existing FileNotFoundError/JSONDecodeError/ValueError catches.
Also adds test_settings_error_paths.py covering all four failure modes:
missing file, corrupted JSON, wrong type, and permission denied.
Gemma 4 returns reasoning_content in streaming responses via
llama-server, but the model wasn't listed in _THINKING_MODEL_PATTERNS,
causing reasoning tokens to be mishandled. Add "gemma" to the pattern
list and register Gemma 4's 128K context window in KNOWN_CONTEXT_WINDOWS
so the agent loop budgets context correctly.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
A native function/tool call whose `arguments` field is valid JSON but not an
object — a bare array like ["ls -la"], or a string/number/bool/null — parsed
fine in function_call_to_tool_block and then every branch called args.get(...),
raising AttributeError ('list'/'str' object has no attribute 'get'). That
propagated out of the streamed agent loop (no surrounding try/except at the
call site in stream_agent_loop) and aborted the user's entire turn. Weaker and
local models routinely emit malformed args like this.
Coerce non-dict parsed arguments to {} (mirrors the existing empty-arguments
behavior), so the tool runs with empty args instead of killing the stream.
Adds tests/test_function_call_non_object_args.py covering array/string/number/
bool/null arguments — they fail before this change and pass after.
datetime.utcnow() is deprecated in Python 3.12 and removed in 3.14.
Swap the five calls in src/cleanup_service.py for a local _utcnow()
helper returning naive UTC, matching the naive DateTime columns the
archive/delete cutoffs compare against (same approach as the
task-scheduler and core-database slices). Add a regression test
asserting the helper stays naive so the cutoff math can't hit a
naive/aware TypeError.
Part of #1116
